created by: @dunder_bird
inspired by: gputable.dev · Brandon @burcs
ModelTable - LLM prices · all providers
1835 rows. Prices USD / 1M tokens.
Get started: OpenRouter
| Model | Via | $/M in | $/M out | Cache R | Cache W | Blend | vs cheapest | Ctx | |
|---|---|---|---|---|---|---|---|---|---|
| Dots3-Note Preview | Atlas Cloud | free | free | — | — | free | — | 512k | src |
| Dots3-Note Preview (free) | — | free | free | — | — | free | — | 512k | src |
| Free Models Router | — | free | free | — | — | free | — | 200k | src |
| Gemma 4 26B A4B | Google AI Studio | free | free | — | — | free | cheapest | 262k | src |
| Gemma 4 26B A4B (free) | — | free | free | — | — | free | — | 262k | src |
| Gemma 4 31B | Google AI Studio | free | free | — | — | free | cheapest | 262k | src |
| Gemma 4 31B (free) | — | free | free | — | — | free | — | 262k | src |
| Inkling | Thinking Machines | free | free | — | — | free | -100% vs Vercel AI Gateway | 1.0M | src |
| Inkling (free) | — | free | free | — | — | free | — | 1.0M | src |
| Inkling Small | Thinking Machines | free | free | — | — | free | -100% vs Vercel AI Gateway | 1.0M | src |
| Inkling Small (free) | — | free | free | — | — | free | — | 1.0M | src |
| Laguna S 2.1 | Poolside | free | free | — | — | free | -100% vs Vercel AI Gateway | 262k | src |
| Laguna S 2.1 (free) | — | free | free | — | — | free | — | 262k | src |
| Laguna XS 2.1 | Poolside | free | free | — | — | free | cheapest | 262k | src |
| Laguna XS 2.1 (free) | — | free | free | — | — | free | — | 262k | src |
| LFM2.5-2.6B | Liquid | free | free | — | — | free | — | 66k | src |
| LFM2.5-2.6B (free) | — | free | free | — | — | free | — | 66k | src |
| Nemotron 3 Nano Omni | Nvidia | free | free | — | — | free | — | 256k | src |
| Nemotron 3 Nano Omni (free) | — | free | free | — | — | free | — | 256k | src |
| Nemotron 3 Super | Nvidia | free | free | — | — | free | cheapest | 262k | src |
| Nemotron 3 Super (free) | — | free | free | — | — | free | — | 262k | src |
| Nemotron 3 Ultra | Nvidia | free | free | — | — | free | cheapest | 1M | src |
| Nemotron 3 Ultra (free) | — | free | free | — | — | free | — | 1M | src |
| Nemotron 3.5 Content Safety | Nvidia | free | free | — | — | free | cheapest | 128k | src |
| Nemotron 3.5 Content Safety (free) | — | free | free | — | — | free | — | 128k | src |
| Nemotron 3.5 Lightning | Nvidia | free | free | — | — | free | cheapest | 1M | src |
| Nemotron 3.5 Lightning (free) | — | free | free | — | — | free | — | 1M | src |
| Nemotron 3.5 Super VL | Nvidia | free | free | — | — | free | cheapest | 1M | src |
| Nemotron 3.5 Super VL (free) | — | free | free | — | — | free | — | 1M | src |
| North Mini Code | Cohere | free | free | — | — | free | — | 256k | src |
| North Mini Code (free) | — | free | free | — | — | free | — | 256k | src |
| Xing4.0 29B A4B | Phala | free | free | — | — | free | — | 262k | src |
| Xing4.0 29B A4B (free) | — | free | free | — | — | free | — | 262k | src |
| Extract | — | $0.040 | free | — | — | $0.010 | cheapest | 1M | src |
| Extract | Scale Down | $0.040 | free | — | — | $0.010 | cheapest | 1M | src |
| Summarize | — | $0.040 | free | — | — | $0.010 | cheapest | 1M | src |
| Summarize | Scale Down | $0.040 | free | — | — | $0.010 | cheapest | 1M | src |
| Mistral Nemo | Io Net | $0.017 | $0.022 | $0.011 | — | $0.020 | cheapest | 128k | src |
| Mistral Nemo | Deka LLM | $0.018 | $0.030 | — | — | $0.027 | cheapest | 131k | src |
| Mistral Nemo | — | $0.029 | $0.030 | — | — | $0.030 | cheapest | 131k | src |
| Mistral Nemo | DeepInfra | $0.029 | $0.030 | — | — | $0.030 | cheapest | 131k | src |
| Mistral Nemo | Parasail | $0.030 | $0.030 | — | — | $0.030 | cheapest | 131k | src |
| DeepSeek V4 Flash 0423 | Baidu | $0.018 | $0.036 | $0.0036 | — | $0.032 | cheapest | 1.0M | src |
| Llama 3.1 8B Instruct | DeepInfra | $0.020 | $0.040 | — | — | $0.035 | cheapest | 131k | src |
| Llama 3.1 8B Instruct | Novita | $0.020 | $0.050 | — | — | $0.043 | cheapest | 16k | src |
| Gemma 3 4B | Parasail | $0.040 | $0.050 | $0.020 | — | $0.048 | cheapest | 131k | src |
| Llama 3 8B Lunaris | — | $0.040 | $0.050 | — | — | $0.048 | cheapest | 8k | src |
| Llama 3 8B Lunaris | Parasail | $0.040 | $0.050 | — | — | $0.048 | cheapest | 8k | src |
| Llama 3 8B Lunaris | DeepInfra | $0.040 | $0.050 | — | — | $0.048 | cheapest | 8k | src |
| DeepSeek V4 Flash 0423 | StreamLake | $0.028 | $0.056 | $0.0056 | — | $0.049 | cheapest | 1.0M | src |
| Ling 3.0 Flash | — | $0.021 | $0.063 | $0.0042 | — | $0.052 | 0% vs Vercel AI Gateway | 262k | src |
| Ling 3.0 Flash | Novita | $0.021 | $0.063 | $0.0042 | — | $0.052 | 0% vs Vercel AI Gateway | 262k | src |
| gpt-oss-20b | — | $0.018 | $0.090 | $0.0090 | — | $0.072 | cheapest | 131k | src |
| gpt-oss-20b | Darkbloom | $0.018 | $0.090 | $0.0090 | — | $0.072 | cheapest | 131k | src |
| Llama 3.1 8B Instruct | — | $0.050 | $0.080 | $0.025 | — | $0.072 | cheapest | 131k | src |
| Llama 3.1 8B Instruct | Groq | $0.050 | $0.080 | $0.025 | — | $0.072 | cheapest | 131k | src |
| Mistral Small 3 | — | $0.050 | $0.080 | — | — | $0.072 | cheapest | 33k | src |
| Mistral Small 3 | DeepInfra | $0.050 | $0.080 | — | — | $0.072 | cheapest | 33k | src |
| Ministral 3 8B 2512 | Mistral | $0.075 | $0.075 | $0.0075 | — | $0.075 | cheapest | 262k | src |
| Ministral 3 8B 2512 (batch) | — | $0.075 | $0.075 | $0.0075 | — | $0.075 | cheapest | 262k | src |
| gpt-oss-20b | AkashML | $0.020 | $0.100 | — | — | $0.080 | cheapest | 131k | src |
| Nex-N2.5-Mini | — | $0.025 | $0.100 | $0.0025 | — | $0.081 | cheapest | 262k | src |
| Nex-N2.5-Mini | Nex AGI | $0.025 | $0.100 | $0.0025 | — | $0.081 | cheapest | 262k | src |
| Gemma 3 4B | — | $0.050 | $0.100 | — | — | $0.087 | cheapest | 131k | src |
| Gemma 3 4B | DeepInfra | $0.050 | $0.100 | — | — | $0.087 | cheapest | 131k | src |
| Granite 4.0 Micro | — | $0.017 | $0.112 | — | — | $0.088 | cheapest | 131k | src |
| Granite 4.0 Micro | Cloudflare | $0.017 | $0.112 | — | — | $0.088 | cheapest | 131k | src |
| gpt-oss-20b | DeepInfra | $0.024 | $0.112 | — | — | $0.090 | cheapest | 131k | src |
| gpt-oss-20b (batch) | — | $0.024 | $0.112 | — | — | $0.090 | cheapest | 131k | src |
| Nemotron 3.5 Lightning | Darkbloom | $0.025 | $0.120 | $0.013 | — | $0.096 | cheapest | 262k | src |
| Phi 4 | DeepInfra | $0.056 | $0.112 | — | — | $0.098 | cheapest | 16k | src |
| Gemma 3 12B | DeepInfra | $0.040 | $0.120 | — | — | $0.100 | +14% vs Novita | 131k | src |
| Ministral 3 3B 2512 | — | $0.100 | $0.100 | $0.010 | — | $0.100 | cheapest | 131k | src |
| Ministral 3 3B 2512 | Mistral | $0.100 | $0.100 | $0.010 | — | $0.100 | cheapest | 131k | src |
| Reka Edge | — | $0.100 | $0.100 | — | — | $0.100 | cheapest | 16k | src |
| Reka Edge | Reka | $0.100 | $0.100 | — | — | $0.100 | cheapest | 16k | src |
| MythoMax 13B | — | $0.080 | $0.110 | — | — | $0.102 | cheapest | 8k | src |
| MythoMax 13B | Parasail | $0.080 | $0.110 | — | — | $0.102 | cheapest | 4k | src |
| gpt-oss-20b | Core Weave | $0.030 | $0.130 | $0.030 | — | $0.105 | cheapest | 131k | src |
| Laguna XS 2.1 | — | $0.060 | $0.120 | $0.030 | — | $0.105 | cheapest | 262k | src |
| Laguna XS 2.1 | Poolside | $0.060 | $0.120 | $0.030 | — | $0.105 | cheapest | 262k | src |
| Qwen3.7 Flash | — | $0.030 | $0.130 | $0.0060 | $0.038 | $0.105 | cheapest | 1M | src |
| Qwen3.7 Flash | Alibaba | $0.030 | $0.130 | $0.0060 | $0.038 | $0.105 | cheapest | 1M | src |
| gpt-oss-120b | DeepInfra | $0.030 | $0.136 | — | — | $0.109 | cheapest | 131k | src |
| gpt-oss-120b (batch) | — | $0.030 | $0.136 | — | — | $0.109 | cheapest | 131k | src |
| Ministral 3 3B 2512 | Mistral mistral/eu | $0.110 | $0.110 | $0.011 | — | $0.110 | cheapest | 131k | src |
| Nemotron 3.5 Lightning | Io Net | $0.047 | $0.134 | $0.023 | — | $0.112 | cheapest | 262k | src |
| gpt-oss-20b | Deka LLM | $0.029 | $0.140 | $0.029 | — | $0.112 | cheapest | 131k | src |
| gpt-oss-20b | DeepInfra | $0.030 | $0.140 | — | — | $0.113 | cheapest | 131k | src |
| Nova Micro 1.0 | — | $0.035 | $0.140 | — | — | $0.114 | cheapest | 128k | src |
| Nova Micro 1.0 | Bedrock | $0.035 | $0.140 | — | — | $0.114 | cheapest | 128k | src |
| Qwen3.5-9B | Darkbloom | $0.080 | $0.130 | $0.040 | — | $0.117 | cheapest | 262k | src |
| gpt-oss-120b | Near AI | $0.030 | $0.150 | $0.015 | — | $0.120 | cheapest | 131k | src |
| gpt-oss-120b | Venice | $0.030 | $0.150 | $0.030 | — | $0.120 | cheapest | 128k | src |
| gpt-oss-20b | Parasail | $0.030 | $0.150 | $0.020 | — | $0.120 | cheapest | 131k | src |
| Schematron V2 Turbo | — | $0.030 | $0.150 | $0.030 | — | $0.120 | 0% vs Vercel AI Gateway | 128k | src |
| Schematron V2 Turbo | Inference Net | $0.030 | $0.150 | $0.030 | — | $0.120 | 0% vs Vercel AI Gateway | 128k | src |
| Qwen3.7 Flash | Alibaba alibaba/us-east-1 | $0.035 | $0.149 | $0.0069 | — | $0.121 | cheapest | 1M | src |
| Command R7B (12-2024) | — | $0.037 | $0.150 | — | — | $0.122 | cheapest | 128k | src |
| Command R7B (12-2024) | Cohere | $0.037 | $0.150 | — | — | $0.122 | cheapest | 128k | src |
| Mercury 2.5 | — | $0.040 | $0.150 | $0.0040 | — | $0.122 | 0% vs Vercel AI Gateway | 260k | src |
| Mercury 2.5 | Inception | $0.040 | $0.150 | $0.0040 | — | $0.122 | 0% vs Vercel AI Gateway | 260k | src |
| Phi 4 | — | $0.070 | $0.140 | — | — | $0.122 | cheapest | 16k | src |
| Phi 4 | DeepInfra bf16 | $0.070 | $0.140 | — | — | $0.122 | cheapest | 16k | src |
| DeepSeek V4.1 Flash | Sail Research | $0.050 | $0.150 | $0.0040 | — | $0.125 | cheapest | 1.0M | src |
| DeepSeek V4.1 Flash (batch) | — | $0.050 | $0.150 | $0.0040 | — | $0.125 | cheapest | 1.0M | src |
| Gemma 3 12B | — | $0.050 | $0.150 | — | — | $0.125 | +43% vs Novita | 131k | src |
| Gemma 3 12B | Next Bit | $0.050 | $0.150 | — | — | $0.125 | +43% vs Novita | 131k | src |
| Gemma 3 12B | DeepInfra bf16 | $0.050 | $0.150 | — | — | $0.125 | +43% vs Novita | 131k | src |
| gpt-oss-20b | Bedrock | $0.070 | $0.150 | — | — | $0.130 | cheapest | 131k | src |
| gpt-oss-120b | Core Weave | $0.030 | $0.170 | $0.030 | — | $0.135 | cheapest | 131k | src |
| Nemotron 3.5 Lightning | DeepInfra | $0.060 | $0.160 | $0.030 | — | $0.135 | cheapest | 262k | src |
| gpt-oss-120b | DeepInfra | $0.037 | $0.170 | — | — | $0.137 | cheapest | 131k | src |
| Granite 4.2 8B | Core Weave | $0.100 | $0.150 | $0.050 | — | $0.138 | cheapest | 131k | src |
| Qwen3.5-9B | — | $0.100 | $0.150 | — | — | $0.138 | cheapest | 262k | src |
| Qwen3.5-9B | Silicon Flow | $0.100 | $0.150 | — | — | $0.138 | cheapest | 262k | src |
| Qwen3.5-9B | DeepInfra | $0.100 | $0.150 | — | — | $0.138 | cheapest | 262k | src |
| Qwen3.5-9B | Venice | $0.100 | $0.150 | — | — | $0.138 | cheapest | 256k | src |
| Gemma 3 27B | DeepInfra | $0.080 | $0.160 | — | — | $0.140 | cheapest | 131k | src |
| gpt-oss-120b | Deka LLM | $0.030 | $0.180 | $0.030 | — | $0.142 | cheapest | 131k | src |
| Hy-MT2-1.8B | — | $0.044 | $0.177 | — | — | $0.144 | cheapest | 8k | src |
| Hy-MT2-1.8B | Tencent | $0.044 | $0.177 | — | — | $0.144 | cheapest | 8k | src |
| Llama Guard 4 12B | DeepInfra | $0.144 | $0.144 | — | — | $0.144 | cheapest | 164k | src |
| gpt-oss-20b | Silicon Flow | $0.040 | $0.180 | — | — | $0.145 | cheapest | 131k | src |
| GLM 5.3 Flash | Sail Research | $0.050 | $0.180 | $0.010 | — | $0.147 | cheapest | 1.0M | src |
| GLM 5.3 Flash (batch) | — | $0.050 | $0.180 | $0.010 | — | $0.147 | cheapest | 1.0M | src |
| gpt-oss-120b | AkashML | $0.030 | $0.187 | $0.030 | — | $0.148 | cheapest | 131k | src |
| DeepSeek V4 Flash 0731 | Baidu | $0.060 | $0.180 | $0.0019 | — | $0.150 | +12% vs Vercel AI Gateway | 1.0M | src |
| DeepSeek V4 Flash 0731 | DeepInfra | $0.060 | $0.180 | $0.015 | — | $0.150 | +12% vs Vercel AI Gateway | 1.0M | src |
| Ling 3.0 Flash | DeepInfra | $0.060 | $0.180 | $0.012 | — | $0.150 | +186% vs Vercel AI Gateway | 131k | src |
| Ling 3.0 Flash VL | — | $0.060 | $0.180 | $0.012 | — | $0.150 | cheapest | 131k | src |
| Ling 3.0 Flash VL | DeepInfra | $0.060 | $0.180 | $0.012 | — | $0.150 | cheapest | 131k | src |
| Ministral 3 8B 2512 | — | $0.150 | $0.150 | $0.015 | — | $0.150 | cheapest | 262k | src |
| Ministral 3 8B 2512 | Mistral | $0.150 | $0.150 | $0.015 | — | $0.150 | cheapest | 262k | src |
| Mistral Nemo | Mistral | $0.150 | $0.150 | $0.015 | — | $0.150 | cheapest | 131k | src |
| GPT-5 Nano | OpenAI | $0.025 | $0.200 | $0.0025 | — | $0.156 | cheapest | 400k | src |
| GPT-5 Nano | OpenAI | $0.025 | $0.200 | $0.0025 | — | $0.156 | cheapest | 400k | src |
| GPT-5 Nano (batch) | — | $0.025 | $0.200 | $0.0025 | — | $0.156 | cheapest | 400k | src |
| DeepSeek V4 Flash 0423 | DeepInfra | $0.090 | $0.180 | $0.018 | — | $0.158 | cheapest | 1.0M | src |
| DeepSeek V4.1 Flash | Decart | $0.090 | $0.180 | $0.018 | — | $0.158 | cheapest | 1.0M | src |
| Laguna S 2.1 | — | $0.090 | $0.180 | $0.0090 | — | $0.158 | 0% vs Vercel AI Gateway | 1.0M | src |
| Laguna S 2.1 | Poolside | $0.090 | $0.180 | $0.0090 | — | $0.158 | 0% vs Vercel AI Gateway | 1.0M | src |
| Llama 3.2 1B Instruct | — | $0.027 | $0.201 | — | — | $0.158 | cheapest | 60k | src |
| Llama 3.2 1B Instruct | Cloudflare | $0.027 | $0.201 | — | — | $0.158 | cheapest | 60k | src |
| DeepSeek V4 Flash 0423 | — | $0.091 | $0.182 | $0.018 | — | $0.159 | cheapest | 1.0M | src |
| DeepSeek V4 Flash 0423 | GMI Cloud | $0.091 | $0.182 | $0.018 | — | $0.159 | cheapest | 1.0M | src |
| Gemma 4 26B A4B | Makora | $0.100 | $0.180 | $0.050 | — | $0.160 | cheapest | 256k | src |
| Gemini 2.5 Flash Lite | Google AI Studio | $0.050 | $0.200 | $0.0050 | $0.042 | $0.163 | cheapest | 1.0M | src |
| Gemini 2.5 Flash Lite | Google AI Studio | $0.050 | $0.200 | $0.010 | — | $0.163 | cheapest | 1.0M | src |
| Gemini 2.5 Flash Lite | $0.050 | $0.200 | $0.010 | — | $0.163 | cheapest | 1.0M | src | |
| Gemini 2.5 Flash Lite (batch) | — | $0.050 | $0.200 | $0.010 | — | $0.163 | cheapest | 1.0M | src |
| GPT-4.1 Nano | OpenAI | $0.050 | $0.200 | $0.013 | — | $0.163 | cheapest | 1.0M | src |
| GPT-4.1 Nano (batch) | — | $0.050 | $0.200 | $0.013 | — | $0.163 | cheapest | 1.0M | src |
| Nemotron 3 Nano 30B A3B | Novita | $0.050 | $0.200 | — | — | $0.163 | 0% vs Vercel AI Gateway | 262k | src |
| Solar Mini 4 | — | $0.050 | $0.200 | $0.0050 | — | $0.163 | cheapest | 524k | src |
| Solar Mini 4 | Upstage | $0.050 | $0.200 | $0.0050 | — | $0.163 | cheapest | 524k | src |
| GLM 5.3 Flash | DeepInfra | $0.060 | $0.200 | $0.012 | — | $0.165 | cheapest | 1.0M | src |
| Ministral 3 8B 2512 | Mistral mistral/eu | $0.165 | $0.165 | $0.017 | — | $0.165 | cheapest | 262k | src |
| Nemotron 3.5 Lightning | — | $0.070 | $0.200 | $0.040 | — | $0.168 | cheapest | 262k | src |
| Nemotron 3.5 Lightning | Core Weave | $0.070 | $0.200 | $0.040 | — | $0.168 | cheapest | 262k | src |
| DeepSeek V4 Flash 0423 | Venice | $0.097 | $0.193 | $0.020 | — | $0.169 | cheapest | 1M | src |
| Mistral Small 3.2 24B | DeepInfra | $0.075 | $0.200 | — | — | $0.169 | cheapest | 128k | src |
| DeepSeek V4 Flash 0423 | DigitalOcean | $0.098 | $0.196 | $0.020 | — | $0.172 | cheapest | 1.0M | src |
| Muse Spark 1.2 Contributor | — | $0.100 | $0.200 | $0.0020 | — | $0.175 | 0% vs Vercel AI Gateway | 1.0M | src |
| Muse Spark 1.2 Contributor | Meta | $0.100 | $0.200 | $0.0020 | — | $0.175 | 0% vs Vercel AI Gateway | 1.0M | src |
| Muse Spark 1.3 Contributor | — | $0.100 | $0.200 | $0.0020 | — | $0.175 | 0% vs Vercel AI Gateway | 1.0M | src |
| Muse Spark 1.3 Contributor | Meta | $0.100 | $0.200 | $0.0020 | — | $0.175 | 0% vs Vercel AI Gateway | 1.0M | src |
| Qwen2.5 7B Instruct | — | $0.100 | $0.200 | — | — | $0.175 | cheapest | 33k | src |
| Qwen2.5 7B Instruct | Phala | $0.100 | $0.200 | — | — | $0.175 | cheapest | 33k | src |
| Reka Flash 3 | — | $0.100 | $0.200 | — | — | $0.175 | cheapest | 66k | src |
| Reka Flash 3 | Reka | $0.100 | $0.200 | — | — | $0.175 | cheapest | 66k | src |
| UI-TARS 7B | — | $0.100 | $0.200 | $0.100 | — | $0.175 | cheapest | 128k | src |
| UI-TARS 7B | Parasail | $0.100 | $0.200 | $0.100 | — | $0.175 | cheapest | 128k | src |
| Gemma 4 26B A4B | Darkbloom | $0.042 | $0.220 | $0.021 | — | $0.175 | cheapest | 131k | src |
| Gemma 3 27B | Novita | $0.119 | $0.200 | — | — | $0.180 | cheapest | 98k | src |
| Llama Guard 4 12B | — | $0.180 | $0.180 | — | — | $0.180 | cheapest | 164k | src |
| Llama Guard 4 12B | DeepInfra bf16 | $0.180 | $0.180 | — | — | $0.180 | cheapest | 164k | src |
| Schematron V2 Small | — | $0.050 | $0.230 | $0.050 | — | $0.185 | 0% vs Vercel AI Gateway | 128k | src |
| Schematron V2 Small | Inference Net | $0.050 | $0.230 | $0.050 | — | $0.185 | 0% vs Vercel AI Gateway | 128k | src |
| Gemma 4 26B A4B | — | $0.068 | $0.225 | $0.037 | — | $0.186 | cheapest | 262k | src |
| Gemma 4 26B A4B | Next Bit | $0.068 | $0.225 | $0.037 | — | $0.186 | cheapest | 262k | src |
| Ling 3.1 Flash | — | $0.075 | $0.225 | $0.015 | — | $0.188 | cheapest | 262k | src |
| Ling 3.1 Flash | Novita | $0.075 | $0.225 | $0.015 | — | $0.188 | cheapest | 262k | src |
| Qwen3 14B | Next Bit | $0.100 | $0.220 | — | — | $0.190 | cheapest | 41k | src |
| Nemotron 3 Nano 30B A3B | — | $0.060 | $0.240 | — | — | $0.195 | +20% vs Vercel AI Gateway | 262k | src |
| Nemotron 3 Nano 30B A3B | Nebius | $0.060 | $0.240 | — | — | $0.195 | +20% vs Vercel AI Gateway | 262k | src |
| Nova Lite 1.0 | — | $0.060 | $0.240 | — | — | $0.195 | cheapest | 300k | src |
| Nova Lite 1.0 | Bedrock | $0.060 | $0.240 | — | — | $0.195 | cheapest | 300k | src |
| Claude Haiku 5.5 | Anthropic | $0.050 | $0.250 | $0.0050 | $0.063 | $0.200 | cheapest | 1M | src |
| Claude Haiku 5.5 (batch) | — | $0.050 | $0.250 | $0.0050 | $0.063 | $0.200 | cheapest | 1M | src |
| GPT-6 Luna | OpenAI | $0.050 | $0.250 | $0.0050 | $0.063 | $0.200 | cheapest | 1.1M | src |
| GPT-6 Luna | OpenAI | $0.050 | $0.250 | $0.0050 | $0.063 | $0.200 | cheapest | 1.1M | src |
| GPT-6 Luna (batch) | — | $0.050 | $0.250 | $0.0050 | $0.063 | $0.200 | cheapest | 1.1M | src |
| GPT-6 Luna Pro | OpenAI | $0.050 | $0.250 | $0.0050 | $0.063 | $0.200 | cheapest | 1.1M | src |
| GPT-6 Luna Pro | OpenAI | $0.050 | $0.250 | $0.0050 | $0.063 | $0.200 | cheapest | 1.1M | src |
| GPT-6 Luna Pro (batch) | — | $0.050 | $0.250 | $0.0050 | $0.063 | $0.200 | cheapest | 1.1M | src |
| gpt-oss-120b | Crusoe | $0.050 | $0.250 | $0.050 | — | $0.200 | cheapest | 131k | src |
| gpt-oss-120b | Mancer 2 | $0.050 | $0.250 | — | — | $0.200 | cheapest | 131k | src |
| gpt-oss-120b | Novita | $0.050 | $0.250 | — | — | $0.200 | cheapest | 131k | src |
| Llama 4 Scout | DeepInfra | $0.080 | $0.240 | — | — | $0.200 | cheapest | 328k | src |
| Ministral 3 14B 2512 | — | $0.200 | $0.200 | $0.020 | — | $0.200 | cheapest | 262k | src |
| Ministral 3 14B 2512 | Mistral | $0.200 | $0.200 | $0.020 | — | $0.200 | cheapest | 262k | src |
| Nemotron 3.5 Content Safety | — | $0.200 | $0.200 | — | — | $0.200 | cheapest | 131k | src |
| Nemotron 3.5 Content Safety | DeepInfra | $0.200 | $0.200 | — | — | $0.200 | cheapest | 131k | src |
| Granite 4.2 8B | — | $0.060 | $0.250 | $0.015 | — | $0.203 | cheapest | 131k | src |
| Granite 4.2 8B | DeepInfra | $0.060 | $0.250 | $0.015 | — | $0.203 | cheapest | 131k | src |
| DeepSeek V4 Flash 0731 | Wafer | $0.130 | $0.230 | $0.125 | — | $0.205 | +53% vs Vercel AI Gateway | 1.0M | src |
| gpt-oss-20b | $0.070 | $0.250 | — | — | $0.205 | cheapest | 131k | src | |
| GLM 5.3 Flash | StreamLake | $0.075 | $0.250 | $0.015 | — | $0.206 | cheapest | 1.0M | src |
| GLM 5.3 Flash | DeepInfra | $0.075 | $0.250 | $0.015 | — | $0.206 | cheapest | 1.0M | src |
| Nex-N2.5-Pro | — | $0.075 | $0.250 | $0.015 | — | $0.206 | cheapest | 262k | src |
| Nex-N2.5-Pro | Nex AGI | $0.075 | $0.250 | $0.015 | — | $0.206 | cheapest | 262k | src |
| DeepSeek V4 Flash 0731 | DigitalOcean | $0.119 | $0.238 | $0.024 | — | $0.208 | +56% vs Vercel AI Gateway | 1.0M | src |
| MiMo-V2.5 | GMI Cloud | $0.119 | $0.238 | $0.0026 | — | $0.208 | cheapest | 1.1M | src |
| Qwen3 14B | — | $0.120 | $0.240 | — | — | $0.210 | cheapest | 41k | src |
| Qwen3 14B | DeepInfra | $0.120 | $0.240 | — | — | $0.210 | cheapest | 41k | src |
| Mistral Small 3.2 24B | — | $0.094 | $0.250 | — | — | $0.211 | cheapest | 256k | src |
| Mistral Small 3.2 24B | Venice | $0.094 | $0.250 | — | — | $0.211 | cheapest | 256k | src |
| Qwen3.5-Flash | — | $0.065 | $0.260 | — | — | $0.211 | cheapest | 1M | src |
| Qwen3.5-Flash | Alibaba | $0.065 | $0.260 | — | — | $0.211 | cheapest | 1M | src |
| Qwen3.5-9B | Parasail | $0.100 | $0.250 | — | — | $0.212 | cheapest | 262k | src |
| DeepSeek V4 Flash 0731 | StreamLake | $0.088 | $0.264 | $0.0028 | — | $0.220 | +64% vs Vercel AI Gateway | 1.0M | src |
| Llama 3.1 8B Instruct | Core Weave | $0.220 | $0.220 | $0.220 | — | $0.220 | cheapest | 131k | src |
| Ministral 3 14B 2512 | Mistral mistral/eu | $0.220 | $0.220 | $0.022 | — | $0.220 | cheapest | 262k | src |
| GLM 5.3 Flash | Decart | $0.083 | $0.275 | $0.017 | — | $0.227 | cheapest | 1.0M | src |
| DeepSeek V4 Flash 0731 | Baseten | $0.130 | $0.260 | $0.028 | — | $0.228 | +70% vs Vercel AI Gateway | 1.0M | src |
| DeepSeek V4 Flash 0731 | Venice | $0.130 | $0.260 | $0.028 | — | $0.228 | +70% vs Vercel AI Gateway | 1M | src |
| Qwen3 Coder 30B A3B Instruct | — | $0.070 | $0.280 | — | — | $0.228 | cheapest | 262k | src |
| Qwen3 Coder 30B A3B Instruct | Silicon Flow | $0.070 | $0.280 | — | — | $0.228 | cheapest | 262k | src |
| Qwen3 32B | — | $0.080 | $0.280 | — | — | $0.230 | cheapest | 131k | src |
| Qwen3 32B | DeepInfra | $0.080 | $0.280 | — | — | $0.230 | cheapest | 41k | src |
| Qwen3.5-9B | Together | $0.170 | $0.250 | — | — | $0.230 | cheapest | 262k | src |
| GLM 5.3 Flash | Novita | $0.084 | $0.280 | $0.017 | — | $0.231 | cheapest | 1.0M | src |
| MiMo-V2.6-Flash | DeepInfra | $0.133 | $0.266 | $0.0027 | — | $0.233 | cheapest | 1.0M | src |
| MiMo-V2.6-Flash | Darkbloom | $0.100 | $0.280 | $0.050 | — | $0.235 | cheapest | 1.0M | src |
| Hy-MT2-30B-A3B | — | $0.074 | $0.295 | — | — | $0.240 | cheapest | 8k | src |
| Hy-MT2-30B-A3B | Tencent | $0.074 | $0.295 | — | — | $0.240 | cheapest | 8k | src |
| Hy-MT2-7B | — | $0.074 | $0.295 | — | — | $0.240 | cheapest | 8k | src |
| Hy-MT2-7B | Tencent | $0.074 | $0.295 | — | — | $0.240 | cheapest | 8k | src |
| DeepSeek V4 Flash 0423 | Silicon Flow | $0.130 | $0.280 | $0.028 | — | $0.242 | cheapest | 1.0M | src |
| DeepSeek V4 Flash 0731 | Core Weave | $0.130 | $0.280 | $0.070 | — | $0.242 | +81% vs Vercel AI Gateway | 262k | src |
| MiMo-V2.6-Flash | Makora | $0.130 | $0.280 | $0.0020 | — | $0.242 | cheapest | 1.0M | src |
| GPT-4o-mini | OpenAI | $0.075 | $0.300 | $0.037 | — | $0.244 | cheapest | 128k | src |
| GPT-4o-mini (batch) | — | $0.075 | $0.300 | $0.037 | — | $0.244 | cheapest | 128k | src |
| gpt-oss-20b | Groq | $0.075 | $0.300 | $0.037 | — | $0.244 | cheapest | 131k | src |
| gpt-oss-safeguard-20b | — | $0.075 | $0.300 | $0.037 | — | $0.244 | 0% vs Groq | 131k | src |
| gpt-oss-safeguard-20b | Groq | $0.075 | $0.300 | $0.037 | — | $0.244 | 0% vs Groq | 131k | src |
| Mistral Small 4 | Mistral | $0.075 | $0.300 | $0.0075 | — | $0.244 | cheapest | 262k | src |
| Mistral Small 4 (batch) | — | $0.075 | $0.300 | $0.0075 | — | $0.244 | cheapest | 262k | src |
| Seed 1.6 Flash | — | $0.075 | $0.300 | — | — | $0.244 | cheapest | 262k | src |
| Seed 1.6 Flash | Seed | $0.075 | $0.300 | — | — | $0.244 | cheapest | 262k | src |
| GLM 5.3 Flash | Sail Research | $0.078 | $0.300 | $0.052 | — | $0.245 | cheapest | 1.0M | src |
| DeepSeek V4 Flash 0423 | Atlas Cloud | $0.140 | $0.280 | $0.028 | — | $0.245 | cheapest | 1.0M | src |
| DeepSeek V4 Flash 0423 | Parasail | $0.140 | $0.280 | $0.070 | — | $0.245 | cheapest | 1.0M | src |
| DeepSeek V4 Flash 0731 | Cohere | $0.140 | $0.280 | $0.070 | — | $0.245 | +83% vs Vercel AI Gateway | 1.0M | src |
| DeepSeek V4 Flash 0731 | Together | $0.140 | $0.280 | $0.030 | — | $0.245 | +83% vs Vercel AI Gateway | 1.0M | src |
| DeepSeek V4 Flash 0731 | Parasail | $0.140 | $0.280 | $0.050 | — | $0.245 | +83% vs Vercel AI Gateway | 1.0M | src |
| MiMo-V2.5 | — | $0.140 | $0.280 | $0.0028 | — | $0.245 | cheapest | 1.1M | src |
| MiMo-V2.5 | Xiaomi | $0.140 | $0.280 | $0.0028 | — | $0.245 | cheapest | 1.0M | src |
| MiMo-V2.6-Flash | — | $0.140 | $0.280 | $0.0028 | — | $0.245 | cheapest | 1.1M | src |
| MiMo-V2.6-Flash | Novita | $0.140 | $0.280 | $0.0028 | — | $0.245 | cheapest | 1.0M | src |
| MiMo-V2.6-Flash | GMI Cloud | $0.140 | $0.280 | $0.0030 | — | $0.245 | cheapest | 1.1M | src |
| MiMo-V2.6-Flash | Xiaomi | $0.140 | $0.280 | $0.0028 | — | $0.245 | cheapest | 1.0M | src |
| DeepSeek V4.1 Flash | Sail Research | $0.090 | $0.300 | $0.0060 | — | $0.247 | cheapest | 1.0M | src |
| GLM 5.3 Flash | GMI Cloud | $0.090 | $0.300 | $0.018 | — | $0.247 | cheapest | 1.0M | src |
| Mistral Small 3.2 24B | Parasail | $0.090 | $0.300 | $0.050 | — | $0.247 | cheapest | 131k | src |
| Qwen3 30B A3B Instruct 2507 | Deka LLM | $0.090 | $0.300 | — | — | $0.247 | cheapest | 262k | src |
| Qwen3 30B A3B Instruct 2507 | Silicon Flow | $0.090 | $0.300 | — | — | $0.247 | cheapest | 262k | src |
| DeepSeek V4 Flash 0731 | Sail Research | $0.100 | $0.300 | $0.030 | — | $0.250 | +87% vs Vercel AI Gateway | 1.0M | src |
| Gemma 3 27B | Nebius | $0.100 | $0.300 | — | — | $0.250 | cheapest | 110k | src |
| Gemma 4 26B A4B | Core Weave | $0.100 | $0.300 | $0.050 | — | $0.250 | cheapest | 262k | src |
| Gemma 4 26B A4B | Cloudflare | $0.100 | $0.300 | $0.050 | — | $0.250 | cheapest | 256k | src |
| Llama 4 Scout | — | $0.100 | $0.300 | — | — | $0.250 | cheapest | 1.3M | src |
| Llama 4 Scout | DeepInfra fp8 | $0.100 | $0.300 | — | — | $0.250 | cheapest | 328k | src |
| Mistral Small 3.2 24B | Mistral | $0.100 | $0.300 | $0.010 | — | $0.250 | cheapest | 33k | src |
| Qwen3 30B A3B Instruct 2507 | — | $0.100 | $0.300 | — | — | $0.250 | cheapest | 262k | src |
| Qwen3 30B A3B Instruct 2507 | Nebius | $0.100 | $0.300 | — | — | $0.250 | cheapest | 262k | src |
| Step 3.5 Flash | — | $0.100 | $0.300 | — | — | $0.250 | cheapest | 262k | src |
| Step 3.5 Flash | Silicon Flow | $0.100 | $0.300 | — | — | $0.250 | cheapest | 262k | src |
| Voxtral Small 24B 2507 | — | $0.100 | $0.300 | $0.010 | — | $0.250 | cheapest | 33k | src |
| Voxtral Small 24B 2507 | Mistral | $0.100 | $0.300 | $0.010 | — | $0.250 | cheapest | 33k | src |
| Llama 3.1 8B Instruct | Cloudflare | $0.152 | $0.287 | — | — | $0.253 | cheapest | 32k | src |
| Gemma 4 26B A4B | Io Net | $0.090 | $0.310 | $0.041 | — | $0.255 | cheapest | 262k | src |
| MiMo-V2.6-Flash | Io Net | $0.150 | $0.290 | $0.025 | — | $0.255 | cheapest | 1.0M | src |
| Llama 3.2 3B Instruct | — | $0.050 | $0.330 | — | — | $0.260 | cheapest | 131k | src |
| Llama 3.2 3B Instruct | Parasail | $0.050 | $0.330 | — | — | $0.260 | cheapest | 131k | src |
| DeepSeek V4 Flash 0423 | Alibaba | $0.150 | $0.300 | $0.030 | — | $0.263 | cheapest | 1M | src |
| Gemma 4 26B A4B | Deka LLM | $0.060 | $0.330 | $0.040 | — | $0.263 | cheapest | 262k | src |
| Llama 3.2 3B Instruct | Cloudflare | $0.051 | $0.335 | — | — | $0.264 | cheapest | 80k | src |
| Llama 3.3 70B Instruct | — | $0.100 | $0.320 | — | — | $0.265 | cheapest | 131k | src |
| Llama 3.3 70B Instruct | DeepInfra | $0.100 | $0.320 | — | — | $0.265 | cheapest | 131k | src |
| DeepSeek V4 Flash 0423 | Wafer | $0.580 | $0.170 | $0.013 | — | $0.273 | cheapest | 1.0M | src |
| Gemma 4 26B A4B | DeepInfra | $0.070 | $0.340 | — | — | $0.273 | cheapest | 262k | src |
| Voxtral Small 24B 2507 | Mistral mistral/eu | $0.110 | $0.330 | $0.011 | — | $0.275 | cheapest | 32k | src |
| DeepSeek V4.1 Flash | DeepInfra | $0.112 | $0.336 | $0.0034 | — | $0.280 | cheapest | 1.0M | src |
| DeepSeek V4.1 Flash | DeepInfra | $0.112 | $0.336 | $0.0034 | — | $0.280 | cheapest | 1.0M | src |
| DeepSeek V4.1 Flash 1017 | DeepInfra | $0.112 | $0.336 | $0.0034 | — | $0.280 | cheapest | 1.0M | src |
| Gemma 4 31B | Core Weave | $0.100 | $0.340 | $0.100 | — | $0.280 | cheapest | 262k | src |
| Gemma 4 31B | DeepInfra fp8 | $0.160 | $0.320 | — | — | $0.280 | cheapest | 262k | src |
| Gemma 3 27B | Next Bit | $0.080 | $0.350 | $0.040 | — | $0.282 | cheapest | 131k | src |
| Qwen3 235B A22B Instruct 2507 | GMI Cloud | $0.087 | $0.350 | $0.018 | — | $0.284 | cheapest | 262k | src |
| DeepSeek V3.2 | GMI Cloud | $0.209 | $0.310 | $0.022 | — | $0.284 | cheapest | 164k | src |
| gpt-oss-120b | $0.090 | $0.360 | — | — | $0.292 | cheapest | 131k | src | |
| Solar Pro 4 | — | $0.090 | $0.360 | $0.018 | — | $0.292 | cheapest | 524k | src |
| Solar Pro 4 | Upstage | $0.090 | $0.360 | $0.018 | — | $0.292 | cheapest | 524k | src |
| MiMo-V2.5 | StreamLake | $0.168 | $0.336 | $0.0034 | — | $0.294 | cheapest | 1M | src |
| MiMo-V2.5 | Novita | $0.168 | $0.336 | $0.0034 | — | $0.294 | cheapest | 1.0M | src |
| Gemma 4 31B | Venice | $0.120 | $0.360 | $0.090 | — | $0.300 | cheapest | 256k | src |
| MiMo-V2.6-Flash | Venice | $0.175 | $0.350 | $0.0037 | — | $0.306 | cheapest | 1M | src |
| Gemma 4 31B | Chutes | $0.120 | $0.370 | $0.012 | — | $0.307 | cheapest | 131k | src |
| DeepSeek V4 Pro 0423 | Baidu | $0.177 | $0.355 | $0.015 | — | $0.311 | cheapest | 1.0M | src |
| GPT-5 Nano | — | $0.050 | $0.400 | $0.0050 | — | $0.313 | cheapest | 400k | src |
| GPT-5 Nano | Azure | $0.050 | $0.400 | $0.010 | — | $0.313 | cheapest | 400k | src |
| GPT-5 Nano | OpenAI openai | $0.050 | $0.400 | $0.0050 | — | $0.313 | cheapest | 400k | src |
| GLM 4.7 Flash | Venice | $0.060 | $0.400 | $0.010 | — | $0.315 | cheapest | 128k | src |
| GLM 4.7 Flash | — | $0.060 | $0.400 | — | — | $0.315 | cheapest | 200k | src |
| GLM 4.7 Flash | Cloudflare | $0.060 | $0.400 | — | — | $0.315 | cheapest | 131k | src |
| GLM 4.7 Flash | Novita | $0.070 | $0.400 | $0.010 | — | $0.318 | cheapest | 200k | src |
| GLM 5.3 Flash | Inference Net | $0.120 | $0.388 | $0.032 | — | $0.321 | cheapest | 1.0M | src |
| Nemotron 3 Super | DeepInfra | $0.085 | $0.400 | — | — | $0.321 | cheapest | 262k | src |
| Gemini 2.5 Flash Lite | — | $0.100 | $0.400 | $0.010 | $0.083 | $0.325 | cheapest | 1.0M | src |
| Gemini 2.5 Flash Lite | $0.100 | $0.400 | $0.010 | $0.083 | $0.325 | cheapest | 1.0M | src | |
| Gemini 2.5 Flash Lite | Google AI Studio google-ai-studio | $0.100 | $0.400 | $0.010 | $0.083 | $0.325 | cheapest | 1.0M | src |
| GPT-4.1 Nano | — | $0.100 | $0.400 | $0.025 | — | $0.325 | cheapest | 1.0M | src |
| GPT-4.1 Nano | Azure | $0.100 | $0.400 | $0.030 | — | $0.325 | cheapest | 1.0M | src |
| GPT-4.1 Nano | OpenAI | $0.100 | $0.400 | $0.025 | — | $0.325 | cheapest | 1.0M | src |
| Nemotron 3.5 Super VL | — | $0.100 | $0.400 | $0.080 | — | $0.325 | cheapest | 1.0M | src |
| Nemotron 3.5 Super VL | Crusoe | $0.100 | $0.400 | $0.080 | — | $0.325 | cheapest | 262k | src |
| Nemotron 3.5 Super VL | DeepInfra | $0.100 | $0.400 | $0.080 | — | $0.325 | cheapest | 262k | src |
| Seed-2.0-Mini | — | $0.100 | $0.400 | — | — | $0.325 | cheapest | 262k | src |
| Seed-2.0-Mini | Seed | $0.100 | $0.400 | — | — | $0.325 | cheapest | 262k | src |
| gpt-oss-120b | DigitalOcean | $0.060 | $0.420 | $0.012 | — | $0.330 | cheapest | 128k | src |
| Gemma 4 26B A4B | Venice | $0.130 | $0.400 | $0.050 | — | $0.333 | cheapest | 256k | src |
| Gemma 4 26B A4B | Parasail | $0.130 | $0.400 | $0.050 | — | $0.333 | cheapest | 262k | src |
| Gemma 4 26B A4B | Novita | $0.130 | $0.400 | — | — | $0.333 | cheapest | 262k | src |
| DeepSeek V4 Pro 0813 | Baidu | $0.133 | $0.400 | $0.0042 | — | $0.333 | cheapest | 1.0M | src |
| Llama 3.3 70B Instruct | Novita | $0.135 | $0.400 | — | — | $0.334 | cheapest | 12k | src |
| Gemma 4 26B A4B | Silicon Flow | $0.140 | $0.400 | $0.050 | — | $0.335 | cheapest | 262k | src |
| Gemma 4 31B | Crusoe | $0.140 | $0.400 | $0.140 | — | $0.335 | cheapest | 262k | src |
| Gemma 4 31B | Friendli | $0.140 | $0.400 | — | — | $0.335 | cheapest | 262k | src |
| Gemma 4 31B | Novita | $0.140 | $0.400 | — | — | $0.335 | cheapest | 262k | src |
| Qwen3 32B | Tenstorrent | $0.140 | $0.400 | $0.090 | — | $0.335 | cheapest | 20k | src |
| Gemma 4 31B | Parasail | $0.150 | $0.400 | $0.060 | — | $0.338 | cheapest | 262k | src |
| GPT-5 Nano | Azure azure/swedencentral | $0.055 | $0.440 | $0.011 | — | $0.344 | cheapest | 400k | src |
| DeepSeek V3.2 | DeepInfra | $0.260 | $0.380 | $0.130 | — | $0.350 | cheapest | 164k | src |
| DeepSeek V3.2 | Atlas Cloud | $0.260 | $0.380 | $0.130 | — | $0.350 | cheapest | 164k | src |
| DeepSeek V4.1 Flash | DeepInfra fp8 | $0.140 | $0.420 | $0.0042 | — | $0.350 | cheapest | 1.0M | src |
| DeepSeek V4.1 Flash 1017 | DeepInfra fp8 | $0.140 | $0.420 | $0.0042 | — | $0.350 | cheapest | 1.0M | src |
| Gemma 4 31B | — | $0.200 | $0.400 | — | — | $0.350 | cheapest | 262k | src |
| GLM 5.3 Flash | Phala | $0.128 | $0.425 | $0.025 | — | $0.351 | cheapest | 1.0M | src |
| Gemma 3 27B | — | $0.080 | $0.450 | $0.040 | — | $0.357 | cheapest | 131k | src |
| Gemma 3 27B | Parasail | $0.080 | $0.450 | $0.040 | — | $0.357 | cheapest | 131k | src |
| GPT-4.1 Nano | Azure azure/swedencentral | $0.110 | $0.440 | $0.033 | — | $0.357 | cheapest | 1.0M | src |
| Nemotron 3 Super | — | $0.080 | $0.450 | — | — | $0.357 | cheapest | 262k | src |
| Nemotron 3 Super | Deka LLM | $0.080 | $0.450 | — | — | $0.357 | cheapest | 262k | src |
| DeepSeek V3.2 | Venice | $0.268 | $0.390 | $0.130 | — | $0.360 | cheapest | 160k | src |
| GLM 5.3 Flash | DigitalOcean | $0.131 | $0.438 | $0.030 | — | $0.361 | cheapest | 1.0M | src |
| DeepSeek V4 Pro 0423 | — | $0.209 | $0.418 | $0.017 | — | $0.365 | cheapest | 1.0M | src |
| DeepSeek V4 Pro 0423 | StreamLake | $0.209 | $0.418 | $0.017 | — | $0.365 | cheapest | 1.0M | src |
| Codestral 2508 | Mistral | $0.150 | $0.450 | $0.015 | — | $0.375 | cheapest | 256k | src |
| Codestral 2508 (batch) | — | $0.150 | $0.450 | $0.015 | — | $0.375 | cheapest | 256k | src |
| DeepSeek V3.2 Exp | — | $0.270 | $0.410 | — | — | $0.375 | cheapest | 164k | src |
| DeepSeek V3.2 Exp | Silicon Flow | $0.270 | $0.410 | — | — | $0.375 | cheapest | 164k | src |
| Qwen3.8 27B | Tenstorrent | $0.020 | $0.500 | $0.0090 | — | $0.380 | +17% vs Vercel AI Gateway | 262k | src |
| DeepSeek V3.2 | — | $0.280 | $0.420 | $0.028 | — | $0.385 | cheapest | 164k | src |
| DeepSeek V3.2 | Baidu | $0.280 | $0.420 | $0.028 | — | $0.385 | cheapest | 131k | src |
| GLM 5.3 Flash | Makora | $0.140 | $0.470 | $0.024 | — | $0.388 | cheapest | 1.0M | src |
| Qwen2.5 72B Instruct | — | $0.360 | $0.400 | — | — | $0.390 | cheapest | 33k | src |
| Qwen2.5 72B Instruct | DeepInfra | $0.360 | $0.400 | — | — | $0.390 | cheapest | 33k | src |
| Qwen3.8 Flash | — | $0.150 | $0.470 | $0.016 | — | $0.390 | 0% vs Novita | 1M | src |
| Qwen3.8 Flash | Alibaba | $0.150 | $0.470 | $0.016 | — | $0.390 | 0% vs Novita | 1M | src |
| Qwen3.8 Omni Flash | — | $0.150 | $0.470 | $0.016 | — | $0.390 | cheapest | 1M | src |
| Qwen3.8 Omni Flash | Alibaba | $0.150 | $0.470 | $0.016 | — | $0.390 | cheapest | 1M | src |
| GLM 5.3 Flash | OpenInference | $0.075 | $0.500 | $0.0075 | — | $0.394 | cheapest | 1.0M | src |
| GLM 5.3 Flash | Relace | $0.075 | $0.500 | $0.0075 | — | $0.394 | cheapest | 1.0M | src |
| Ternary Bonsai 2 27B | — | $0.075 | $0.500 | $0.037 | — | $0.394 | cheapest | 262k | src |
| Ternary Bonsai 2 27B | Darkbloom | $0.075 | $0.500 | $0.037 | — | $0.394 | cheapest | 262k | src |
| GLM 5.3 Flash | Near AI | $0.080 | $0.500 | $0.012 | — | $0.395 | cheapest | 1.0M | src |
| Claude Haiku 5.5 | — | $0.100 | $0.500 | $0.010 | $0.125 | $0.400 | cheapest | 1M | src |
| Claude Haiku 5.5 | $0.100 | $0.500 | $0.010 | $0.125 | $0.400 | cheapest | 1M | src | |
| Claude Haiku 5.5 | Claude Platform On AWS | $0.100 | $0.500 | $0.010 | $0.125 | $0.400 | cheapest | 1M | src |
| Claude Haiku 5.5 | Azure | $0.100 | $0.500 | $0.010 | $0.125 | $0.400 | cheapest | 1M | src |
| Claude Haiku 5.5 | Anthropic | $0.100 | $0.500 | $0.010 | $0.125 | $0.400 | cheapest | 1M | src |
| Claude Haiku 5.5 | Bedrock | $0.100 | $0.500 | $0.010 | $0.125 | $0.400 | cheapest | 1M | src |
| Claude Haiku Latest | — | $0.100 | $0.500 | $0.010 | $0.125 | $0.400 | cheapest | 1M | src |
| DeepSeek Flash Latest | — | $0.100 | $0.500 | $0.0020 | — | $0.400 | cheapest | 1.0M | src |
| DeepSeek V4.1 Flash 1017 | Inference Net | $0.100 | $0.500 | $0.0020 | — | $0.400 | cheapest | 262k | src |
| GPT Luna Latest | — | $0.100 | $0.500 | $0.010 | $0.125 | $0.400 | cheapest | 1.1M | src |
| GPT-6 Luna | — | $0.100 | $0.500 | $0.010 | $0.125 | $0.400 | cheapest | 1.1M | src |
| GPT-6 Luna | OpenAI openai | $0.100 | $0.500 | $0.010 | $0.125 | $0.400 | cheapest | 1.1M | src |
| GPT-6 Luna | Azure | $0.100 | $0.500 | $0.010 | $0.125 | $0.400 | cheapest | 1.1M | src |
| GPT-6 Luna Pro | — | $0.100 | $0.500 | $0.010 | $0.125 | $0.400 | cheapest | 1.1M | src |
| GPT-6 Luna Pro | OpenAI openai | $0.100 | $0.500 | $0.010 | $0.125 | $0.400 | cheapest | 1.1M | src |
| GPT-6 Luna Pro | Azure | $0.100 | $0.500 | $0.010 | $0.125 | $0.400 | cheapest | 1.1M | src |
| gpt-oss-120b | Baseten | $0.100 | $0.500 | $0.100 | — | $0.400 | cheapest | 128k | src |
| Llama 3.1 70B Instruct | — | $0.400 | $0.400 | — | — | $0.400 | cheapest | 131k | src |
| Llama 3.1 70B Instruct | DeepInfra | $0.400 | $0.400 | — | — | $0.400 | cheapest | 131k | src |
| MythoMax 13B | DeepInfra | $0.400 | $0.400 | — | — | $0.400 | cheapest | 4k | src |
| UnslopNemo 12B | — | $0.400 | $0.400 | — | — | $0.400 | cheapest | 1.0M | src |
| UnslopNemo 12B | Parasail | $0.400 | $0.400 | — | — | $0.400 | cheapest | 1.0M | src |
| DeepSeek V4 Flash 0731 | Reka | $0.021 | $0.528 | $0.0056 | — | $0.401 | +200% vs Vercel AI Gateway | 262k | src |
| GLM 5.3 Flash | Wafer | $0.120 | $0.500 | $0.060 | — | $0.405 | cheapest | 1.0M | src |
| Qwen3 30B A3B | — | $0.120 | $0.500 | — | — | $0.405 | cheapest | 41k | src |
| Qwen3 30B A3B | DeepInfra | $0.120 | $0.500 | — | — | $0.405 | cheapest | 41k | src |
| GLM 5.3 Flash | — | $0.150 | $0.500 | $0.030 | — | $0.412 | cheapest | 1.0M | src |
| GLM 5.3 Flash | Modal | $0.150 | $0.500 | $0.030 | — | $0.412 | cheapest | 1.0M | src |
| GLM 5.3 Flash | Baseten | $0.150 | $0.500 | $0.030 | — | $0.412 | cheapest | 1.0M | src |
| GLM 5.3 Flash | Crusoe | $0.150 | $0.500 | $0.030 | — | $0.412 | cheapest | 1.0M | src |
| GLM 5.3 Flash | Core Weave | $0.150 | $0.500 | $0.020 | — | $0.412 | cheapest | 1.0M | src |
| GLM 5.3 Flash | Atlas Cloud | $0.150 | $0.500 | $0.030 | — | $0.412 | cheapest | 1.0M | src |
| GLM 5.3 Flash | Fireworks | $0.150 | $0.500 | $0.030 | — | $0.412 | cheapest | 1.0M | src |
| GLM 5.3 Flash | Friendli | $0.150 | $0.500 | $0.030 | — | $0.412 | cheapest | 1.0M | src |
| GLM 5.3 Flash | Silicon Flow | $0.150 | $0.500 | $0.030 | — | $0.412 | cheapest | 1.0M | src |
| GLM 5.3 Flash | Together | $0.150 | $0.500 | $0.030 | — | $0.412 | cheapest | 1.0M | src |
| GLM 5.3 Flash | Parasail | $0.150 | $0.500 | $0.030 | — | $0.412 | cheapest | 1.0M | src |
| GLM 5.3 Flash | Venice | $0.150 | $0.500 | $0.030 | — | $0.412 | cheapest | 1.0M | src |
| GLM 5.3 Flash | Z.AI | $0.150 | $0.500 | $0.030 | — | $0.412 | cheapest | 1.0M | src |
| Nemotron 3.5 Super VL | Together | $0.150 | $0.500 | $0.020 | — | $0.412 | cheapest | 262k | src |
| Nemotron 3.5 Super VL | Core Weave | $0.150 | $0.500 | $0.020 | — | $0.412 | cheapest | 1.0M | src |
| Gemma 4 31B | DeepInfra | $0.135 | $0.510 | $0.075 | — | $0.416 | cheapest | 262k | src |
| DeepSeek V4 Flash 0423 | Mancer 2 | $0.190 | $0.500 | — | — | $0.422 | cheapest | 1.0M | src |
| Hy3 | — | $0.132 | $0.528 | $0.033 | — | $0.429 | cheapest | 262k | src |
| Hy3 | Tencent | $0.132 | $0.528 | $0.033 | — | $0.429 | cheapest | 262k | src |
| Llama 3.3 70B Instruct | Parasail | $0.220 | $0.500 | $0.110 | — | $0.430 | cheapest | 131k | src |
| DeepSeek V4.1 Flash | Morph | $0.088 | $0.550 | $0.0080 | — | $0.434 | cheapest | 1.0M | src |
| Qwen3 235B A22B Instruct 2507 | — | $0.090 | $0.550 | — | — | $0.435 | cheapest | 262k | src |
| Qwen3 235B A22B Instruct 2507 | DeepInfra | $0.090 | $0.550 | — | — | $0.435 | cheapest | 262k | src |
| DeepSeek V4.1 Flash | Atlas Cloud | $0.135 | $0.540 | $0.013 | — | $0.439 | cheapest | 1.0M | src |
| Claude Haiku 5.5 | Google google-vertex/europe | $0.110 | $0.550 | $0.011 | $0.138 | $0.440 | cheapest | 1M | src |
| Claude Haiku 5.5 | Google google-vertex/us | $0.110 | $0.550 | $0.011 | $0.138 | $0.440 | cheapest | 1M | src |
| Claude Haiku 5.5 | Azure azure/us | $0.110 | $0.550 | $0.011 | $0.138 | $0.440 | cheapest | 1M | src |
| Claude Haiku 5.5 | Bedrock amazon-bedrock/us-east-1 | $0.110 | $0.550 | $0.011 | $0.138 | $0.440 | cheapest | 1M | src |
| Claude Haiku 5.5 | Bedrock amazon-bedrock/eu-west-1 | $0.110 | $0.550 | $0.011 | $0.138 | $0.440 | cheapest | 1M | src |
| GPT-6 Luna | Azure azure/us | $0.110 | $0.550 | $0.011 | $0.138 | $0.440 | cheapest | 1.1M | src |
| GPT-6 Luna | Azure azure/eu | $0.110 | $0.550 | $0.011 | $0.138 | $0.440 | cheapest | 1.1M | src |
| GPT-6 Luna | Bedrock | $0.110 | $0.550 | $0.011 | $0.138 | $0.440 | cheapest | 1.1M | src |
| GPT-6 Luna Pro | Azure azure/us | $0.110 | $0.550 | $0.011 | $0.138 | $0.440 | cheapest | 1.1M | src |
| GPT-6 Luna Pro | Azure azure/eu | $0.110 | $0.550 | $0.011 | $0.138 | $0.440 | cheapest | 1.1M | src |
| Llama 3.3 70B Instruct | AkashML | $0.200 | $0.520 | $0.100 | — | $0.440 | cheapest | 131k | src |
| Cydonia 24B V4.1 | — | $0.300 | $0.500 | $0.150 | — | $0.450 | cheapest | 131k | src |
| Cydonia 24B V4.1 | Parasail | $0.300 | $0.500 | $0.150 | — | $0.450 | cheapest | 131k | src |
| Hunyuan A13B Instruct | — | $0.140 | $0.570 | — | — | $0.463 | cheapest | 131k | src |
| Hunyuan A13B Instruct | Silicon Flow | $0.140 | $0.570 | — | — | $0.463 | cheapest | 131k | src |
| Qwen3 32B | Silicon Flow | $0.140 | $0.570 | — | — | $0.463 | cheapest | 131k | src |
| Hy3 | Novita | $0.140 | $0.580 | $0.035 | — | $0.470 | cheapest | 262k | src |
| Hy3 | GMI Cloud | $0.140 | $0.580 | $0.035 | — | $0.470 | cheapest | 262k | src |
| DeepSeek V4 Flash 0423 | Azure | $0.210 | $0.560 | $0.031 | — | $0.472 | cheapest | 1.0M | src |
| GPT-5.6 Luna | OpenAI | $0.100 | $0.600 | $0.010 | $0.125 | $0.475 | cheapest | 1.1M | src |
| GPT-5.6 Luna | OpenAI | $0.100 | $0.600 | $0.010 | — | $0.475 | cheapest | 1.1M | src |
| GPT-5.6 Luna (batch) | — | $0.100 | $0.600 | $0.010 | — | $0.475 | cheapest | 1.1M | src |
| GPT-5.6 Luna Pro | OpenAI | $0.100 | $0.600 | $0.010 | $0.125 | $0.475 | cheapest | 1.1M | src |
| GPT-5.6 Luna Pro | OpenAI | $0.100 | $0.600 | $0.010 | — | $0.475 | cheapest | 1.1M | src |
| GPT-5.6 Luna Pro (batch) | — | $0.100 | $0.600 | $0.010 | — | $0.475 | cheapest | 1.1M | src |
| DeepSeek V4 Flash 0731 | Inceptron | $0.130 | $0.598 | $0.027 | — | $0.481 | +260% vs Vercel AI Gateway | 1.0M | src |
| DeepSeek V4.1 Flash | StreamLake | $0.150 | $0.599 | $0.0030 | — | $0.487 | cheapest | 1.0M | src |
| Command R (08-2024) | — | $0.150 | $0.600 | — | — | $0.487 | cheapest | 128k | src |
| Command R (08-2024) | Cohere | $0.150 | $0.600 | — | — | $0.487 | cheapest | 128k | src |
| DeepSeek V4.1 Flash | — | $0.150 | $0.600 | $0.0030 | — | $0.487 | cheapest | 1.0M | src |
| DeepSeek V4.1 Flash | DeepSeek | $0.150 | $0.600 | $0.0030 | — | $0.487 | cheapest | 1.0M | src |
| DeepSeek V4.1 Flash 1017 | — | $0.150 | $0.600 | $0.0030 | — | $0.487 | cheapest | 1.0M | src |
| DeepSeek V4.1 Flash 1017 | DeepSeek | $0.150 | $0.600 | $0.0030 | — | $0.487 | cheapest | 1.0M | src |
| Gemma 4 26B A4B | $0.150 | $0.600 | — | — | $0.487 | cheapest | 262k | src | |
| GPT-4o-mini | — | $0.150 | $0.600 | $0.075 | — | $0.487 | cheapest | 128k | src |
| GPT-4o-mini | Azure | $0.150 | $0.600 | $0.075 | — | $0.487 | cheapest | 128k | src |
| GPT-4o-mini | OpenAI | $0.150 | $0.600 | $0.075 | — | $0.487 | cheapest | 128k | src |
| GPT-4o-mini (2024-07-18) | — | $0.150 | $0.600 | $0.075 | — | $0.487 | cheapest | 128k | src |
| GPT-4o-mini (2024-07-18) | OpenAI | $0.150 | $0.600 | $0.075 | — | $0.487 | cheapest | 128k | src |
| gpt-oss-120b | — | $0.150 | $0.600 | $0.075 | — | $0.487 | cheapest | 131k | src |
| gpt-oss-120b | Bedrock | $0.150 | $0.600 | — | — | $0.487 | cheapest | 131k | src |
| gpt-oss-120b | Nebius | $0.150 | $0.600 | — | — | $0.487 | cheapest | 131k | src |
| gpt-oss-120b | Silicon Flow | $0.150 | $0.600 | $0.075 | — | $0.487 | cheapest | 131k | src |
| gpt-oss-120b | Phala | $0.150 | $0.600 | — | — | $0.487 | cheapest | 131k | src |
| gpt-oss-120b | Together | $0.150 | $0.600 | — | — | $0.487 | cheapest | 131k | src |
| gpt-oss-120b | Groq | $0.150 | $0.600 | $0.075 | — | $0.487 | cheapest | 131k | src |
| Llama 4 Scout | Novita | $0.180 | $0.590 | — | — | $0.487 | cheapest | 131k | src |
| Mistral Small 4 | — | $0.150 | $0.600 | $0.015 | — | $0.487 | cheapest | 262k | src |
| Mistral Small 4 | Mistral | $0.150 | $0.600 | $0.015 | — | $0.487 | cheapest | 262k | src |
| Qwen3 Coder 30B A3B Instruct | Bedrock | $0.150 | $0.600 | — | — | $0.487 | cheapest | 262k | src |
| Qwen3 VL 30B A3B Instruct | — | $0.150 | $0.600 | — | — | $0.487 | cheapest | 262k | src |
| Qwen3 VL 30B A3B Instruct | DeepInfra | $0.150 | $0.600 | — | — | $0.487 | cheapest | 262k | src |
| Solar Pro 3 | — | $0.150 | $0.600 | $0.015 | — | $0.487 | cheapest | 131k | src |
| Solar Pro 3 | Upstage | $0.150 | $0.600 | $0.015 | — | $0.487 | cheapest | 131k | src |
| GLM 5.2 | Baidu | $0.189 | $0.594 | $0.035 | — | $0.493 | cheapest | 1.0M | src |
| GPT-5.4 Nano | OpenAI | $0.100 | $0.625 | $0.010 | — | $0.494 | cheapest | 400k | src |
| GPT-5.4 Nano | OpenAI | $0.100 | $0.625 | $0.010 | — | $0.494 | cheapest | 400k | src |
| GPT-5.4 Nano (batch) | — | $0.100 | $0.625 | $0.010 | — | $0.494 | cheapest | 400k | src |
| Hy3 preview | — | $0.180 | $0.600 | $0.060 | — | $0.495 | cheapest | 262k | src |
| Hy3 preview | GMI Cloud | $0.180 | $0.600 | $0.060 | — | $0.495 | cheapest | 262k | src |
| DeepSeek V4 Flash 0731 | Mancer 2 | $0.200 | $0.600 | — | — | $0.500 | +274% vs Vercel AI Gateway | 1.0M | src |
| DeepSeek V4.1 Flash | OpenInference | $0.200 | $0.600 | $0.0080 | — | $0.500 | cheapest | 1.0M | src |
| DeepSeek V4.1 Flash | Relace | $0.200 | $0.600 | $0.0080 | — | $0.500 | cheapest | 1.0M | src |
| Qwen3 235B A22B Instruct 2507 | Nebius | $0.200 | $0.600 | — | — | $0.500 | cheapest | 262k | src |
| Saba | — | $0.200 | $0.600 | $0.020 | — | $0.500 | cheapest | 33k | src |
| Saba | Mistral | $0.200 | $0.600 | $0.020 | — | $0.500 | cheapest | 33k | src |
| Mistral Small 3.1 24B | — | $0.351 | $0.555 | — | — | $0.504 | cheapest | 128k | src |
| Mistral Small 3.1 24B | Cloudflare | $0.351 | $0.555 | — | — | $0.504 | cheapest | 128k | src |
| GLM 5.3 Flash | Morph | $0.085 | $0.650 | $0.030 | — | $0.509 | cheapest | 1.0M | src |
| DeepSeek V4.1 Flash | Wafer | $0.100 | $0.650 | $0.060 | — | $0.512 | cheapest | 1.0M | src |
| GLM 5.3 Flash | Parasail fp4 | $0.188 | $0.625 | $0.037 | — | $0.516 | cheapest | 1.0M | src |
| Hy3 | Phala | $0.150 | $0.640 | $0.040 | — | $0.517 | cheapest | 262k | src |
| DeepSeek V4.1 Flash | Core Weave | $0.150 | $0.650 | $0.0020 | — | $0.525 | cheapest | 1.0M | src |
| MiMo-V2.5-Pro | GMI Cloud | $0.304 | $0.609 | $0.0028 | — | $0.533 | cheapest | 1.1M | src |
| GPT-4o-mini | Azure azure/swedencentral | $0.165 | $0.660 | $0.083 | — | $0.536 | cheapest | 128k | src |
| Llama 4 Maverick | — | $0.188 | $0.652 | $0.050 | — | $0.536 | cheapest | 1.0M | src |
| Llama 4 Maverick | DigitalOcean | $0.188 | $0.652 | $0.050 | — | $0.536 | cheapest | 128k | src |
| Mistral Small 4 | Mistral mistral/eu | $0.165 | $0.660 | $0.017 | — | $0.536 | cheapest | 262k | src |
| Mistral Small 4 | Mistral mistral/us | $0.165 | $0.660 | $0.017 | — | $0.536 | cheapest | 262k | src |
| LFM2.5-24B-A2B | — | $0.050 | $0.700 | $0.025 | — | $0.537 | 0% vs Vercel AI Gateway | 128k | src |
| LFM2.5-24B-A2B | Liquid | $0.050 | $0.700 | $0.025 | — | $0.537 | 0% vs Vercel AI Gateway | 128k | src |
| MythoMax 13B | Mancer 2 | $0.350 | $0.600 | — | — | $0.537 | cheapest | 8k | src |
| Qwen3.6 35B A3B | Darkbloom | $0.050 | $0.700 | $0.025 | — | $0.537 | cheapest | 262k | src |
| DeepSeek V4 Flash Vision Exp | — | $0.216 | $0.647 | $0.0069 | — | $0.539 | 0% vs Vercel AI Gateway | 1.0M | src |
| DeepSeek V4 Flash Vision Exp | DeepInfra | $0.216 | $0.647 | $0.0069 | — | $0.539 | 0% vs Vercel AI Gateway | 1.0M | src |
| DeepSeek V4 Flash 0731 | Silicon Flow | $0.220 | $0.660 | $0.028 | — | $0.550 | +311% vs Vercel AI Gateway | 1.0M | src |
| Saba | Mistral mistral/eu | $0.220 | $0.660 | $0.022 | — | $0.550 | cheapest | 33k | src |
| DeepSeek V4.1 Flash | Inference Net | $0.103 | $0.715 | $0.0080 | — | $0.562 | cheapest | 1.0M | src |
| Qwen3 VL 30B A3B Instruct | Novita | $0.200 | $0.700 | — | — | $0.575 | cheapest | 131k | src |
| ReMM SLERP 13B | — | $0.350 | $0.650 | — | — | $0.575 | cheapest | 6k | src |
| ReMM SLERP 13B | Mancer 2 | $0.350 | $0.650 | — | — | $0.575 | cheapest | 6k | src |
| Qwen3.5-35B-A3B | Darkbloom | $0.065 | $0.750 | $0.033 | — | $0.579 | cheapest | 262k | src |
| DeepSeek V4.1 Flash | GMI Cloud | $0.180 | $0.720 | $0.0036 | — | $0.585 | cheapest | 1.0M | src |
| Gemini 2.5 Flash Lite | Google AI Studio google-ai-studio/priority | $0.180 | $0.720 | $0.018 | $0.150 | $0.585 | cheapest | 1.0M | src |
| GLM 5.3 Flash | Next Bit | $0.250 | $0.700 | $0.075 | — | $0.588 | cheapest | 1.0M | src |
| gpt-oss-120b | Parasail | $0.100 | $0.750 | $0.055 | — | $0.588 | cheapest | 131k | src |
| Llama 4 Scout | $0.250 | $0.700 | — | — | $0.588 | cheapest | 1.3M | src | |
| Gemini 3.1 Flash Lite | $0.125 | $0.750 | $0.013 | $0.042 | $0.594 | cheapest | 1.0M | src | |
| Gemini 3.1 Flash Lite | Google AI Studio | $0.125 | $0.750 | $0.013 | $0.042 | $0.594 | cheapest | 1.0M | src |
| Gemini 3.1 Flash Lite | $0.125 | $0.750 | $0.013 | — | $0.594 | cheapest | 1.0M | src | |
| Gemini 3.1 Flash Lite (batch) | — | $0.125 | $0.750 | $0.013 | — | $0.594 | cheapest | 1.0M | src |
| Gemini 3.1 Flash Lite Preview | Google AI Studio | $0.125 | $0.750 | $0.013 | $0.042 | $0.594 | cheapest | 1.0M | src |
| DeepSeek V3 | DeepInfra | $0.256 | $0.712 | — | — | $0.598 | cheapest | 164k | src |
| gpt-oss-120b | Mara | $0.150 | $0.750 | — | — | $0.600 | cheapest | 131k | src |
| Qwen3 235B A22B Instruct 2507 | Venice | $0.150 | $0.750 | — | — | $0.600 | cheapest | 128k | src |
| ReMM SLERP 13B | Next Bit | $0.450 | $0.650 | — | — | $0.600 | cheapest | 6k | src |
| GLM 5.3 Flash | Fireworks fireworks/us | $0.225 | $0.750 | $0.045 | — | $0.619 | cheapest | 1.0M | src |
| WizardLM-2 8x22B | — | $0.620 | $0.620 | — | — | $0.620 | cheapest | 66k | src |
| WizardLM-2 8x22B | Novita | $0.620 | $0.620 | — | — | $0.620 | cheapest | 66k | src |
| GPT-3.5 Turbo | OpenAI | $0.250 | $0.750 | — | — | $0.625 | cheapest | 16k | src |
| GPT-3.5 Turbo (batch) | — | $0.250 | $0.750 | — | — | $0.625 | cheapest | 16k | src |
| Mercury 2 | — | $0.250 | $0.750 | $0.025 | — | $0.625 | 0% vs Vercel AI Gateway | 128k | src |
| Mercury 2 | Inception | $0.250 | $0.750 | $0.025 | — | $0.625 | 0% vs Vercel AI Gateway | 128k | src |
| Mistral Large 3 2512 | Mistral | $0.250 | $0.750 | $0.025 | — | $0.625 | cheapest | 262k | src |
| Mistral Large 3 2512 (batch) | — | $0.250 | $0.750 | $0.025 | — | $0.625 | cheapest | 262k | src |
| Qwen3 VL 8B Instruct | — | $0.250 | $0.750 | $0.120 | — | $0.625 | cheapest | 262k | src |
| Qwen3 VL 8B Instruct | Parasail | $0.250 | $0.750 | $0.120 | — | $0.625 | cheapest | 262k | src |
| Qwen3 Coder Next | — | $0.120 | $0.800 | $0.070 | — | $0.630 | cheapest | 262k | src |
| Qwen3 Coder Next | Parasail | $0.120 | $0.800 | $0.070 | — | $0.630 | cheapest | 262k | src |
| DeepSeek V4.1 Flash | DigitalOcean | $0.195 | $0.780 | $0.0060 | — | $0.634 | cheapest | 1.0M | src |
| DeepSeek V4.1 Flash | Novita | $0.195 | $0.780 | $0.0039 | — | $0.634 | cheapest | 1.0M | src |
| Qwen3 235B A22B Instruct 2507 | Parasail | $0.140 | $0.800 | $0.050 | — | $0.635 | cheapest | 131k | src |
| Gemma 2 27B | — | $0.650 | $0.650 | — | — | $0.650 | cheapest | 8k | src |
| Gemma 2 27B | Next Bit | $0.650 | $0.650 | — | — | $0.650 | cheapest | 8k | src |
| GPT-4.1 Mini | OpenAI | $0.200 | $0.800 | $0.050 | — | $0.650 | cheapest | 1.0M | src |
| GPT-4.1 Mini (batch) | — | $0.200 | $0.800 | $0.050 | — | $0.650 | cheapest | 1.0M | src |
| gpt-oss-120b | Cerebras | $0.350 | $0.750 | $0.350 | — | $0.650 | cheapest | 131k | src |
| Hy3 | Atlas Cloud | $0.200 | $0.800 | $0.050 | — | $0.650 | cheapest | 262k | src |
| Qwen-Plus | — | $0.260 | $0.780 | $0.052 | $0.325 | $0.650 | cheapest | 1M | src |
| Qwen-Plus | Alibaba | $0.260 | $0.780 | $0.052 | $0.325 | $0.650 | cheapest | 1M | src |
| Trinity Large Thinking | — | $0.250 | $0.800 | $0.060 | — | $0.662 | 0% vs Vercel AI Gateway | 262k | src |
| Trinity Large Thinking | Arcee AI | $0.250 | $0.800 | $0.060 | — | $0.662 | 0% vs Vercel AI Gateway | 262k | src |
| Weaver (alpha) | — | $0.400 | $0.750 | — | — | $0.662 | cheapest | 8k | src |
| Weaver (alpha) | Mancer 2 | $0.400 | $0.750 | — | — | $0.662 | cheapest | 8k | src |
| DeepSeek V3.2 | Silicon Flow | $0.259 | $0.800 | $0.140 | — | $0.665 | cheapest | 164k | src |
| GLM 4.5 Air | — | $0.130 | $0.850 | $0.025 | — | $0.670 | 0% vs Novita | 131k | src |
| GLM 4.5 Air | Novita | $0.130 | $0.850 | $0.025 | — | $0.670 | 0% vs Novita | 131k | src |
| GLM 5.3 Flash | Inceptron | $0.100 | $0.863 | $0.075 | — | $0.672 | cheapest | 1.0M | src |
| Qwen3 Next 80B A3B Instruct | DeepInfra | $0.072 | $0.880 | — | — | $0.678 | cheapest | 262k | src |
| GLM 4.5 Air | Silicon Flow | $0.140 | $0.860 | — | — | $0.680 | +1% vs Novita | 131k | src |
| DeepSeek V4.1 Flash | Phala | $0.210 | $0.840 | $0.0042 | — | $0.682 | cheapest | 1.0M | src |
| MiniMax M2.7 | GMI Cloud | $0.210 | $0.840 | $0.042 | — | $0.682 | 0% vs Vercel AI Gateway | 197k | src |
| DeepSeek V4.1 Flash | Cloudflare | $0.100 | $0.900 | $0.030 | — | $0.700 | cheapest | 1.0M | src |
| Hermes 3 70B Instruct | — | $0.700 | $0.700 | — | — | $0.700 | cheapest | 131k | src |
| Hermes 3 70B Instruct | DeepInfra | $0.700 | $0.700 | — | — | $0.700 | cheapest | 131k | src |
| Qwen3.6 35B A3B | AkashML | $0.100 | $0.900 | $0.050 | — | $0.700 | cheapest | 262k | src |
| Llama 4 Maverick | Novita | $0.270 | $0.850 | — | — | $0.705 | cheapest | 1.0M | src |
| Llama 3.3 70B Instruct | Core Weave | $0.710 | $0.710 | $0.710 | — | $0.710 | cheapest | 128k | src |
| Qwen3 VL 235B A22B Instruct | DeepInfra | $0.200 | $0.880 | $0.110 | — | $0.710 | 0% vs Vercel AI Gateway | 262k | src |
| DeepSeek V4 Flash 0731 | GMI Cloud | $0.286 | $0.858 | $0.0091 | — | $0.715 | +435% vs Vercel AI Gateway | 1.0M | src |
| Qwen3 235B A22B Instruct 2507 | $0.220 | $0.880 | — | — | $0.715 | cheapest | 262k | src | |
| MiniMax M3 | DeepInfra | $0.224 | $0.880 | $0.045 | — | $0.716 | cheapest | 524k | src |
| Llama 3.1 70B Instruct | Bedrock | $0.720 | $0.720 | — | — | $0.720 | cheapest | 131k | src |
| Llama 3.3 70B Instruct | $0.720 | $0.720 | — | — | $0.720 | cheapest | 128k | src | |
| Llama 3.3 Euryale 70B | — | $0.650 | $0.750 | — | — | $0.725 | cheapest | 131k | src |
| Llama 3.3 Euryale 70B | Next Bit | $0.650 | $0.750 | — | — | $0.725 | cheapest | 131k | src |
| Uncensored | — | $0.200 | $0.900 | — | — | $0.725 | cheapest | 128k | src |
| Uncensored | Venice | $0.200 | $0.900 | — | — | $0.725 | cheapest | 128k | src |
| Qwen3.6 35B A3B | DeepInfra | $0.100 | $0.950 | $0.100 | — | $0.738 | cheapest | 262k | src |
| Skyfall 36B V2 | — | $0.550 | $0.800 | $0.250 | — | $0.738 | cheapest | 33k | src |
| Skyfall 36B V2 | Parasail | $0.550 | $0.800 | $0.250 | — | $0.738 | cheapest | 33k | src |
| Llama 3.3 70B Instruct | Groq | $0.590 | $0.790 | $0.295 | — | $0.740 | cheapest | 131k | src |
| DeepSeek V3 | — | $0.320 | $0.890 | — | — | $0.748 | cheapest | 164k | src |
| DeepSeek V3 | DeepInfra fp4 | $0.320 | $0.890 | — | — | $0.748 | cheapest | 164k | src |
| gpt-oss-120b | Samba Nova | $0.140 | $0.950 | — | — | $0.748 | cheapest | 131k | src |
| Qwen3.7 Plus | Alibaba | $0.230 | $0.920 | — | — | $0.748 | cheapest | 262k | src |
| Qwen3.7 Plus (batch) | — | $0.230 | $0.920 | — | — | $0.748 | cheapest | 262k | src |
| Codestral 2508 | — | $0.300 | $0.900 | $0.030 | — | $0.750 | cheapest | 256k | src |
| Codestral 2508 | Mistral | $0.300 | $0.900 | $0.030 | — | $0.750 | cheapest | 256k | src |
| GLM 4.6V | — | $0.300 | $0.900 | $0.055 | — | $0.750 | 0% vs Novita | 131k | src |
| GLM 4.6V | Novita | $0.300 | $0.900 | $0.055 | — | $0.750 | 0% vs Novita | 131k | src |
| GLM 4.6V | Z.AI | $0.300 | $0.900 | $0.050 | — | $0.750 | 0% vs Novita | 131k | src |
| Ling 3.1 Flash | DeepInfra | $0.300 | $0.900 | $0.060 | — | $0.750 | cheapest | 262k | src |
| MiMo-V2.6-Pro | DeepInfra | $0.430 | $0.870 | $0.0036 | — | $0.760 | 0% vs DeepInfra | 1.0M | src |
| MiMo-V2.5-Pro | — | $0.435 | $0.870 | $0.0036 | — | $0.761 | cheapest | 1.1M | src |
| MiMo-V2.5-Pro | Atlas Cloud | $0.435 | $0.870 | $0.0036 | — | $0.761 | cheapest | 1.0M | src |
| MiMo-V2.5-Pro | Xiaomi | $0.435 | $0.870 | $0.0036 | — | $0.761 | cheapest | 1.0M | src |
| MiMo-V2.6-Pro | — | $0.435 | $0.870 | $0.0036 | — | $0.761 | +0% vs DeepInfra | 1.1M | src |
| MiMo-V2.6-Pro | Novita | $0.435 | $0.870 | $0.0036 | — | $0.761 | +0% vs DeepInfra | 1.0M | src |
| MiMo-V2.6-Pro | GMI Cloud | $0.435 | $0.870 | $0.0040 | — | $0.761 | +0% vs DeepInfra | 1.1M | src |
| MiMo-V2.6-Pro | Xiaomi | $0.435 | $0.870 | $0.0036 | — | $0.761 | +0% vs DeepInfra | 1.0M | src |
| DeepSeek V4 Flash 0731 | Phala | $0.308 | $0.924 | $0.020 | — | $0.770 | +476% vs Vercel AI Gateway | 1.0M | src |
| DeepSeek V3.1 | — | $0.250 | $0.950 | $0.130 | — | $0.775 | 0% vs Vercel AI Gateway | 164k | src |
| DeepSeek V3.1 | DeepInfra | $0.250 | $0.950 | $0.130 | — | $0.775 | 0% vs Vercel AI Gateway | 164k | src |
| Qwen3.6 35B A3B | Deka LLM | $0.100 | $1.00 | $0.050 | — | $0.775 | cheapest | 262k | src |
| Qwen3.6 35B A3B | Venice | $0.100 | $1.00 | — | — | $0.775 | cheapest | 256k | src |
| MiniMax M3 | Core Weave | $0.230 | $0.960 | $0.050 | — | $0.777 | cheapest | 262k | src |
| MiniMax M2.5 | — | $0.270 | $0.950 | $0.030 | — | $0.780 | cheapest | 205k | src |
| MiniMax M2.5 | Venice | $0.270 | $0.950 | $0.030 | — | $0.780 | cheapest | 198k | src |
| MiniMax M3 | GMI Cloud | $0.240 | $0.960 | $0.048 | — | $0.780 | cheapest | 1.0M | src |
| Qwen3 Coder Flash | — | $0.195 | $0.975 | $0.039 | $0.244 | $0.780 | cheapest | 1M | src |
| Qwen3 Coder Flash | Alibaba | $0.195 | $0.975 | $0.039 | $0.244 | $0.780 | cheapest | 1M | src |
| GPT-5 Mini | OpenAI | $0.125 | $1.00 | $0.013 | — | $0.781 | cheapest | 400k | src |
| GPT-5 Mini | OpenAI | $0.125 | $1.00 | $0.013 | — | $0.781 | cheapest | 400k | src |
| GPT-5 Mini (batch) | — | $0.125 | $1.00 | $0.013 | — | $0.781 | cheapest | 400k | src |
| Qwen3.5-35B-A3B | DeepInfra | $0.140 | $1.00 | $0.050 | — | $0.785 | cheapest | 262k | src |
| Llama 3.3 70B Instruct | Samba Nova | $0.450 | $0.900 | — | — | $0.787 | cheapest | 131k | src |
| Qwen3.5-35B-A3B | — | $0.150 | $1.00 | $0.050 | — | $0.787 | cheapest | 262k | src |
| Qwen3.5-35B-A3B | Parasail | $0.150 | $1.00 | $0.050 | — | $0.787 | cheapest | 262k | src |
| Qwen3.5-35B-A3B | Venice | $0.150 | $1.00 | $0.050 | — | $0.787 | cheapest | 256k | src |
| Qwen3.6 35B A3B | — | $0.150 | $1.00 | $0.050 | — | $0.787 | cheapest | 262k | src |
| Qwen3.6 35B A3B | Parasail | $0.150 | $1.00 | $0.050 | — | $0.787 | cheapest | 262k | src |
| DeepSeek V3.2 | DigitalOcean | $0.300 | $0.960 | $0.090 | — | $0.795 | cheapest | 164k | src |
| GPT-6 Luna | OpenAI openai/fast | $0.200 | $1.00 | $0.020 | $0.250 | $0.800 | cheapest | 1.1M | src |
| GPT-6 Luna Pro | OpenAI openai/fast | $0.200 | $1.00 | $0.020 | $0.250 | $0.800 | cheapest | 1.1M | src |
| Mistral Medium 3.1 | Mistral | $0.200 | $1.00 | $0.020 | — | $0.800 | cheapest | 131k | src |
| Mistral Medium 3.1 (batch) | — | $0.200 | $1.00 | $0.020 | — | $0.800 | cheapest | 131k | src |
| Beam 1.0 501B A23B | Nebius | $0.250 | $1.00 | — | — | $0.813 | cheapest | 1.0M | src |
| DeepSeek V3 0324 | Silicon Flow | $0.250 | $1.00 | — | — | $0.813 | cheapest | 164k | src |
| Qwen3 235B A22B Instruct 2507 | Google google-vertex/us-south1 | $0.250 | $1.00 | — | — | $0.813 | cheapest | 262k | src |
| DeepSeek V3.1 | Silicon Flow | $0.270 | $1.00 | — | — | $0.818 | +5% vs Vercel AI Gateway | 164k | src |
| DeepSeek V3.1 Terminus | — | $0.270 | $1.00 | — | — | $0.818 | cheapest | 164k | src |
| DeepSeek V3.1 Terminus | Silicon Flow | $0.270 | $1.00 | — | — | $0.818 | cheapest | 164k | src |
| Qwen3 VL 30B A3B Instruct | Silicon Flow | $0.290 | $1.00 | — | — | $0.823 | cheapest | 262k | src |
| Qwen3 VL 30B A3B Thinking | — | $0.290 | $1.00 | — | — | $0.823 | cheapest | 262k | src |
| Qwen3 VL 30B A3B Thinking | Silicon Flow | $0.290 | $1.00 | — | — | $0.823 | cheapest | 262k | src |
| Codestral 2508 | Mistral mistral/eu | $0.330 | $0.990 | $0.033 | — | $0.825 | cheapest | 256k | src |
| Qwen3 Coder 480B A35B | — | $0.300 | $1.00 | $0.100 | — | $0.825 | cheapest | 262k | src |
| Qwen3 Coder 480B A35B | DeepInfra | $0.300 | $1.00 | $0.100 | — | $0.825 | cheapest | 262k | src |
| MiniMax M2 | — | $0.255 | $1.02 | — | — | $0.829 | cheapest | 205k | src |
| MiniMax M2 | MiniMax | $0.255 | $1.02 | — | — | $0.829 | cheapest | 205k | src |
| DeepSeek V3 | StreamLake | $0.257 | $1.03 | — | — | $0.836 | cheapest | 128k | src |
| Llama 4 Maverick | Parasail | $0.350 | $1.00 | $0.170 | — | $0.838 | cheapest | 524k | src |
| MiMo-V2.5-Pro | Novita | $0.480 | $0.960 | $0.0040 | — | $0.840 | cheapest | 1.0M | src |
| Qwen3 Next 80B A3B Instruct | — | $0.090 | $1.10 | — | — | $0.848 | cheapest | 262k | src |
| Qwen3 Next 80B A3B Instruct | DeepInfra fp8 | $0.090 | $1.10 | — | — | $0.848 | cheapest | 262k | src |
| Llama 3.1 Euryale 70B v2.2 | — | $0.850 | $0.850 | — | — | $0.850 | cheapest | 131k | src |
| Llama 3.1 Euryale 70B v2.2 | DeepInfra | $0.850 | $0.850 | — | — | $0.850 | cheapest | 131k | src |
| Qwen3 Next 80B A3B Instruct | Parasail | $0.100 | $1.10 | $0.070 | — | $0.850 | cheapest | 262k | src |
| DeepSeek V3.1 Terminus | StreamLake | $0.343 | $1.03 | — | — | $0.857 | cheapest | 128k | src |
| GLM 4.5 Air | Z.AI | $0.200 | $1.10 | $0.030 | — | $0.875 | +31% vs Novita | 131k | src |
| MiniMax-01 | — | $0.200 | $1.10 | — | — | $0.875 | cheapest | 1.0M | src |
| MiniMax-01 | MiniMax | $0.200 | $1.10 | — | — | $0.875 | cheapest | 1.0M | src |
| MiniMax M2.5 | StreamLake | $0.270 | $1.08 | $0.027 | — | $0.877 | cheapest | 200k | src |
| MiniMax M2.7 | Novita | $0.270 | $1.08 | $0.054 | — | $0.877 | +29% vs Vercel AI Gateway | 205k | src |
| DeepSeek V4 Flash 0731 | Alibaba | $0.352 | $1.06 | $0.035 | — | $0.880 | +558% vs Vercel AI Gateway | 1M | src |
| Qwen3.6 Flash | — | $0.188 | $1.13 | — | $0.234 | $0.891 | cheapest | 1M | src |
| Qwen3.6 Flash | Alibaba | $0.188 | $1.13 | — | $0.234 | $0.891 | cheapest | 1M | src |
| DeepSeek V4.1 Flash | Ionstream | $0.270 | $1.10 | $0.0050 | — | $0.892 | cheapest | 1.0M | src |
| MiniMax M3 | DeepInfra fp8 | $0.280 | $1.10 | $0.056 | — | $0.895 | cheapest | 524k | src |
| Gemma 4 31B | Io Net | $0.361 | $1.09 | $0.180 | — | $0.910 | cheapest | 262k | src |
| Step 3.7 Flash | — | $0.200 | $1.15 | $0.040 | — | $0.912 | 0% vs Novita | 262k | src |
| Step 3.7 Flash | Novita | $0.200 | $1.15 | $0.040 | — | $0.912 | 0% vs Novita | 262k | src |
| Step 3.7 Flash | Step Fun | $0.200 | $1.15 | $0.040 | — | $0.912 | 0% vs Novita | 256k | src |
| MiMo-V2.5-Pro | StreamLake | $0.522 | $1.04 | $0.0043 | — | $0.913 | cheapest | 1M | src |
| Qwen2.5 Coder 32B Instruct | — | $0.660 | $1.00 | — | — | $0.915 | cheapest | 33k | src |
| Qwen2.5 Coder 32B Instruct | Cloudflare | $0.660 | $1.00 | — | — | $0.915 | cheapest | 33k | src |
| DeepSeek V3 0324 | — | $0.290 | $1.14 | $0.110 | — | $0.927 | cheapest | 164k | src |
| DeepSeek V3 0324 | GMI Cloud | $0.290 | $1.14 | $0.110 | — | $0.927 | cheapest | 128k | src |
| DeepSeek V4.1 Flash | Makora | $0.270 | $1.15 | $0.0090 | — | $0.930 | cheapest | 1.0M | src |
| DeepSeek V4 Flash 0731 | Alibaba alibaba/us-east-1 | $0.374 | $1.12 | $0.037 | — | $0.935 | +599% vs Vercel AI Gateway | 1M | src |
| Gemma 4 31B | Model Run | $0.750 | $1.00 | $0.200 | — | $0.938 | cheapest | 262k | src |
| Gemma 4 31B | Silicon Flow | $0.750 | $1.00 | $0.250 | — | $0.938 | cheapest | 262k | src |
| Qwen3 Next 80B A3B Instruct | $0.150 | $1.20 | — | — | $0.938 | cheapest | 262k | src | |
| Qwen3 Next 80B A3B Thinking | — | $0.150 | $1.20 | — | — | $0.938 | 0% vs Vercel AI Gateway | 262k | src |
| Qwen3 Next 80B A3B Thinking | $0.150 | $1.20 | — | — | $0.938 | 0% vs Vercel AI Gateway | 262k | src | |
| Qwen3.8 27B | Chutes | $0.039 | $1.25 | $0.0039 | — | $0.947 | +191% vs Vercel AI Gateway | 262k | src |
| GPT-5.6 Luna | — | $0.200 | $1.20 | $0.020 | $0.250 | $0.950 | cheapest | 1.1M | src |
| GPT-5.6 Luna | Azure | $0.200 | $1.20 | $0.020 | $0.250 | $0.950 | cheapest | 1.1M | src |
| GPT-5.6 Luna | OpenAI openai | $0.200 | $1.20 | $0.020 | $0.250 | $0.950 | cheapest | 1.1M | src |
| GPT-5.6 Luna Pro | — | $0.200 | $1.20 | $0.020 | $0.250 | $0.950 | cheapest | 1.1M | src |
| GPT-5.6 Luna Pro | Azure | $0.200 | $1.20 | $0.020 | $0.250 | $0.950 | cheapest | 1.1M | src |
| GPT-5.6 Luna Pro | OpenAI openai | $0.200 | $1.20 | $0.020 | $0.250 | $0.950 | cheapest | 1.1M | src |
| Llama 4 Maverick | $0.350 | $1.15 | — | — | $0.950 | cheapest | 524k | src | |
| Qwen2.5 VL 72B Instruct | — | $0.800 | $1.00 | $0.400 | — | $0.950 | cheapest | 128k | src |
| Qwen2.5 VL 72B Instruct | Parasail | $0.800 | $1.00 | $0.400 | — | $0.950 | cheapest | 128k | src |
| GLM 5.2 | Inceptron | $0.690 | $1.04 | $0.140 | — | $0.952 | cheapest | 1.0M | src |
| Gemma 4 31B | Samba Nova | $0.380 | $1.15 | — | — | $0.958 | cheapest | 131k | src |
| DeepSeek V4 Flash 0731 | Relace | $0.0061 | $1.28 | $0.0061 | — | $0.962 | +619% vs Vercel AI Gateway | 1.0M | src |
| DeepSeek V4 Flash 0731 | OpenInference | $0.0061 | $1.28 | $0.0061 | — | $0.962 | +619% vs Vercel AI Gateway | 1.0M | src |
| DeepSeek V4 Flash 0423 | Relace | $0.017 | $1.28 | $0.017 | — | $0.964 | cheapest | 1.0M | src |
| DeepSeek V4 Flash 0423 | OpenInference | $0.017 | $1.28 | $0.017 | — | $0.964 | cheapest | 1.0M | src |
| DeepSeek V4 Flash 0731 | — | $0.020 | $1.28 | $0.020 | — | $0.965 | +621% vs Vercel AI Gateway | 1.0M | src |
| DeepSeek V4 Flash Latest | — | $0.020 | $1.28 | $0.020 | — | $0.965 | cheapest | 1.0M | src |
| DeepSeek V4.1 Flash | Crusoe | $0.290 | $1.20 | $0.0070 | — | $0.973 | cheapest | 1.0M | src |
| MiniMax M2.5 | Atlas Cloud | $0.295 | $1.20 | $0.060 | — | $0.974 | cheapest | 197k | src |
| DeepSeek V4.1 Flash | Nebius | $0.300 | $1.20 | — | — | $0.975 | cheapest | 1.0M | src |
| DeepSeek V4.1 Flash | Prime Intellect | $0.300 | $1.20 | $0.030 | — | $0.975 | cheapest | 1.0M | src |
| DeepSeek V4.1 Flash | Baidu | $0.300 | $1.20 | $0.0060 | — | $0.975 | cheapest | 1.0M | src |
| DeepSeek V4.1 Flash | Baseten | $0.300 | $1.20 | $0.0070 | — | $0.975 | cheapest | 1.0M | src |
| DeepSeek V4.1 Flash | Alibaba | $0.300 | $1.20 | $0.030 | — | $0.975 | cheapest | 1M | src |
| DeepSeek V4.1 Flash | Together | $0.300 | $1.20 | $0.0060 | — | $0.975 | cheapest | 1.0M | src |
| DeepSeek V4.1 Flash | Silicon Flow | $0.300 | $1.20 | $0.0060 | — | $0.975 | cheapest | 1.0M | src |
| DeepSeek V4.1 Flash | Modal | $0.300 | $1.20 | $0.030 | — | $0.975 | cheapest | 1.0M | src |
| DeepSeek V4.1 Flash | Parasail | $0.300 | $1.20 | $0.0060 | — | $0.975 | cheapest | 1.0M | src |
| DeepSeek V4.1 Flash | Fireworks | $0.300 | $1.20 | $0.0060 | — | $0.975 | cheapest | 1.0M | src |
| DeepSeek V4.1 Flash | Venice | $0.300 | $1.20 | $0.0075 | — | $0.975 | cheapest | 1M | src |
| Gemini 2.5 Flash | Google AI Studio | $0.150 | $1.25 | $0.015 | $0.042 | $0.975 | cheapest | 1.0M | src |
| Gemini 2.5 Flash | $0.150 | $1.25 | $0.030 | — | $0.975 | cheapest | 1.0M | src | |
| Gemini 2.5 Flash (batch) | — | $0.150 | $1.25 | $0.030 | — | $0.975 | cheapest | 1.0M | src |
| Gemini 3.5 Flash Lite | $0.150 | $1.25 | $0.015 | $0.042 | $0.975 | cheapest | 1.0M | src | |
| Gemini 3.5 Flash Lite | Google AI Studio | $0.150 | $1.25 | $0.015 | $0.042 | $0.975 | cheapest | 1.0M | src |
| Gemini 3.5 Flash Lite | $0.150 | $1.25 | $0.015 | — | $0.975 | cheapest | 1.0M | src | |
| Gemini 3.5 Flash Lite (batch) | — | $0.150 | $1.25 | $0.015 | — | $0.975 | cheapest | 1.0M | src |
| LongCat 2.0 | — | $0.300 | $1.20 | $0.0060 | — | $0.975 | cheapest | 1.0M | src |
| LongCat 2.0 | Atlas Cloud | $0.300 | $1.20 | $0.0060 | — | $0.975 | cheapest | 1.0M | src |
| MiniMax M2 | $0.300 | $1.20 | — | — | $0.975 | cheapest | 197k | src | |
| MiniMax M2-her | — | $0.300 | $1.20 | $0.030 | — | $0.975 | cheapest | 66k | src |
| MiniMax M2-her | MiniMax | $0.300 | $1.20 | $0.030 | — | $0.975 | cheapest | 66k | src |
| MiniMax M2.1 | — | $0.300 | $1.20 | $0.030 | — | $0.975 | 0% vs Vercel AI Gateway | 205k | src |
| MiniMax M2.1 | MiniMax | $0.300 | $1.20 | $0.030 | — | $0.975 | 0% vs Vercel AI Gateway | 205k | src |
| MiniMax M2.5 | GMI Cloud | $0.300 | $1.20 | $0.030 | — | $0.975 | cheapest | 197k | src |
| MiniMax M2.5 | DigitalOcean | $0.300 | $1.20 | $0.060 | — | $0.975 | cheapest | 66k | src |
| MiniMax M2.5 | Friendli | $0.300 | $1.20 | $0.060 | — | $0.975 | cheapest | 197k | src |
| MiniMax M2.5 | Novita | $0.300 | $1.20 | $0.030 | — | $0.975 | cheapest | 205k | src |
| MiniMax M2.5 | MiniMax | $0.300 | $1.20 | $0.030 | — | $0.975 | cheapest | 205k | src |
| MiniMax M2.7 | — | $0.300 | $1.20 | $0.060 | — | $0.975 | +43% vs Vercel AI Gateway | 205k | src |
| MiniMax M2.7 | Atlas Cloud | $0.300 | $1.20 | $0.060 | — | $0.975 | +43% vs Vercel AI Gateway | 197k | src |
| MiniMax M2.7 | MiniMax | $0.300 | $1.20 | $0.060 | — | $0.975 | +43% vs Vercel AI Gateway | 205k | src |
| MiniMax M3 | — | $0.300 | $1.20 | $0.060 | — | $0.975 | cheapest | 1.0M | src |
| MiniMax M3 | StreamLake | $0.300 | $1.20 | $0.060 | — | $0.975 | cheapest | 1M | src |
| MiniMax M3 | Venice | $0.300 | $1.20 | $0.060 | — | $0.975 | cheapest | 524k | src |
| MiniMax M3 | Together | $0.300 | $1.20 | $0.060 | — | $0.975 | cheapest | 524k | src |
| MiniMax M3 | Parasail | $0.300 | $1.20 | $0.060 | — | $0.975 | cheapest | 1.0M | src |
| MiniMax M3 | Atlas Cloud | $0.300 | $1.20 | $0.060 | — | $0.975 | cheapest | 524k | src |
| MiniMax M3 | Novita | $0.300 | $1.20 | $0.060 | — | $0.975 | cheapest | 1M | src |
| MiniMax M3 | MiniMax | $0.300 | $1.20 | $0.060 | — | $0.975 | cheapest | 524k | src |
| Muse Glimmer 30B | — | $0.300 | $1.20 | $0.040 | — | $0.975 | cheapest | 131k | src |
| Muse Glimmer 30B | DeepInfra | $0.300 | $1.20 | $0.040 | — | $0.975 | cheapest | 131k | src |
| DeepSeek V4 Pro 0813 | Sail Research | $0.448 | $1.16 | $0.093 | — | $0.985 | cheapest | 1.0M | src |
| GPT-5.4 Nano | — | $0.200 | $1.25 | $0.020 | — | $0.988 | cheapest | 400k | src |
| GPT-5.4 Nano | Azure | $0.200 | $1.25 | $0.020 | — | $0.988 | cheapest | 400k | src |
| GPT-5.4 Nano | OpenAI openai | $0.200 | $1.25 | $0.020 | — | $0.988 | cheapest | 400k | src |
| Beam 1.0 501B A23B | Together | $0.400 | $1.20 | $0.040 | — | $1.00 | cheapest | 1.0M | src |
| DeepSeek V3.2 | Phala | $1.00 | $1.00 | $0.500 | — | $1.00 | cheapest | 164k | src |
| Hermes 3 405B Instruct | — | $1.00 | $1.00 | — | — | $1.00 | cheapest | 131k | src |
| Hermes 3 405B Instruct | DeepInfra | $1.00 | $1.00 | — | — | $1.00 | cheapest | 131k | src |
| Nemotron 3.5 Super VL | Venice | $0.250 | $1.25 | $0.125 | — | $1.00 | cheapest | 262k | src |
| Qwen3.6 35B A3B | Core Weave | $0.250 | $1.25 | $0.250 | — | $1.00 | cheapest | 262k | src |
| Qwen3.6 35B A3B | Atlas Cloud | $0.250 | $1.25 | $0.250 | — | $1.00 | cheapest | 262k | src |
| Sonar | — | $1.00 | $1.00 | — | — | $1.00 | 0% vs Perplexity | 127k | src |
| Sonar | Perplexity | $1.00 | $1.00 | — | — | $1.00 | 0% vs Perplexity | 127k | src |
| Qwen3.6 35B A3B | Phala | $0.200 | $1.27 | $0.056 | — | $1.00 | cheapest | 262k | src |
| Inkling Small | — | $0.450 | $1.20 | $0.100 | — | $1.01 | +4% vs Vercel AI Gateway | 524k | src |
| Inkling Small | DeepInfra | $0.450 | $1.20 | $0.100 | — | $1.01 | +4% vs Vercel AI Gateway | 524k | src |
| Qwen3.5-35B-A3B | Alibaba | $0.163 | $1.30 | — | — | $1.02 | cheapest | 262k | src |
| Qwen3.8 27B | Near AI | $0.040 | $1.35 | $0.018 | — | $1.02 | +215% vs Vercel AI Gateway | 262k | src |
| DeepSeek V4 Flash 0731 | Novita | $0.409 | $1.23 | $0.026 | — | $1.02 | +665% vs Vercel AI Gateway | 1.0M | src |
| GLM 5.3 FlashX | — | $0.370 | $1.25 | $0.090 | — | $1.03 | 0% vs Vercel AI Gateway | 1.0M | src |
| GLM 5.3 FlashX | Z.AI | $0.370 | $1.25 | $0.090 | — | $1.03 | 0% vs Vercel AI Gateway | 1.0M | src |
| Llama 3.3 70B Instruct | Together | $1.04 | $1.04 | — | — | $1.04 | cheapest | 131k | src |
| Qwen3.7 Plus | — | $0.320 | $1.28 | $0.064 | $0.400 | $1.04 | cheapest | 1M | src |
| Qwen3.7 Plus | Alibaba | $0.320 | $1.28 | $0.064 | $0.400 | $1.04 | cheapest | 1M | src |
| GPT-5.6 Luna | Azure azure/us | $0.220 | $1.32 | $0.022 | $0.275 | $1.04 | cheapest | 1.1M | src |
| GPT-5.6 Luna | Bedrock | $0.220 | $1.32 | $0.022 | $0.275 | $1.04 | cheapest | 1.1M | src |
| GPT-5.6 Luna | Azure azure/eu | $0.220 | $1.32 | $0.022 | $0.275 | $1.04 | cheapest | 1.1M | src |
| GPT-5.6 Luna Pro | Azure azure/eu | $0.220 | $1.32 | $0.022 | $0.275 | $1.04 | cheapest | 1.1M | src |
| MiniMax M3 | Model Run | $0.300 | $1.30 | $0.050 | — | $1.05 | cheapest | 1.0M | src |
| GPT-5.4 Nano | Azure azure/us | $0.220 | $1.38 | $0.022 | — | $1.09 | cheapest | 400k | src |
| DeepSeek V4 Flash 0423 | Cloudflare | $0.440 | $1.32 | $0.014 | — | $1.10 | cheapest | 384k | src |
| DeepSeek V4 Flash 0731 | Atlas Cloud | $0.440 | $1.32 | $0.028 | — | $1.10 | +722% vs Vercel AI Gateway | 1.0M | src |
| DeepSeek V4 Flash 0731 | Cloudflare | $0.440 | $1.32 | $0.014 | — | $1.10 | +722% vs Vercel AI Gateway | 1.0M | src |
| DeepSeek V4 Flash Vision Exp | GMI Cloud | $0.440 | $1.32 | $0.014 | — | $1.10 | +104% vs Vercel AI Gateway | 1.0M | src |
| DeepSeek V4 Flash Vision Exp | Silicon Flow | $0.440 | $1.32 | $0.028 | — | $1.10 | +104% vs Vercel AI Gateway | 1.0M | src |
| Morph V3 Fast | — | $0.800 | $1.20 | — | — | $1.10 | 0% vs Vercel AI Gateway | 82k | src |
| Morph V3 Fast | Morph | $0.800 | $1.20 | — | — | $1.10 | 0% vs Vercel AI Gateway | 82k | src |
| GLM 4.7 | DeepInfra | $0.320 | $1.40 | $0.064 | — | $1.13 | cheapest | 203k | src |
| Relace Apply 3 | — | $0.850 | $1.25 | — | — | $1.15 | cheapest | 256k | src |
| Relace Apply 3 | Relace | $0.850 | $1.25 | — | — | $1.15 | cheapest | 256k | src |
| Perceptron Mk1 | — | $0.150 | $1.50 | — | — | $1.16 | cheapest | 33k | src |
| Perceptron Mk1 | Perceptron | $0.150 | $1.50 | — | — | $1.16 | cheapest | 33k | src |
| Perceptron Mk1.5 | — | $0.150 | $1.50 | — | — | $1.16 | cheapest | 37k | src |
| Perceptron Mk1.5 | Perceptron | $0.150 | $1.50 | — | — | $1.16 | cheapest | 37k | src |
| Gemini 3 Flash Preview | $0.250 | $1.50 | $0.025 | $0.042 | $1.19 | cheapest | 1.0M | src | |
| Gemini 3 Flash Preview | Google AI Studio | $0.250 | $1.50 | $0.025 | $0.042 | $1.19 | cheapest | 1.0M | src |
| Gemini 3 Flash Preview | $0.250 | $1.50 | — | — | $1.19 | cheapest | 1.0M | src | |
| Gemini 3 Flash Preview (batch) | — | $0.250 | $1.50 | — | — | $1.19 | cheapest | 1.0M | src |
| Gemini 3.1 Flash Lite | — | $0.250 | $1.50 | $0.025 | $0.083 | $1.19 | cheapest | 1.0M | src |
| Gemini 3.1 Flash Lite | Google AI Studio google-ai-studio | $0.250 | $1.50 | $0.025 | $0.083 | $1.19 | cheapest | 1.0M | src |
| Gemini 3.1 Flash Lite | Google google-vertex/global | $0.250 | $1.50 | $0.025 | $0.083 | $1.19 | cheapest | 1.0M | src |
| Gemini 3.1 Flash Lite Preview | — | $0.250 | $1.50 | $0.025 | $0.083 | $1.19 | cheapest | 1.0M | src |
| Gemini 3.1 Flash Lite Preview | Google AI Studio google-ai-studio | $0.250 | $1.50 | $0.025 | $0.083 | $1.19 | cheapest | 1.0M | src |
| Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) | — | $0.250 | $1.50 | — | — | $1.19 | cheapest | 66k | src |
| Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) | $0.250 | $1.50 | — | — | $1.19 | cheapest | 66k | src | |
| Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) | Google AI Studio | $0.250 | $1.50 | — | — | $1.19 | cheapest | 66k | src |
| GLM 5.2 | DeepInfra | $0.450 | $1.44 | $0.084 | — | $1.19 | cheapest | 1.0M | src |
| Command A+ | — | $0.300 | $1.50 | $0.150 | — | $1.20 | cheapest | 192k | src |
| Command A+ | Cohere | $0.300 | $1.50 | $0.150 | — | $1.20 | cheapest | 192k | src |
| Muse Glimmer 30B | Together | $0.350 | $1.50 | $0.040 | — | $1.21 | cheapest | 131k | src |
| Qwen3 Coder 480B A35B | Venice | $0.350 | $1.50 | $0.040 | — | $1.21 | cheapest | 256k | src |
| GLM 5.3 Flash | Reka | $0.060 | $1.60 | $0.040 | — | $1.22 | cheapest | 1.0M | src |
| GLM Flash Latest | — | $0.060 | $1.60 | $0.040 | — | $1.22 | cheapest | 1.0M | src |
| Qwen3.5-27B | Alibaba | $0.195 | $1.56 | — | — | $1.22 | cheapest | 262k | src |
| Aion 3.5 Mini | — | $0.700 | $1.40 | $0.180 | — | $1.23 | cheapest | 262k | src |
| Aion 3.5 Mini | Aion Labs | $0.700 | $1.40 | $0.180 | — | $1.23 | cheapest | 262k | src |
| Aion-3.0-Mini | — | $0.700 | $1.40 | $0.180 | — | $1.23 | cheapest | 131k | src |
| Aion-3.0-Mini | Aion Labs | $0.700 | $1.40 | $0.180 | — | $1.23 | cheapest | 131k | src |
| Qwen3.5 Plus 2026-02-15 | — | $0.260 | $1.56 | — | — | $1.24 | cheapest | 1M | src |
| Qwen3.5 Plus 2026-02-15 | Alibaba | $0.260 | $1.56 | — | — | $1.24 | cheapest | 1M | src |
| DeepSeek V3.2 | Friendli | $0.500 | $1.50 | $0.250 | — | $1.25 | cheapest | 164k | src |
| GPT-3.5 Turbo | — | $0.500 | $1.50 | — | — | $1.25 | cheapest | 16k | src |
| GPT-3.5 Turbo | OpenAI | $0.500 | $1.50 | — | — | $1.25 | cheapest | 16k | src |
| Mistral Large 3 2512 | — | $0.500 | $1.50 | $0.050 | — | $1.25 | cheapest | 262k | src |
| Mistral Large 3 2512 | Mistral | $0.500 | $1.50 | $0.050 | — | $1.25 | cheapest | 262k | src |
| GLM 5.3 | Sail Research | $0.500 | $1.50 | $0.119 | — | $1.25 | cheapest | 1.0M | src |
| GLM 5.3 | Inceptron | $0.550 | $1.50 | $0.180 | — | $1.27 | cheapest | 1.0M | src |
| DeepSeek V3.1 | Samba Nova | $0.650 | $1.50 | — | — | $1.29 | +66% vs Vercel AI Gateway | 131k | src |
| GLM 4.6 | DeepInfra | $0.400 | $1.60 | $0.080 | — | $1.30 | cheapest | 203k | src |
| GPT-4.1 Mini | — | $0.400 | $1.60 | $0.100 | — | $1.30 | cheapest | 1.0M | src |
| GPT-4.1 Mini | Azure | $0.400 | $1.60 | $0.100 | — | $1.30 | cheapest | 1.0M | src |
| GPT-4.1 Mini | OpenAI | $0.400 | $1.60 | $0.100 | — | $1.30 | cheapest | 1.0M | src |
| Gemini 3.1 Flash Lite | Google google-vertex/eu | $0.275 | $1.65 | $0.028 | $0.083 | $1.31 | cheapest | 1.0M | src |
| Gemini 3.1 Flash Lite | Google google-vertex/us | $0.275 | $1.65 | $0.028 | $0.083 | $1.31 | cheapest | 1.0M | src |
| Qwen3.8 27B | Cerebras | $0.990 | $1.49 | $0.990 | — | $1.36 | +320% vs Vercel AI Gateway | 66k | src |
| DeepSeek V3.1 | Core Weave | $0.550 | $1.65 | $0.550 | — | $1.38 | +77% vs Vercel AI Gateway | 161k | src |
| Mistral Large 3 2512 | Mistral mistral/eu | $0.550 | $1.65 | $0.055 | — | $1.38 | cheapest | 262k | src |
| Aion-2.0 | — | $0.800 | $1.60 | $0.200 | — | $1.40 | cheapest | 131k | src |
| Aion-2.0 | Aion Labs | $0.800 | $1.60 | $0.200 | — | $1.40 | cheapest | 131k | src |
| Aion-RP 1.0 (8B) | — | $0.800 | $1.60 | — | — | $1.40 | cheapest | 33k | src |
| Aion-RP 1.0 (8B) | Aion Labs | $0.800 | $1.60 | — | — | $1.40 | cheapest | 33k | src |
| DeepSeek V3.2 | $0.560 | $1.68 | — | — | $1.40 | cheapest | 164k | src | |
| Qwen3 Coder 480B A35B | $0.220 | $1.80 | — | — | $1.41 | cheapest | 262k | src | |
| Qwen3.5-35B-A3B | Atlas Cloud | $0.225 | $1.80 | $0.225 | — | $1.41 | cheapest | 262k | src |
| Qwen3.5-35B-A3B | Silicon Flow | $0.240 | $1.80 | $0.150 | — | $1.41 | cheapest | 262k | src |
| Qwen3.6 35B A3B | Silicon Flow | $0.240 | $1.80 | $0.150 | — | $1.41 | cheapest | 262k | src |
| GLM 4.7 | DeepInfra fp4 | $0.400 | $1.75 | $0.080 | — | $1.41 | cheapest | 203k | src |
| GLM 4.6 | Venice | $0.430 | $1.75 | $0.080 | — | $1.42 | cheapest | 198k | src |
| Nemotron 3 Ultra | DeepInfra | $0.400 | $1.76 | $0.080 | — | $1.42 | cheapest | 262k | src |
| DeepSeek V3.1 | Mara | $0.600 | $1.70 | — | — | $1.43 | +84% vs Vercel AI Gateway | 131k | src |
| Qwen3.5 Plus 2026-04-20 | — | $0.300 | $1.80 | — | $0.375 | $1.43 | cheapest | 1M | src |
| Qwen3.5 Plus 2026-04-20 | Alibaba | $0.300 | $1.80 | — | $0.375 | $1.43 | cheapest | 1M | src |
| GPT-4.1 Mini | Azure azure/swedencentral | $0.440 | $1.76 | $0.110 | — | $1.43 | cheapest | 1.0M | src |
| Qwen3.8 27B | DeepInfra | $0.150 | $1.88 | $0.037 | — | $1.44 | +344% vs Vercel AI Gateway | 262k | src |
| GLM 5.2 | StreamLake | $0.556 | $1.75 | $0.103 | — | $1.45 | cheapest | 1.0M | src |
| DeepSeek V4.1 Flash | Fireworks fireworks/us | $0.450 | $1.80 | $0.0090 | — | $1.46 | cheapest | 1.0M | src |
| MiMo-V2.5-Pro | DigitalOcean | $0.480 | $1.80 | $0.096 | — | $1.47 | cheapest | 262k | src |
| Kimi K2.6 | Baidu | $0.432 | $1.82 | $0.073 | — | $1.47 | cheapest | 262k | src |
| Qwen3 VL 235B A22B Instruct | — | $0.210 | $1.90 | $0.100 | — | $1.48 | +108% vs Vercel AI Gateway | 262k | src |
| Qwen3 VL 235B A22B Instruct | Venice | $0.210 | $1.90 | $0.100 | — | $1.48 | +108% vs Vercel AI Gateway | 128k | src |
| Qwen3 VL 235B A22B Instruct | Parasail | $0.210 | $1.90 | $0.100 | — | $1.48 | +108% vs Vercel AI Gateway | 131k | src |
| GLM 5.2 | DeepInfra fp4 | $0.563 | $1.80 | $0.105 | — | $1.49 | cheapest | 1.0M | src |
| Gemini 3.6 Flash | $0.375 | $1.88 | $0.037 | $0.021 | $1.50 | cheapest | 1.0M | src | |
| Gemini 3.6 Flash | Google AI Studio | $0.375 | $1.88 | $0.037 | $0.021 | $1.50 | cheapest | 1.0M | src |
| Gemini 3.6 Flash | $0.375 | $1.88 | $0.037 | $0.042 | $1.50 | cheapest | 1.0M | src | |
| Gemini 3.6 Flash (batch) | — | $0.375 | $1.88 | $0.037 | $0.042 | $1.50 | cheapest | 1.0M | src |
| Gemini 3.7 Flash | $0.375 | $1.88 | $0.037 | $0.021 | $1.50 | cheapest | 1.0M | src | |
| Gemini 3.7 Flash | Google AI Studio | $0.375 | $1.88 | $0.037 | $0.021 | $1.50 | cheapest | 1.0M | src |
| Gemini 3.7 Flash | $0.375 | $1.88 | $0.037 | $0.042 | $1.50 | cheapest | 1.0M | src | |
| Gemini 3.7 Flash (batch) | — | $0.375 | $1.88 | $0.037 | $0.042 | $1.50 | cheapest | 1.0M | src |
| Gemini 3.8 Flash | Google AI Studio | $0.375 | $1.88 | $0.037 | $0.021 | $1.50 | cheapest | 1.0M | src |
| Gemini 3.8 Flash | $0.375 | $1.88 | $0.037 | $0.021 | $1.50 | cheapest | 1.0M | src | |
| Gemini 3.8 Flash | $0.375 | $1.88 | $0.037 | $0.042 | $1.50 | cheapest | 1.0M | src | |
| Gemini 3.8 Flash (batch) | — | $0.375 | $1.88 | $0.037 | $0.042 | $1.50 | cheapest | 1.0M | src |
| GLM 4.5V | — | $0.600 | $1.80 | $0.110 | — | $1.50 | 0% vs Novita | 66k | src |
| GLM 4.5V | Novita | $0.600 | $1.80 | $0.110 | — | $1.50 | 0% vs Novita | 66k | src |
| GLM 4.5V | Z.AI | $0.600 | $1.80 | $0.110 | — | $1.50 | 0% vs Novita | 66k | src |
| MiniMax M2.7 | Groq | $0.600 | $1.80 | — | — | $1.50 | +120% vs Vercel AI Gateway | 197k | src |
| Qwen3.8 27B | AkashML | $0.225 | $1.98 | $0.050 | — | $1.54 | +374% vs Vercel AI Gateway | 262k | src |
| Qwen3.6 Plus | — | $0.325 | $1.95 | — | $0.406 | $1.54 | cheapest | 1M | src |
| Qwen3.6 Plus | Alibaba | $0.325 | $1.95 | — | $0.406 | $1.54 | cheapest | 1M | src |
| GLM 4.7 | Venice | $0.400 | $1.93 | $0.080 | — | $1.55 | cheapest | 198k | src |
| GLM 5.3 | Baidu | $0.599 | $1.88 | $0.111 | — | $1.56 | cheapest | 1.0M | src |
| GPT-5 Mini | — | $0.250 | $2.00 | $0.025 | — | $1.56 | cheapest | 400k | src |
| GPT-5 Mini | Azure | $0.250 | $2.00 | $0.030 | — | $1.56 | cheapest | 400k | src |
| GPT-5 Mini | OpenAI openai | $0.250 | $2.00 | $0.025 | — | $1.56 | cheapest | 400k | src |
| GPT-5.1-Codex-Mini | — | $0.250 | $2.00 | $0.030 | — | $1.56 | cheapest | 400k | src |
| GPT-5.1-Codex-Mini | Azure | $0.250 | $2.00 | $0.030 | — | $1.56 | cheapest | 400k | src |
| Qwen3.5-27B | Silicon Flow | $0.250 | $2.00 | — | — | $1.56 | cheapest | 262k | src |
| Qwen3.6 27B | — | $0.250 | $2.00 | $0.025 | — | $1.56 | cheapest | 262k | src |
| Qwen3.6 27B | Chutes | $0.250 | $2.00 | $0.025 | — | $1.56 | cheapest | 262k | src |
| Seed 1.6 | — | $0.250 | $2.00 | — | — | $1.56 | 0% vs Vercel AI Gateway | 262k | src |
| Seed 1.6 | Seed | $0.250 | $2.00 | — | — | $1.56 | 0% vs Vercel AI Gateway | 262k | src |
| Seed-2.0-Lite | — | $0.250 | $2.00 | — | — | $1.56 | cheapest | 262k | src |
| Seed-2.0-Lite | Seed | $0.250 | $2.00 | — | — | $1.56 | cheapest | 262k | src |
| Kimi K2.6 | Chutes | $0.450 | $1.95 | $0.045 | — | $1.57 | cheapest | 262k | src |
| GLM 5 | StreamLake | $0.600 | $1.92 | $0.120 | — | $1.59 | cheapest | 198k | src |
| GLM 5 | GMI Cloud | $0.600 | $1.92 | $0.120 | — | $1.59 | cheapest | 203k | src |
| Devstral 2 2512 | — | $0.400 | $2.00 | $0.040 | — | $1.60 | cheapest | 262k | src |
| Devstral 2 2512 | Mistral | $0.400 | $2.00 | $0.040 | — | $1.60 | cheapest | 262k | src |
| MiMo-V2.5 | Venice | $0.400 | $2.00 | $0.080 | — | $1.60 | cheapest | 1M | src |
| Mistral Medium 3 | — | $0.400 | $2.00 | $0.040 | — | $1.60 | cheapest | 131k | src |
| Mistral Medium 3 | Mistral | $0.400 | $2.00 | $0.040 | — | $1.60 | cheapest | 131k | src |
| Mistral Medium 3.1 | — | $0.400 | $2.00 | $0.040 | — | $1.60 | cheapest | 131k | src |
| Mistral Medium 3.1 | Mistral | $0.400 | $2.00 | $0.040 | — | $1.60 | cheapest | 131k | src |
| GLM 5.3 | DeepInfra | $0.450 | $2.00 | $0.100 | — | $1.61 | cheapest | 1.0M | src |
| GLM 5.3 (batch) | — | $0.450 | $2.00 | $0.100 | — | $1.61 | cheapest | 1.0M | src |
| GLM 4.7 | — | $0.540 | $1.98 | $0.099 | — | $1.62 | cheapest | 205k | src |
| GLM 4.7 | Novita | $0.540 | $1.98 | $0.099 | — | $1.62 | cheapest | 205k | src |
| GLM 4.6 | — | $0.500 | $2.00 | $0.100 | — | $1.63 | cheapest | 205k | src |
| GLM 4.6 | DeepInfra fp4 | $0.500 | $2.00 | $0.100 | — | $1.63 | cheapest | 203k | src |
| Qwen3.5-122B-A10B | — | $0.260 | $2.08 | — | — | $1.63 | cheapest | 262k | src |
| Qwen3.5-122B-A10B | Silicon Flow | $0.260 | $2.08 | — | — | $1.63 | cheapest | 262k | src |
| Qwen3.5-122B-A10B | Alibaba | $0.260 | $2.08 | — | — | $1.63 | cheapest | 262k | src |
| DeepSeek V4 Pro 0813 | — | $0.660 | $1.98 | $0.022 | — | $1.65 | cheapest | 1.0M | src |
| DeepSeek V4 Pro 0813 | StreamLake | $0.660 | $1.98 | $0.022 | — | $1.65 | cheapest | 1.0M | src |
| DeepSeek V4 Pro 0813 | DeepSeek | $0.660 | $1.98 | $0.022 | — | $1.65 | cheapest | 1.0M | src |
| Morph V3 Large | — | $0.900 | $1.90 | — | — | $1.65 | 0% vs Vercel AI Gateway | 262k | src |
| Morph V3 Large | Morph | $0.900 | $1.90 | — | — | $1.65 | 0% vs Vercel AI Gateway | 262k | src |
| Qwen3.8 27B | Darkbloom | $0.035 | $2.20 | $0.018 | — | $1.66 | +410% vs Vercel AI Gateway | 262k | src |
| Qwen3.8 27B | Reka | $0.040 | $2.20 | $0.020 | — | $1.66 | +411% vs Vercel AI Gateway | 262k | src |
| DeepSeek V4 Pro 0423 | GMI Cloud | $0.957 | $1.91 | $0.080 | — | $1.67 | cheapest | 1.0M | src |
| Qwen3.5-27B | Atlas Cloud | $0.270 | $2.16 | $0.270 | — | $1.69 | cheapest | 262k | src |
| GLM 5.2 | Novita | $0.650 | $2.04 | $0.121 | — | $1.69 | cheapest | 1.0M | src |
| Qwen3.8 27B | — | $0.240 | $2.20 | $0.050 | — | $1.71 | +426% vs Vercel AI Gateway | 1M | src |
| Qwen3.8 27B | Parasail | $0.240 | $2.20 | $0.050 | — | $1.71 | +426% vs Vercel AI Gateway | 262k | src |
| GPT-5 Mini | Azure azure/swedencentral | $0.275 | $2.20 | $0.033 | — | $1.72 | cheapest | 400k | src |
| Qwen3.8 27B | Wafer | $0.040 | $2.30 | $0.039 | — | $1.74 | +434% vs Vercel AI Gateway | 262k | src |
| Mistral Large 4 | — | $0.680 | $2.09 | $0.070 | — | $1.74 | 0% vs Vercel AI Gateway | 1.0M | src |
| Mistral Large 4 | Mistral | $0.680 | $2.09 | $0.070 | — | $1.74 | 0% vs Vercel AI Gateway | 1.0M | src |
| R1 0528 | — | $0.500 | $2.15 | $0.350 | — | $1.74 | cheapest | 164k | src |
| R1 0528 | DeepInfra | $0.500 | $2.15 | $0.350 | — | $1.74 | cheapest | 164k | src |
| GPT-3.5 Turbo (older v0613) | — | $1.00 | $2.00 | — | — | $1.75 | cheapest | 4k | src |
| GPT-3.5 Turbo (older v0613) | Azure | $1.00 | $2.00 | — | — | $1.75 | cheapest | 4k | src |
| Grok 4.3 | xAI | $1.00 | $2.00 | $0.160 | — | $1.75 | cheapest | 1M | src |
| Grok 4.3 (batch) | — | $1.00 | $2.00 | $0.160 | — | $1.75 | cheapest | 1M | src |
| Grok Build 0.1 | — | $1.00 | $2.00 | $0.200 | — | $1.75 | 0% vs Vercel AI Gateway | 256k | src |
| Grok Build 0.1 | xAI | $1.00 | $2.00 | $0.200 | — | $1.75 | 0% vs Vercel AI Gateway | 256k | src |
| MiniMax M1 | MiniMax | $0.400 | $2.20 | — | — | $1.75 | cheapest | 1M | src |
| Mistral Medium 3 | Mistral mistral/eu | $0.440 | $2.20 | $0.044 | — | $1.76 | cheapest | 131k | src |
| Mistral Medium 3.1 | Mistral mistral/eu | $0.440 | $2.20 | $0.044 | — | $1.76 | cheapest | 131k | src |
| R1 0528 | Silicon Flow | $0.500 | $2.18 | — | — | $1.76 | cheapest | 164k | src |
| Llama 3.3 70B Instruct | Cloudflare | $0.293 | $2.25 | — | — | $1.76 | cheapest | 24k | src |
| Nemotron 3 Ultra | DeepInfra fp4 | $0.500 | $2.20 | $0.100 | — | $1.77 | cheapest | 262k | src |
| GPT-5.4 Mini | OpenAI | $0.375 | $2.25 | $0.037 | — | $1.78 | cheapest | 400k | src |
| GPT-5.4 Mini | OpenAI | $0.375 | $2.25 | $0.037 | — | $1.78 | cheapest | 400k | src |
| GPT-5.4 Mini (batch) | — | $0.375 | $2.25 | $0.037 | — | $1.78 | cheapest | 400k | src |
| Qwen3.8 27B | Ionstream | $0.089 | $2.35 | $0.085 | — | $1.78 | +449% vs Vercel AI Gateway | 262k | src |
| GLM 4.6 | Novita | $0.550 | $2.20 | $0.110 | — | $1.79 | cheapest | 205k | src |
| MiniMax M1 | — | $0.550 | $2.20 | — | — | $1.79 | cheapest | 1M | src |
| MiniMax M1 | Novita | $0.550 | $2.20 | — | — | $1.79 | cheapest | 1M | src |
| o3 Mini | OpenAI | $0.550 | $2.20 | $0.275 | — | $1.79 | cheapest | 200k | src |
| o3 Mini (batch) | — | $0.550 | $2.20 | $0.275 | — | $1.79 | cheapest | 200k | src |
| o4 Mini | OpenAI | $0.550 | $2.20 | $0.138 | — | $1.79 | cheapest | 200k | src |
| o4 Mini (batch) | — | $0.550 | $2.20 | $0.138 | — | $1.79 | cheapest | 200k | src |
| GLM 4.5 | — | $0.600 | $2.20 | $0.110 | — | $1.80 | 0% vs Vercel AI Gateway | 131k | src |
| GLM 4.5 | Z.AI | $0.600 | $2.20 | $0.110 | — | $1.80 | 0% vs Vercel AI Gateway | 131k | src |
| GLM 4.6 | Z.AI | $0.600 | $2.20 | $0.110 | — | $1.80 | cheapest | 203k | src |
| GLM 4.7 | $0.600 | $2.20 | — | — | $1.80 | cheapest | 200k | src | |
| GLM 4.7 | Z.AI | $0.600 | $2.20 | $0.110 | — | $1.80 | cheapest | 203k | src |
| GLM 5.2 | DigitalOcean | $0.700 | $2.20 | $0.105 | — | $1.82 | cheapest | 1.0M | src |
| GLM 5.2 | Silicon Flow | $0.700 | $2.20 | $0.130 | — | $1.82 | cheapest | 1.0M | src |
| GLM 5.3 | Silicon Flow | $0.700 | $2.20 | $0.130 | — | $1.82 | cheapest | 1.0M | src |
| GLM 5.3 | Novita | $0.700 | $2.20 | $0.130 | — | $1.82 | cheapest | 1.0M | src |
| DeepSeek V4 Pro 0423 | DigitalOcean | $1.04 | $2.09 | $0.209 | — | $1.83 | cheapest | 1.0M | src |
| DeepSeek V4 Pro 0423 | Reka | $1.05 | $2.10 | $0.210 | — | $1.84 | cheapest | 1.0M | src |
| Qwen3.5 397B A17B | Alibaba | $0.390 | $2.34 | — | — | $1.85 | cheapest | 262k | src |
| GLM 5 | Baidu | $0.700 | $2.24 | $0.140 | — | $1.85 | cheapest | 203k | src |
| R1 0528 | StreamLake | $0.571 | $2.29 | — | — | $1.86 | cheapest | 128k | src |
| Kimi K2 0711 | — | $0.570 | $2.30 | — | — | $1.87 | cheapest | 131k | src |
| Kimi K2 0711 | Novita | $0.570 | $2.30 | — | — | $1.87 | cheapest | 131k | src |
| GPT-3.5 Turbo Instruct | — | $1.50 | $2.00 | — | — | $1.88 | cheapest | 4k | src |
| GPT-3.5 Turbo Instruct | OpenAI | $1.50 | $2.00 | — | — | $1.88 | cheapest | 4k | src |
| MiniMax M2.1 | MiniMax fp8 | $0.300 | $2.40 | $0.030 | — | $1.88 | +92% vs Vercel AI Gateway | 205k | src |
| Nemotron 3 Super | Crusoe | $0.300 | $2.40 | $0.150 | — | $1.88 | cheapest | 262k | src |
| Qwen3.5-122B-A10B | Atlas Cloud | $0.300 | $2.40 | $0.300 | — | $1.88 | cheapest | 262k | src |
| Qwen3.5-27B | Phala | $0.300 | $2.40 | $0.030 | — | $1.88 | cheapest | 262k | src |
| Qwen3.5-27B | Novita | $0.300 | $2.40 | — | — | $1.88 | cheapest | 262k | src |
| Qwen3.8 27B | Deka LLM | $0.040 | $2.50 | $0.020 | — | $1.89 | +480% vs Vercel AI Gateway | 262k | src |
| GPT-5.6 Luna | OpenAI openai/fast | $0.400 | $2.40 | $0.040 | $0.500 | $1.90 | cheapest | 1.1M | src |
| GPT-5.6 Luna Pro | OpenAI openai/fast | $0.400 | $2.40 | $0.040 | $0.500 | $1.90 | cheapest | 1.1M | src |
| Mistral Large 4 | Mistral mistral/eu | $0.748 | $2.30 | $0.077 | — | $1.91 | +10% vs Vercel AI Gateway | 524k | src |
| Qwen3.8 27B | Model Run | $0.200 | $2.50 | $0.090 | — | $1.93 | +492% vs Vercel AI Gateway | 262k | src |
| Qwen3.8 27B | Mancer 2 | $0.200 | $2.50 | — | — | $1.93 | +492% vs Vercel AI Gateway | 262k | src |
| Qwen3.8 27B | Phala | $0.200 | $2.50 | $0.050 | — | $1.93 | +492% vs Vercel AI Gateway | 1M | src |
| DeepSeek V4 Pro 0813 | Wafer | $0.250 | $2.50 | $0.249 | — | $1.94 | cheapest | 1.0M | src |
| Kimi K2.6 | DigitalOcean | $0.570 | $2.40 | $0.114 | — | $1.94 | cheapest | 262k | src |
| Qwen3.6 27B | Reka | $0.290 | $2.50 | $0.029 | — | $1.95 | cheapest | 262k | src |
| DeepSeek V4.1 Flash | Baseten baseten/fast | $0.600 | $2.40 | $0.014 | — | $1.95 | cheapest | 1.0M | src |
| Gemini 2.5 Flash | — | $0.300 | $2.50 | $0.030 | $0.083 | $1.95 | cheapest | 1.0M | src |
| Gemini 2.5 Flash | $0.300 | $2.50 | $0.030 | $0.083 | $1.95 | cheapest | 1.0M | src | |
| Gemini 2.5 Flash | Google AI Studio google-ai-studio | $0.300 | $2.50 | $0.030 | $0.083 | $1.95 | cheapest | 1.0M | src |
| Gemini 3.5 Flash Lite | — | $0.300 | $2.50 | $0.030 | $0.083 | $1.95 | cheapest | 1.0M | src |
| Gemini 3.5 Flash Lite | Google AI Studio google-ai-studio | $0.300 | $2.50 | $0.030 | $0.083 | $1.95 | cheapest | 1.0M | src |
| Gemini 3.5 Flash Lite | Google google-vertex/global | $0.300 | $2.50 | $0.030 | $0.083 | $1.95 | cheapest | 1.0M | src |
| GPT Audio Mini | — | $0.600 | $2.40 | — | — | $1.95 | cheapest | 128k | src |
| GPT Audio Mini | OpenAI | $0.600 | $2.40 | — | — | $1.95 | cheapest | 128k | src |
| MiniMax M2.5 | MiniMax fp8 | $0.600 | $2.40 | $0.060 | — | $1.95 | cheapest | 205k | src |
| MiniMax M2.7 | MiniMax fp8 | $0.600 | $2.40 | $0.060 | — | $1.95 | +186% vs Vercel AI Gateway | 205k | src |
| MiniMax M3 | Mara | $0.600 | $2.40 | — | — | $1.95 | cheapest | 1.0M | src |
| MiniMax M3 | Samba Nova | $0.600 | $2.40 | $0.060 | — | $1.95 | cheapest | 1.0M | src |
| Moondream 3 Preview | — | $0.300 | $2.50 | — | — | $1.95 | cheapest | 32k | src |
| Moondream 3 Preview | Prime Intellect | $0.300 | $2.50 | — | — | $1.95 | cheapest | 32k | src |
| Moondream 3.1 | — | $0.300 | $2.50 | — | — | $1.95 | cheapest | 32k | src |
| Moondream 3.1 | Prime Intellect | $0.300 | $2.50 | — | — | $1.95 | cheapest | 32k | src |
| Nano Banana (Gemini 2.5 Flash Image) | — | $0.300 | $2.50 | $0.030 | $0.083 | $1.95 | 0% vs Vercel AI Gateway | 33k | src |
| Nano Banana (Gemini 2.5 Flash Image) | $0.300 | $2.50 | $0.030 | $0.083 | $1.95 | 0% vs Vercel AI Gateway | 33k | src | |
| Nemotron 3 Ultra | — | $0.600 | $2.40 | $0.120 | — | $1.95 | cheapest | 262k | src |
| Nemotron 3 Ultra | Baseten | $0.600 | $2.40 | $0.120 | — | $1.95 | cheapest | 203k | src |
| Nova 2 Lite | — | $0.300 | $2.50 | — | — | $1.95 | 0% vs Vercel AI Gateway | 1M | src |
| Nova 2 Lite | Bedrock | $0.300 | $2.50 | — | — | $1.95 | 0% vs Vercel AI Gateway | 1M | src |
| GLM 5.2 | — | $0.620 | $2.42 | $0.140 | — | $1.97 | cheapest | 1.0M | src |
| GLM 5.2 | Core Weave | $0.620 | $2.42 | $0.140 | — | $1.97 | cheapest | 1.0M | src |
| Kimi K2.5 | Atlas Cloud | $0.490 | $2.50 | $0.200 | — | $2.00 | cheapest | 262k | src |
| Claude Haiku 4.5 | Anthropic | $0.500 | $2.50 | $0.050 | $0.625 | $2.00 | cheapest | 200k | src |
| Claude Haiku 4.5 (batch) | — | $0.500 | $2.50 | $0.050 | $0.625 | $2.00 | cheapest | 200k | src |
| Kimi K2.5 | — | $0.500 | $2.50 | $0.150 | — | $2.00 | cheapest | 262k | src |
| Kimi K2.5 | Silicon Flow | $0.500 | $2.50 | $0.150 | — | $2.00 | cheapest | 262k | src |
| Seed 2.1 Turbo | — | $0.500 | $2.50 | — | — | $2.00 | 0% vs Vercel AI Gateway | 262k | src |
| Seed 2.1 Turbo | Seed | $0.500 | $2.50 | — | — | $2.00 | 0% vs Vercel AI Gateway | 262k | src |
| Qwen3.5-27B | — | $0.260 | $2.60 | — | — | $2.02 | cheapest | 262k | src |
| Qwen3.5-27B | Reka | $0.260 | $2.60 | $0.026 | — | $2.02 | cheapest | 33k | src |
| Qwen3.5-27B | DeepInfra | $0.260 | $2.60 | — | — | $2.02 | cheapest | 262k | src |
| GLM 5.3 | DeepInfra | $0.563 | $2.50 | $0.125 | — | $2.02 | cheapest | 1.0M | src |
| Qwen3.8 27B | Alibaba | $0.425 | $2.55 | $0.085 | $0.531 | $2.02 | +521% vs Vercel AI Gateway | 1M | src |
| GLM 5.3 | Tenstorrent | $0.600 | $2.50 | $0.100 | — | $2.02 | cheapest | 1.0M | src |
| Kimi K2 0905 | — | $0.600 | $2.50 | — | — | $2.02 | cheapest | 262k | src |
| Kimi K2 0905 | Novita | $0.600 | $2.50 | — | — | $2.02 | cheapest | 262k | src |
| Kimi K2 Thinking | — | $0.600 | $2.50 | $0.150 | — | $2.02 | 0% vs Novita | 262k | src |
| Kimi K2 Thinking | $0.600 | $2.50 | — | — | $2.02 | 0% vs Novita | 262k | src | |
| Kimi K2 Thinking | Novita | $0.600 | $2.50 | $0.150 | — | $2.02 | 0% vs Novita | 262k | src |
| Kimi K2.6 | StreamLake | $0.599 | $2.52 | $0.101 | — | $2.04 | cheapest | 256k | src |
| GLM 4.7 | Mancer 2 | $0.700 | $2.50 | — | — | $2.05 | cheapest | 131k | src |
| R1 | — | $0.700 | $2.50 | — | — | $2.05 | cheapest | 64k | src |
| R1 | Novita | $0.700 | $2.50 | — | — | $2.05 | cheapest | 64k | src |
| R1 0528 | Novita | $0.700 | $2.50 | $0.350 | — | $2.05 | cheapest | 164k | src |
| Hy4 preview | — | $0.834 | $2.50 | $0.042 | — | $2.08 | cheapest | 1.0M | src |
| Hy4 preview | DeepInfra | $0.834 | $2.50 | $0.042 | — | $2.08 | cheapest | 1.0M | src |
| Hy4 preview | Novita | $0.834 | $2.50 | $0.042 | — | $2.08 | cheapest | 1M | src |
| Hy4 preview | Silicon Flow | $0.834 | $2.50 | $0.042 | — | $2.08 | cheapest | 1.0M | src |
| Hy4 preview | Tencent | $0.834 | $2.50 | $0.042 | — | $2.08 | cheapest | 1.0M | src |
| GPT-5 Image Mini | — | $2.50 | $2.00 | $0.250 | — | $2.13 | cheapest | 400k | src |
| GPT-5 Image Mini | OpenAI | $2.50 | $2.00 | $0.250 | — | $2.13 | cheapest | 400k | src |
| Gemini 3.1 Flash Lite | Google google-vertex/global/priority | $0.450 | $2.70 | $0.045 | $0.150 | $2.14 | cheapest | 1.0M | src |
| Gemini 3.1 Flash Lite | Google AI Studio google-ai-studio/priority | $0.450 | $2.70 | $0.045 | $0.150 | $2.14 | cheapest | 1.0M | src |
| Gemini 3.1 Flash Lite Preview | Google AI Studio google-ai-studio/priority | $0.450 | $2.70 | $0.045 | $0.150 | $2.14 | cheapest | 1.0M | src |
| Qwen3.6 27B | Alibaba | $0.450 | $2.70 | — | — | $2.14 | cheapest | 262k | src |
| Gemini 3.5 Flash Lite | Google google-vertex/eu | $0.330 | $2.75 | $0.033 | $0.083 | $2.15 | cheapest | 1.0M | src |
| Gemini 3.5 Flash Lite | Google google-vertex/us | $0.330 | $2.75 | $0.033 | $0.083 | $2.15 | cheapest | 1.0M | src |
| GLM 5 | Silicon Flow | $0.950 | $2.55 | $0.200 | — | $2.15 | cheapest | 205k | src |
| Grok 4.20 | — | $1.25 | $2.50 | $0.200 | — | $2.19 | cheapest | 2M | src |
| Grok 4.20 | xAI | $1.25 | $2.50 | $0.200 | — | $2.19 | cheapest | 2M | src |
| Grok 4.20 Multi-Agent | — | $1.25 | $2.50 | $0.200 | — | $2.19 | 0% vs Vercel AI Gateway | 2M | src |
| Grok 4.20 Multi-Agent | xAI | $1.25 | $2.50 | $0.200 | — | $2.19 | 0% vs Vercel AI Gateway | 2M | src |
| Grok 4.3 | — | $1.25 | $2.50 | $0.200 | — | $2.19 | cheapest | 1M | src |
| Grok 4.3 | xAI | $1.25 | $2.50 | $0.200 | — | $2.19 | cheapest | 1M | src |
| GLM 5.3 | Phala | $0.840 | $2.64 | $0.156 | — | $2.19 | cheapest | 1.0M | src |
| DeepSeek V4 Pro 0423 | Cloudflare | $1.15 | $2.55 | $0.200 | — | $2.20 | cheapest | 1.0M | src |
| GLM 5.3 | Decart | $0.840 | $2.66 | $0.190 | — | $2.21 | cheapest | 1.0M | src |
| GLM 5.3 | Deka LLM | $0.180 | $2.95 | $0.150 | — | $2.26 | cheapest | 1.0M | src |
| DeepSeek V4 Pro 0423 | DeepInfra | $1.30 | $2.60 | $0.100 | — | $2.27 | cheapest | 1.0M | src |
| DeepSeek V4 Pro 0813 | DeepInfra | $1.30 | $2.60 | $0.100 | — | $2.27 | cheapest | 1.0M | src |
| Step 5 Preview | — | $1.00 | $2.70 | $0.100 | — | $2.27 | 0% vs Novita | 1.0M | src |
| Step 5 Preview | Inference Net | $1.00 | $2.70 | $0.050 | — | $2.27 | 0% vs Novita | 1.0M | src |
| Step 5 Preview | Featherless | $1.00 | $2.70 | $0.100 | — | $2.27 | 0% vs Novita | 262k | src |
| Step 5 Preview | DeepInfra | $1.00 | $2.70 | $0.100 | — | $2.27 | 0% vs Novita | 1.0M | src |
| Step 5 Preview | Step Fun | $1.00 | $2.70 | $0.100 | — | $2.27 | 0% vs Novita | 1M | src |
| Kimi K2.5 | Novita | $0.570 | $2.85 | $0.095 | — | $2.28 | cheapest | 262k | src |
| DeepSeek V4 Pro 0813 | Ionstream | $0.370 | $2.93 | $0.088 | — | $2.29 | cheapest | 1.0M | src |
| GLM 5.3 | Io Net | $0.490 | $2.90 | $0.190 | — | $2.30 | cheapest | 262k | src |
| Qwen3.8 27B | Core Weave | $0.400 | $3.00 | $0.150 | — | $2.35 | +623% vs Vercel AI Gateway | 262k | src |
| Qwen3.8 27B | Novita | $0.420 | $3.00 | $0.085 | — | $2.35 | +625% vs Vercel AI Gateway | 1M | src |
| Qwen3.5 397B A17B | DeepInfra | $0.450 | $3.00 | $0.220 | — | $2.36 | cheapest | 262k | src |
| GLM 5.3 | DigitalOcean | $0.910 | $2.86 | $0.169 | — | $2.37 | cheapest | 1.0M | src |
| Gemini 3 Flash Preview | — | $0.500 | $3.00 | $0.050 | $0.083 | $2.38 | cheapest | 1.0M | src |
| Gemini 3 Flash Preview | Google AI Studio google-ai-studio | $0.500 | $3.00 | $0.050 | $0.083 | $2.38 | cheapest | 1.0M | src |
| Gemini 3 Flash Preview | Google google-vertex/global | $0.500 | $3.00 | $0.050 | $0.083 | $2.38 | cheapest | 1.0M | src |
| Nano Banana 2 (Gemini 3.1 Flash Image Preview) | — | $0.500 | $3.00 | — | — | $2.38 | cheapest | 66k | src |
| Nano Banana 2 (Gemini 3.1 Flash Image Preview) | Google AI Studio | $0.500 | $3.00 | — | — | $2.38 | cheapest | 66k | src |
| Nano Banana 2 (Gemini 3.1 Flash Image) | — | $0.500 | $3.00 | — | — | $2.38 | cheapest | 131k | src |
| Nano Banana 2 (Gemini 3.1 Flash Image) | Google AI Studio | $0.500 | $3.00 | — | — | $2.38 | cheapest | 66k | src |
| Nano Banana 2 (Gemini 3.1 Flash Image) | $0.500 | $3.00 | — | — | $2.38 | cheapest | 131k | src | |
| Seed-2.0-Code | — | $0.500 | $3.00 | — | — | $2.38 | cheapest | 262k | src |
| Seed-2.0-Code | Seed | $0.500 | $3.00 | — | — | $2.38 | cheapest | 262k | src |
| DeepSeek V4 Pro 0813 | Phala | $0.957 | $2.88 | $0.099 | — | $2.40 | cheapest | 1.0M | src |
| Glimpse | — | $0.600 | $3.00 | $0.060 | — | $2.40 | 0% vs Vercel AI Gateway | 262k | src |
| Glimpse | Together | $0.600 | $3.00 | $0.060 | — | $2.40 | 0% vs Vercel AI Gateway | 262k | src |
| Kimi K2.5 | Bedrock | $0.600 | $3.00 | — | — | $2.40 | cheapest | 262k | src |
| Kimi K2.7 Code | StreamLake | $0.713 | $3.00 | $0.142 | — | $2.43 | cheapest | 256k | src |
| GLM 5.2 | Atlas Cloud | $0.938 | $2.95 | $0.174 | — | $2.45 | cheapest | 1.0M | src |
| DeepSeek V4 Pro 0423 | Relace | $0.900 | $3.00 | $0.160 | — | $2.48 | cheapest | 1.0M | src |
| DeepSeek V4 Pro 0813 | Novita | $0.990 | $2.97 | $0.033 | — | $2.48 | cheapest | 1.0M | src |
| Qwen3.6 27B | Silicon Flow | $0.300 | $3.20 | — | — | $2.48 | cheapest | 262k | src |
| DeepSeek V4 Pro 0423 | Alibaba | $1.42 | $2.83 | $0.118 | — | $2.48 | cheapest | 1M | src |
| Qwen3.6 27B | DeepInfra | $0.320 | $3.20 | — | — | $2.48 | cheapest | 262k | src |
| Beam 1.0 501B A23B | — | $1.00 | $3.00 | $0.100 | — | $2.50 | cheapest | 1.0M | src |
| Beam 1.0 501B A23B | Core Weave | $1.00 | $3.00 | $0.100 | — | $2.50 | cheapest | 1.0M | src |
| Hermes 4 405B | — | $1.00 | $3.00 | — | — | $2.50 | cheapest | 131k | src |
| Hermes 4 405B | Nebius | $1.00 | $3.00 | — | — | $2.50 | cheapest | 131k | src |
| Nemotron 3 Ultra | Venice | $0.625 | $3.13 | $0.188 | — | $2.50 | cheapest | 256k | src |
| Qwen3.5-122B-A10B | Novita | $0.400 | $3.20 | — | — | $2.50 | cheapest | 262k | src |
| Relace Search | — | $1.00 | $3.00 | — | — | $2.50 | cheapest | 256k | src |
| Relace Search | Relace | $1.00 | $3.00 | — | — | $2.50 | cheapest | 256k | src |
| Kimi K2.6 | Inceptron | $0.432 | $3.20 | $0.159 | — | $2.51 | cheapest | 262k | src |
| Qwen3.8 27B | Cloudflare | $0.450 | $3.20 | $0.050 | — | $2.51 | +673% vs Vercel AI Gateway | 262k | src |
| Qwen3.8 27B | Venice | $0.450 | $3.20 | — | — | $2.51 | +673% vs Vercel AI Gateway | 262k | src |
| GLM 5.1 | Baidu | $0.965 | $3.03 | $0.179 | — | $2.51 | cheapest | 203k | src |
| Qwen3.6 27B | Phala | $0.320 | $3.25 | $0.030 | — | $2.52 | cheapest | 262k | src |
| GLM 5.1 | — | $0.966 | $3.04 | $0.179 | — | $2.52 | cheapest | 205k | src |
| GLM 5.1 | StreamLake | $0.966 | $3.04 | $0.179 | — | $2.52 | cheapest | 200k | src |
| GLM 5.2 | Alibaba | $0.966 | $3.04 | $0.193 | — | $2.52 | cheapest | 1M | src |
| Qwen3.6 27B | Venice | $0.325 | $3.25 | — | — | $2.52 | cheapest | 256k | src |
| GLM 5.1 | Chutes | $0.980 | $3.08 | $0.098 | — | $2.56 | cheapest | 203k | src |
| GLM 5.3 | GMI Cloud | $0.980 | $3.08 | $0.182 | — | $2.56 | cheapest | 1.0M | src |
| GLM 5.2 | Phala | $1.26 | $3.00 | $0.220 | — | $2.56 | cheapest | 1.0M | src |
| Nova Pro 1.0 | — | $0.800 | $3.20 | — | — | $2.60 | cheapest | 300k | src |
| Nova Pro 1.0 | Bedrock | $0.800 | $3.20 | — | — | $2.60 | cheapest | 300k | src |
| Nano Banana 2 (Gemini 3.1 Flash Image) | Google google-vertex/us | $0.550 | $3.30 | — | — | $2.61 | cheapest | 131k | src |
| Kimi K2.5 | Venice | $0.532 | $3.33 | $0.209 | — | $2.63 | cheapest | 256k | src |
| DeepSeek V4 Pro 0813 | GMI Cloud | $1.06 | $3.17 | $0.035 | — | $2.64 | cheapest | 1.0M | src |
| GLM 5 | — | $1.00 | $3.20 | $0.200 | — | $2.65 | cheapest | 205k | src |
| GLM 5 | Bedrock | $1.00 | $3.20 | — | — | $2.65 | cheapest | 203k | src |
| GLM 5 | Venice | $1.00 | $3.20 | $0.200 | — | $2.65 | cheapest | 198k | src |
| GLM 5 | Novita | $1.00 | $3.20 | $0.200 | — | $2.65 | cheapest | 203k | src |
| GLM 5 | Z.AI | $1.00 | $3.20 | $0.200 | — | $2.65 | cheapest | 203k | src |
| Kimi K2.7 Code | — | $0.671 | $3.35 | $0.180 | — | $2.68 | cheapest | 262k | src |
| Kimi K2.7 Code | Inceptron | $0.671 | $3.35 | $0.180 | — | $2.68 | cheapest | 262k | src |
| Kimi K2.6 | — | $0.650 | $3.41 | $0.150 | — | $2.72 | cheapest | 262k | src |
| Kimi K2.6 | Core Weave | $0.650 | $3.41 | $0.150 | — | $2.72 | cheapest | 262k | src |
| DeepSeek V4 Pro 0423 | Parasail | $0.450 | $3.48 | $0.100 | — | $2.72 | cheapest | 1.0M | src |
| DeepSeek V4 Pro 0423 | Silicon Flow | $1.50 | $3.13 | $0.135 | — | $2.73 | cheapest | 1.0M | src |
| DeepSeek V4 Pro 0423 | Alibaba fp8 | $1.56 | $3.12 | $0.130 | — | $2.73 | cheapest | 1M | src |
| Qwen3 235B A22B Thinking 2507 | — | $0.450 | $3.50 | — | — | $2.74 | cheapest | 128k | src |
| Qwen3 235B A22B Thinking 2507 | Venice | $0.450 | $3.50 | — | — | $2.74 | cheapest | 128k | src |
| Kimi K2.6 | Silicon Flow | $0.770 | $3.40 | $0.140 | — | $2.74 | cheapest | 262k | src |
| Kimi K2.6 | Novita | $0.800 | $3.40 | $0.160 | — | $2.75 | cheapest | 262k | src |
| Qwen3.5 397B A17B | DigitalOcean | $0.550 | $3.50 | $0.110 | — | $2.76 | cheapest | 131k | src |
| Qwen3.5 397B A17B | Phala | $0.550 | $3.50 | $0.225 | — | $2.76 | cheapest | 262k | src |
| Qwen3.5 397B A17B | Atlas Cloud | $0.550 | $3.50 | $0.550 | — | $2.76 | cheapest | 262k | src |
| DeepSeek V4 Pro 0423 | Novita | $1.60 | $3.20 | $0.135 | — | $2.80 | cheapest | 1.0M | src |
| Kimi K2.6 | Crusoe | $0.700 | $3.50 | $0.350 | — | $2.80 | cheapest | 262k | src |
| Kimi K2.7 Code | Core Weave | $0.710 | $3.50 | $0.150 | — | $2.80 | cheapest | 262k | src |
| DeepSeek V4 Pro 0813 | Alibaba | $1.12 | $3.37 | $0.112 | — | $2.81 | cheapest | 1M | src |
| Kimi K2.6 | DeepInfra | $0.750 | $3.50 | $0.150 | — | $2.81 | cheapest | 262k | src |
| Kimi K2.6 | Venice | $0.750 | $3.50 | $0.160 | — | $2.81 | cheapest | 256k | src |
| Kimi K2.6 | Parasail | $0.750 | $3.50 | $0.160 | — | $2.81 | cheapest | 262k | src |
| Kimi K2.7 Code | Venice | $0.750 | $3.50 | $0.160 | — | $2.81 | cheapest | 256k | src |
| Qwen3.5 397B A17B | — | $0.500 | $3.60 | $0.300 | — | $2.83 | cheapest | 262k | src |
| Qwen3.5 397B A17B | Parasail | $0.500 | $3.60 | $0.300 | — | $2.83 | cheapest | 262k | src |
| Qwen3.5 397B A17B | StreamLake | $0.600 | $3.60 | $0.120 | — | $2.85 | cheapest | 256k | src |
| Qwen3.5 397B A17B | GMI Cloud | $0.600 | $3.60 | — | — | $2.85 | cheapest | 262k | src |
| Qwen3.5 397B A17B | Novita | $0.600 | $3.60 | — | — | $2.85 | cheapest | 262k | src |
| DeepSeek V4 Pro 0423 | Venice | $1.65 | $3.30 | $0.330 | — | $2.89 | cheapest | 1M | src |
| Kimi K2.6 | GMI Cloud | $0.855 | $3.60 | $0.144 | — | $2.91 | cheapest | 262k | src |
| GLM 5.2 | Alibaba fp8 | $1.12 | $3.52 | $0.224 | — | $2.92 | cheapest | 1M | src |
| DeepSeek V4 Pro 0423 | Atlas Cloud | $1.68 | $3.38 | $0.130 | — | $2.96 | cheapest | 1.0M | src |
| Gemini 3.6 Flash | — | $0.750 | $3.75 | $0.075 | $0.042 | $3.00 | cheapest | 1.0M | src |
| Gemini 3.6 Flash | Google AI Studio google-ai-studio | $0.750 | $3.75 | $0.075 | $0.042 | $3.00 | cheapest | 1.0M | src |
| Gemini 3.6 Flash | Google google-vertex/global | $0.750 | $3.75 | $0.075 | $0.042 | $3.00 | cheapest | 1.0M | src |
| Gemini 3.7 Flash | — | $0.750 | $3.75 | $0.075 | $0.042 | $3.00 | cheapest | 1.0M | src |
| Gemini 3.7 Flash | Google AI Studio google-ai-studio | $0.750 | $3.75 | $0.075 | $0.042 | $3.00 | cheapest | 1.0M | src |
| Gemini 3.7 Flash | Google google-vertex/global | $0.750 | $3.75 | $0.075 | $0.042 | $3.00 | cheapest | 1.0M | src |
| Gemini 3.8 Flash | Google AI Studio google-ai-studio | $0.750 | $3.75 | $0.075 | $0.042 | $3.00 | cheapest | 1.0M | src |
| Gemini 3.8 Flash | Google google-vertex/global | $0.750 | $3.75 | $0.075 | $0.042 | $3.00 | cheapest | 1.0M | src |
| Gemini Flash Latest | — | $0.750 | $3.75 | $0.075 | $0.042 | $3.00 | cheapest | 1.0M | src |
| Mistral Medium 3.5 | Mistral | $0.750 | $3.75 | — | — | $3.00 | cheapest | 262k | src |
| Mistral Medium 3.5 (batch) | — | $0.750 | $3.75 | — | — | $3.00 | cheapest | 262k | src |
| Kimi K2.7 Code | Silicon Flow | $0.859 | $3.80 | $0.180 | — | $3.06 | cheapest | 262k | src |
| DeepSeek V4 Pro 0813 | Deka LLM | $0.880 | $3.80 | $0.150 | — | $3.07 | cheapest | 1.0M | src |
| GLM 5.1 | Silicon Flow | $1.19 | $3.74 | $0.600 | — | $3.10 | cheapest | 205k | src |
| GLM 5.3 | Alibaba | $1.19 | $3.74 | $0.238 | — | $3.10 | cheapest | 1M | src |
| Kimi K2.7 Code | Novita | $0.912 | $3.84 | $0.182 | — | $3.11 | cheapest | 262k | src |
| GLM 5.3 | Reka | $0.140 | $4.20 | $0.105 | — | $3.19 | cheapest | 262k | src |
| Kimi K2.6 | Atlas Cloud | $0.950 | $4.00 | $0.160 | — | $3.24 | cheapest | 262k | src |
| Kimi K2.6 | Cloudflare | $0.950 | $4.00 | $0.160 | — | $3.24 | cheapest | 262k | src |
| Kimi K2.6 | Moonshot AI | $0.950 | $4.00 | $0.160 | — | $3.24 | cheapest | 262k | src |
| Kimi K2.7 Code | Phala | $0.950 | $4.00 | $0.190 | — | $3.24 | cheapest | 262k | src |
| Kimi K2.7 Code | Nebius | $0.950 | $4.00 | — | — | $3.24 | cheapest | 262k | src |
| Kimi K2.7 Code | GMI Cloud | $0.950 | $4.00 | $0.190 | — | $3.24 | cheapest | 262k | src |
| Kimi K2.7 Code | Alibaba | $0.950 | $4.00 | $0.190 | — | $3.24 | cheapest | 262k | src |
| Kimi K2.7 Code | Cloudflare | $0.950 | $4.00 | $0.190 | — | $3.24 | cheapest | 262k | src |
| Kimi K2.7 Code | Moonshot AI | $0.950 | $4.00 | $0.190 | — | $3.24 | cheapest | 262k | src |
| Sakana Namazu | — | $0.950 | $4.00 | $0.150 | — | $3.24 | 0% vs Vercel AI Gateway | 262k | src |
| Sakana Namazu | Sakana AI | $0.950 | $4.00 | $0.150 | — | $3.24 | 0% vs Vercel AI Gateway | 262k | src |
| GPT-4.1 | OpenAI | $1.00 | $4.00 | $0.250 | — | $3.25 | cheapest | 1.0M | src |
| GPT-4.1 (batch) | — | $1.00 | $4.00 | $0.250 | — | $3.25 | cheapest | 1.0M | src |
| o3 | OpenAI | $1.00 | $4.00 | $0.250 | — | $3.25 | cheapest | 200k | src |
| o3 (batch) | — | $1.00 | $4.00 | $0.250 | — | $3.25 | cheapest | 200k | src |
| Inkling | DeepInfra | $0.950 | $4.05 | $0.160 | — | $3.27 | 0% vs Vercel AI Gateway | 524k | src |
| GLM 5.1 | Atlas Cloud | $1.26 | $3.96 | $0.234 | — | $3.29 | cheapest | 203k | src |
| GLM 5.3 | Friendli | $1.26 | $3.96 | $0.234 | — | $3.29 | cheapest | 1.0M | src |
| Inkling | — | $1.00 | $4.05 | $0.170 | — | $3.29 | +0% vs Vercel AI Gateway | 524k | src |
| Inkling | Together | $1.00 | $4.05 | $0.170 | — | $3.29 | +0% vs Vercel AI Gateway | 524k | src |
| DeepSeek V4 Pro 0813 | Core Weave | $1.31 | $3.96 | $0.044 | — | $3.30 | cheapest | 1.0M | src |
| DeepSeek V4 Pro 0813 | Alibaba alibaba/us-east-1 | $1.32 | $3.96 | $0.132 | — | $3.30 | cheapest | 1M | src |
| DeepSeek V4 Pro 0813 | Atlas Cloud | $1.32 | $3.96 | $0.132 | — | $3.30 | cheapest | 1.0M | src |
| DeepSeek V4 Pro 0813 | Parasail | $1.32 | $3.96 | $0.044 | — | $3.30 | cheapest | 1.0M | src |
| DeepSeek V4 Pro 0813 | Together | $1.32 | $3.96 | $0.130 | — | $3.30 | cheapest | 1.0M | src |
| DeepSeek V4 Pro 0813 | DigitalOcean | $1.32 | $3.96 | $0.044 | — | $3.30 | cheapest | 1.0M | src |
| DeepSeek V4 Pro 0813 | Silicon Flow | $1.32 | $3.96 | $0.044 | — | $3.30 | cheapest | 1.0M | src |
| DeepSeek V4 Pro 0813 | Cloudflare | $1.32 | $3.96 | $0.044 | — | $3.30 | cheapest | 1.0M | src |
| Gemini 3.6 Flash | Google google-vertex/us | $0.825 | $4.13 | $0.083 | $0.042 | $3.30 | cheapest | 1.0M | src |
| Gemini 3.7 Flash | Google google-vertex/us | $0.825 | $4.13 | $0.083 | $0.042 | $3.30 | cheapest | 1.0M | src |
| Gemini 3.8 Flash | — | $0.825 | $4.13 | $0.083 | $0.042 | $3.30 | cheapest | 1.0M | src |
| Gemini 3.8 Flash | Google google-vertex/us | $0.825 | $4.13 | $0.083 | $0.042 | $3.30 | cheapest | 1.0M | src |
| GLM 5 Turbo | — | $1.20 | $4.00 | $0.240 | — | $3.30 | 0% vs Vercel AI Gateway | 203k | src |
| GLM 5 Turbo | Z.AI | $1.20 | $4.00 | $0.240 | — | $3.30 | 0% vs Vercel AI Gateway | 203k | src |
| GLM 5.3 | Core Weave | $1.20 | $4.00 | $0.190 | — | $3.30 | cheapest | 1.0M | src |
| GLM 5V Turbo | — | $1.20 | $4.00 | $0.240 | — | $3.30 | 0% vs Vercel AI Gateway | 203k | src |
| GLM 5V Turbo | Z.AI | $1.20 | $4.00 | $0.240 | — | $3.30 | 0% vs Vercel AI Gateway | 203k | src |
| GLM 5.3 | Inference Net | $0.080 | $4.38 | $0.076 | — | $3.31 | cheapest | 1.0M | src |
| GLM 5.3 | Relace | $0.063 | $4.40 | $0.059 | — | $3.32 | cheapest | 1.0M | src |
| GLM Latest | — | $0.063 | $4.40 | $0.059 | — | $3.32 | cheapest | 1.0M | src |
| GLM 5.3 | Makora | $0.140 | $4.40 | $0.100 | — | $3.33 | cheapest | 1.0M | src |
| GLM 5.3 | AkashML | $0.190 | $4.40 | $0.190 | — | $3.35 | cheapest | 1.0M | src |
| DeepSeek V4 Pro 0423 | Azure | $1.91 | $3.83 | $0.160 | — | $3.35 | cheapest | 1.0M | src |
| GLM 5.1 | Phala | $1.21 | $4.20 | $0.600 | — | $3.45 | cheapest | 203k | src |
| GLM 5.1 | Alibaba | $1.33 | $4.18 | $0.247 | — | $3.47 | cheapest | 203k | src |
| Grok Build 0.1 | xAI xai/zdr/priority | $2.00 | $4.00 | $0.400 | — | $3.50 | +100% vs Vercel AI Gateway | 256k | src |
| Grok Build 0.1 | xAI xai/priority | $2.00 | $4.00 | $0.400 | — | $3.50 | +100% vs Vercel AI Gateway | 256k | src |
| Muse Spark 1.1 | — | $1.25 | $4.25 | $0.150 | — | $3.50 | 0% vs Vercel AI Gateway | 1.0M | src |
| Muse Spark 1.1 | Meta | $1.25 | $4.25 | $0.150 | — | $3.50 | 0% vs Vercel AI Gateway | 1.0M | src |
| Muse Spark 1.2 | — | $1.25 | $4.25 | $0.150 | — | $3.50 | 0% vs Vercel AI Gateway | 1.0M | src |
| Muse Spark 1.2 | Meta | $1.25 | $4.25 | $0.150 | — | $3.50 | 0% vs Vercel AI Gateway | 1.0M | src |
| Muse Spark 1.3 | — | $1.25 | $4.25 | $0.150 | — | $3.50 | 0% vs Vercel AI Gateway | 1.0M | src |
| Muse Spark 1.3 | Meta | $1.25 | $4.25 | $0.150 | — | $3.50 | 0% vs Vercel AI Gateway | 1.0M | src |
| Muse Spark Open | — | $1.25 | $4.25 | $0.150 | — | $3.50 | 0% vs Vercel AI Gateway | 1.0M | src |
| Muse Spark Open | Modal | $1.25 | $4.25 | $0.150 | — | $3.50 | 0% vs Vercel AI Gateway | 1M | src |
| Muse Spark Open | Together | $1.25 | $4.25 | $0.150 | — | $3.50 | 0% vs Vercel AI Gateway | 1.0M | src |
| Muse Spark Open | Nebius | $1.25 | $4.25 | — | — | $3.50 | 0% vs Vercel AI Gateway | 1.0M | src |
| Muse Spark Open | Fireworks | $1.25 | $4.25 | $0.150 | — | $3.50 | 0% vs Vercel AI Gateway | 1.0M | src |
| Muse Spark Open | Baseten | $1.25 | $4.25 | $0.150 | — | $3.50 | 0% vs Vercel AI Gateway | 1.0M | src |
| Gemini 2.5 Flash | Google google-vertex/global/priority | $0.540 | $4.50 | $0.054 | $0.150 | $3.51 | cheapest | 1.0M | src |
| Gemini 2.5 Flash | Google AI Studio google-ai-studio/priority | $0.540 | $4.50 | $0.054 | $0.150 | $3.51 | cheapest | 1.0M | src |
| Gemini 3.5 Flash Lite | Google google-vertex/global/priority | $0.540 | $4.50 | $0.054 | $0.150 | $3.51 | cheapest | 1.0M | src |
| Gemini 3.5 Flash Lite | Google AI Studio google-ai-studio/priority | $0.540 | $4.50 | $0.054 | $0.150 | $3.51 | cheapest | 1.0M | src |
| Beam 1.0 501B A23B | Baseten | $1.30 | $4.30 | $0.130 | — | $3.55 | cheapest | 1.0M | src |
| Gemini 3.5 Flash | $0.750 | $4.50 | $0.075 | $0.042 | $3.56 | cheapest | 1.0M | src | |
| Gemini 3.5 Flash | Google AI Studio | $0.750 | $4.50 | $0.075 | $0.042 | $3.56 | cheapest | 1.0M | src |
| Gemini 3.5 Flash | $0.750 | $4.50 | $0.075 | — | $3.56 | cheapest | 1.0M | src | |
| Gemini 3.5 Flash (batch) | — | $0.750 | $4.50 | $0.075 | — | $3.56 | cheapest | 1.0M | src |
| GPT Mini Latest | — | $0.750 | $4.50 | $0.075 | — | $3.56 | cheapest | 400k | src |
| GPT-5.4 Mini | — | $0.750 | $4.50 | $0.075 | — | $3.56 | cheapest | 400k | src |
| GPT-5.4 Mini | Azure | $0.750 | $4.50 | $0.075 | — | $3.56 | cheapest | 400k | src |
| GPT-5.4 Mini | OpenAI openai | $0.750 | $4.50 | $0.075 | — | $3.56 | cheapest | 400k | src |
| Qwen3.5 397B A17B | Venice | $0.750 | $4.50 | — | — | $3.56 | cheapest | 128k | src |
| o3 Mini | — | $1.10 | $4.40 | $0.550 | — | $3.58 | cheapest | 200k | src |
| o3 Mini | OpenAI | $1.10 | $4.40 | $0.550 | — | $3.58 | cheapest | 200k | src |
| o3 Mini High | — | $1.10 | $4.40 | $0.550 | — | $3.58 | cheapest | 200k | src |
| o3 Mini High | OpenAI | $1.10 | $4.40 | $0.550 | — | $3.58 | cheapest | 200k | src |
| o4 Mini | — | $1.10 | $4.40 | $0.275 | — | $3.58 | cheapest | 200k | src |
| o4 Mini | OpenAI | $1.10 | $4.40 | $0.275 | — | $3.58 | cheapest | 200k | src |
| o4 Mini High | — | $1.10 | $4.40 | $0.275 | — | $3.58 | cheapest | 200k | src |
| o4 Mini High | OpenAI | $1.10 | $4.40 | $0.275 | — | $3.58 | cheapest | 200k | src |
| GLM 5.3 | — | $0.079 | $4.80 | $0.078 | — | $3.62 | cheapest | 1.0M | src |
| GLM 5.3 | Wafer | $0.079 | $4.80 | $0.078 | — | $3.62 | cheapest | 1.0M | src |
| GLM 5.3 | Wafer fp4 | $0.170 | $4.80 | $0.169 | — | $3.64 | cheapest | 1.0M | src |
| GLM 5.1 | Novita | $1.38 | $4.40 | $0.260 | — | $3.65 | cheapest | 205k | src |
| GLM 5.1 | Nebius | $1.40 | $4.40 | — | — | $3.65 | cheapest | 203k | src |
| GLM 5.1 | GMI Cloud | $1.40 | $4.40 | $0.260 | — | $3.65 | cheapest | 203k | src |
| GLM 5.1 | Friendli | $1.40 | $4.40 | $0.260 | — | $3.65 | cheapest | 203k | src |
| GLM 5.1 | Z.AI | $1.40 | $4.40 | $0.260 | — | $3.65 | cheapest | 203k | src |
| GLM 5.2 | Nebius | $1.40 | $4.40 | — | — | $3.65 | cheapest | 1.0M | src |
| GLM 5.2 | Mistral | $1.40 | $4.40 | $0.140 | — | $3.65 | cheapest | 1.0M | src |
| GLM 5.2 | Baseten | $1.40 | $4.40 | $0.140 | — | $3.65 | cheapest | 1.0M | src |
| GLM 5.2 | Together | $1.40 | $4.40 | $0.260 | — | $3.65 | cheapest | 1.0M | src |
| GLM 5.2 | Venice | $1.40 | $4.40 | $0.260 | — | $3.65 | cheapest | 1M | src |
| GLM 5.2 | GMI Cloud | $1.40 | $4.40 | $0.260 | — | $3.65 | cheapest | 1.0M | src |
| GLM 5.2 | Parasail | $1.40 | $4.40 | $0.260 | — | $3.65 | cheapest | 262k | src |
| GLM 5.2 | Friendli | $1.40 | $4.40 | $0.260 | — | $3.65 | cheapest | 1.0M | src |
| GLM 5.2 | Z.AI | $1.40 | $4.40 | $0.260 | — | $3.65 | cheapest | 1.0M | src |
| GLM 5.3 | Mistral | $1.40 | $4.40 | $0.140 | — | $3.65 | cheapest | 1.0M | src |
| GLM 5.3 | Baseten | $1.40 | $4.40 | $0.140 | — | $3.65 | cheapest | 1.0M | src |
| GLM 5.3 | Nebius | $1.40 | $4.40 | — | — | $3.65 | cheapest | 1.0M | src |
| GLM 5.3 | Crusoe | $1.40 | $4.40 | $0.130 | — | $3.65 | cheapest | 1.0M | src |
| GLM 5.3 | Prime Intellect | $1.40 | $4.40 | $0.260 | — | $3.65 | cheapest | 1.0M | src |
| GLM 5.3 | Venice | $1.40 | $4.40 | $0.260 | — | $3.65 | cheapest | 1M | src |
| GLM 5.3 | Together | $1.40 | $4.40 | $0.260 | — | $3.65 | cheapest | 1.0M | src |
| GLM 5.3 | Parasail | $1.40 | $4.40 | $0.260 | — | $3.65 | cheapest | 1.0M | src |
| GLM 5.3 | Modal | $1.40 | $4.40 | $0.260 | — | $3.65 | cheapest | 1.0M | src |
| GLM 5.3 | Fireworks | $1.40 | $4.40 | $0.260 | — | $3.65 | cheapest | 1.0M | src |
| GLM 5.3 | Cloudflare | $1.40 | $4.40 | $0.260 | — | $3.65 | cheapest | 1.0M | src |
| GLM 5.3 | Atlas Cloud | $1.40 | $4.40 | $0.260 | — | $3.65 | cheapest | 1.0M | src |
| GLM 5.3 | Z.AI | $1.40 | $4.40 | $0.260 | — | $3.65 | cheapest | 1.0M | src |
| GLM 5.1 | Venice | $1.40 | $4.40 | $0.260 | — | $3.65 | cheapest | 200k | src |
| Qwen3.7 Max | — | $1.48 | $4.42 | $0.295 | $1.84 | $3.69 | +18% vs Novita | 1M | src |
| Qwen3.7 Max | Alibaba | $1.48 | $4.42 | $0.295 | $1.84 | $3.69 | +18% vs Novita | 1M | src |
| Kimi K2.6 | Phala | $1.09 | $4.60 | $0.370 | — | $3.72 | cheapest | 262k | src |
| GPT-3.5 Turbo 16k | — | $3.00 | $4.00 | — | — | $3.75 | cheapest | 16k | src |
| GPT-3.5 Turbo 16k | Azure | $3.00 | $4.00 | — | — | $3.75 | cheapest | 16k | src |
| GPT-3.5 Turbo 16k | OpenAI | $3.00 | $4.00 | — | — | $3.75 | cheapest | 16k | src |
| Gemini 2.5 Pro | Google AI Studio | $0.625 | $5.00 | $0.063 | $0.188 | $3.91 | cheapest | 1.0M | src |
| Gemini 2.5 Pro | $0.625 | $5.00 | $0.125 | — | $3.91 | cheapest | 1.0M | src | |
| Gemini 2.5 Pro (batch) | — | $0.625 | $5.00 | $0.125 | — | $3.91 | cheapest | 1.0M | src |
| GPT-5 | OpenAI | $0.625 | $5.00 | $0.063 | — | $3.91 | cheapest | 400k | src |
| GPT-5 (batch) | — | $0.625 | $5.00 | $0.063 | — | $3.91 | cheapest | 400k | src |
| GPT-5.1 | OpenAI | $0.625 | $5.00 | $0.063 | — | $3.91 | cheapest | 400k | src |
| GPT-5.1 | OpenAI | $0.625 | $5.00 | $0.063 | — | $3.91 | cheapest | 400k | src |
| GPT-5.1 (batch) | — | $0.625 | $5.00 | $0.063 | — | $3.91 | cheapest | 400k | src |
| GPT-5.4 Mini | Azure azure/us | $0.825 | $4.95 | $0.083 | — | $3.92 | cheapest | 400k | src |
| Claude Haiku 4.5 | — | $1.00 | $5.00 | $0.100 | $1.25 | $4.00 | cheapest | 200k | src |
| Claude Haiku 4.5 | Azure | $1.00 | $5.00 | $0.100 | $1.25 | $4.00 | cheapest | 200k | src |
| Claude Haiku 4.5 | Bedrock | $1.00 | $5.00 | $0.100 | $1.25 | $4.00 | cheapest | 200k | src |
| Claude Haiku 4.5 | $1.00 | $5.00 | $0.100 | $1.25 | $4.00 | cheapest | 200k | src | |
| Claude Haiku 4.5 | Anthropic | $1.00 | $5.00 | $0.100 | $1.25 | $4.00 | cheapest | 200k | src |
| Claude Sonnet 5 | Anthropic | $1.00 | $5.00 | $0.100 | $1.25 | $4.00 | cheapest | 1M | src |
| Claude Sonnet 5 (batch) | — | $1.00 | $5.00 | $0.100 | $1.25 | $4.00 | cheapest | 1M | src |
| Claude Sonnet 5.5 | Anthropic | $1.00 | $5.00 | $0.050 | $1.25 | $4.00 | cheapest | 1M | src |
| Claude Sonnet 5.5 (batch) | — | $1.00 | $5.00 | $0.050 | $1.25 | $4.00 | cheapest | 1M | src |
| Gemini 4 Argon | Google AI Studio | $1.00 | $5.00 | $0.050 | $0.094 | $4.00 | cheapest | 1.0M | src |
| Gemini 4 Argon | $1.00 | $5.00 | $0.050 | $0.188 | $4.00 | cheapest | 1.0M | src | |
| Gemini 4 Argon (batch) | — | $1.00 | $5.00 | $0.050 | $0.188 | $4.00 | cheapest | 1.0M | src |
| GPT-6 Sol | OpenAI | $1.00 | $5.00 | $0.100 | $1.25 | $4.00 | cheapest | 1.1M | src |
| GPT-6 Sol | OpenAI | $1.00 | $5.00 | $0.100 | $1.25 | $4.00 | cheapest | 1.1M | src |
| GPT-6 Sol (batch) | — | $1.00 | $5.00 | $0.100 | $1.25 | $4.00 | cheapest | 1.1M | src |
| GPT-6 Sol Pro | OpenAI | $1.00 | $5.00 | $0.100 | $1.25 | $4.00 | cheapest | 1.1M | src |
| GPT-6 Sol Pro | OpenAI | $1.00 | $5.00 | $0.100 | $1.25 | $4.00 | cheapest | 1.1M | src |
| GPT-6 Sol Pro (batch) | — | $1.00 | $5.00 | $0.100 | $1.25 | $4.00 | cheapest | 1.1M | src |
| GPT-6.1 Sol | OpenAI | $1.00 | $5.00 | $0.050 | $1.25 | $4.00 | cheapest | 1.1M | src |
| GPT-6.1 Sol | OpenAI | $1.00 | $5.00 | $0.050 | $1.25 | $4.00 | cheapest | 1.1M | src |
| GPT-6.1 Sol (batch) | — | $1.00 | $5.00 | $0.050 | $1.25 | $4.00 | cheapest | 1.1M | src |
| GPT-6.1 Sol Pro | OpenAI | $1.00 | $5.00 | $0.050 | $1.25 | $4.00 | cheapest | 1.1M | src |
| GPT-6.1 Sol Pro | OpenAI | $1.00 | $5.00 | $0.050 | $1.25 | $4.00 | cheapest | 1.1M | src |
| GPT-6.1 Sol Pro (batch) | — | $1.00 | $5.00 | $0.050 | $1.25 | $4.00 | cheapest | 1.1M | src |
| GLM 5.2 | Mistral mistral/eu | $1.54 | $4.84 | $0.154 | — | $4.01 | cheapest | 1.0M | src |
| GLM 5.3 | Mistral nvfp4 | $1.54 | $4.84 | $0.154 | — | $4.01 | cheapest | 1.0M | src |
| GPT-4o | OpenAI | $1.25 | $5.00 | $0.625 | — | $4.06 | cheapest | 128k | src |
| GPT-4o (batch) | — | $1.25 | $5.00 | $0.625 | — | $4.06 | cheapest | 128k | src |
| DeepSeek V3.2 | Mara | $3.00 | $4.50 | — | — | $4.13 | cheapest | 33k | src |
| DeepSeek V3.2 | Samba Nova | $3.00 | $4.50 | — | — | $4.13 | cheapest | 33k | src |
| DeepSeek V4 Pro 0813 | Venice | $1.65 | $4.95 | $0.165 | — | $4.13 | cheapest | 1M | src |
| Gemini 3 Flash Preview | Google google-vertex/global/priority | $0.900 | $5.40 | $0.090 | $0.150 | $4.28 | cheapest | 1.0M | src |
| Gemini 3 Flash Preview | Google AI Studio google-ai-studio/priority | $0.900 | $5.40 | $0.090 | $0.150 | $4.28 | cheapest | 1.0M | src |
| Grok 4.20 | xAI xai/zdr/priority | $2.50 | $5.00 | $0.400 | — | $4.38 | cheapest | 2M | src |
| Grok 4.20 | xAI xai/priority | $2.50 | $5.00 | $0.400 | — | $4.38 | cheapest | 2M | src |
| Grok 4.20 Multi-Agent | xAI xai/zdr/priority | $2.50 | $5.00 | $0.400 | — | $4.38 | +100% vs Vercel AI Gateway | 2M | src |
| Grok 4.20 Multi-Agent | xAI xai/priority | $2.50 | $5.00 | $0.400 | — | $4.38 | +100% vs Vercel AI Gateway | 2M | src |
| Grok 4.3 | xAI xai/zdr/priority | $2.50 | $5.00 | $0.400 | — | $4.38 | cheapest | 1M | src |
| Grok 4.3 | xAI xai/priority | $2.50 | $5.00 | $0.400 | — | $4.38 | cheapest | 1M | src |
| Magnum v4 72B | — | $2.50 | $5.00 | — | — | $4.38 | cheapest | 33k | src |
| Magnum v4 72B | Mancer 2 | $2.50 | $5.00 | — | — | $4.38 | cheapest | 33k | src |
| Claude Haiku 4.5 | Bedrock amazon-bedrock/us | $1.10 | $5.50 | $0.110 | $1.38 | $4.40 | cheapest | 200k | src |
| Claude Haiku 4.5 | Google google-vertex/us-east5 | $1.10 | $5.50 | $0.110 | $1.38 | $4.40 | cheapest | 200k | src |
| Claude Haiku 4.5 | Bedrock amazon-bedrock/eu-west-1 | $1.10 | $5.50 | $0.110 | $1.38 | $4.40 | cheapest | 200k | src |
| Claude Haiku 4.5 | Google google-vertex/europe | $1.10 | $5.50 | $0.110 | $1.38 | $4.40 | cheapest | 200k | src |
| GLM 5.2 | Relace | $0.075 | $6.00 | $0.075 | — | $4.52 | cheapest | 1.0M | src |
| GLM 5.2 | Morph | $0.079 | $6.00 | $0.079 | — | $4.52 | cheapest | 1.0M | src |
| GLM 5.3 | Morph | $0.080 | $6.00 | $0.050 | — | $4.52 | cheapest | 1.0M | src |
| Palmyra X5 | — | $0.600 | $6.00 | — | — | $4.65 | cheapest | 1.0M | src |
| Palmyra X5 | Bedrock | $0.600 | $6.00 | — | — | $4.65 | cheapest | 1.0M | src |
| Gemini 3.1 Pro Preview | $1.00 | $6.00 | $0.100 | $0.188 | $4.75 | cheapest | 1.0M | src | |
| Gemini 3.1 Pro Preview | Google AI Studio | $1.00 | $6.00 | $0.100 | $0.188 | $4.75 | cheapest | 1.0M | src |
| Gemini 3.1 Pro Preview | $1.00 | $6.00 | — | — | $4.75 | cheapest | 1.0M | src | |
| Gemini 3.1 Pro Preview (batch) | — | $1.00 | $6.00 | — | — | $4.75 | cheapest | 1.0M | src |
| GPT-5.6 Terra | OpenAI | $1.00 | $6.00 | $0.100 | $1.25 | $4.75 | cheapest | 1.1M | src |
| GPT-5.6 Terra | OpenAI | $1.00 | $6.00 | $0.100 | — | $4.75 | cheapest | 1.1M | src |
| GPT-5.6 Terra (batch) | — | $1.00 | $6.00 | $0.100 | — | $4.75 | cheapest | 1.1M | src |
| GPT-5.6 Terra Pro | OpenAI | $1.00 | $6.00 | $0.100 | $1.25 | $4.75 | cheapest | 1.1M | src |
| GPT-5.6 Terra Pro | OpenAI | $1.00 | $6.00 | $0.100 | — | $4.75 | cheapest | 1.1M | src |
| GPT-5.6 Terra Pro (batch) | — | $1.00 | $6.00 | $0.100 | — | $4.75 | cheapest | 1.1M | src |
| Nano Banana Pro (Gemini 3 Pro Image Preview) | Google AI Studio | $1.00 | $6.00 | $0.100 | $0.188 | $4.75 | cheapest | 66k | src |
| Fugu Max | — | $2.00 | $6.00 | $0.250 | — | $5.00 | 0% vs Vercel AI Gateway | 1M | src |
| Fugu Max | Sakana AI | $2.00 | $6.00 | $0.250 | — | $5.00 | 0% vs Vercel AI Gateway | 1M | src |
| Grok 4.5 | — | $2.00 | $6.00 | $0.300 | — | $5.00 | 0% vs Vercel AI Gateway | 500k | src |
| Grok 4.5 | xAI | $2.00 | $6.00 | $0.300 | — | $5.00 | 0% vs Vercel AI Gateway | 500k | src |
| Grok 4.6 | — | $2.00 | $6.00 | $0.500 | — | $5.00 | 0% vs Vercel AI Gateway | 500k | src |
| Grok 4.6 | xAI | $2.00 | $6.00 | $0.500 | — | $5.00 | 0% vs Vercel AI Gateway | 500k | src |
| Grok 4.7 | — | $2.00 | $6.00 | $0.500 | — | $5.00 | 0% vs Vercel AI Gateway | 500k | src |
| Grok 4.7 | xAI | $2.00 | $6.00 | $0.500 | — | $5.00 | 0% vs Vercel AI Gateway | 500k | src |
| Grok Latest | — | $2.00 | $6.00 | $0.500 | — | $5.00 | cheapest | 500k | src |
| Mistral Large | — | $2.00 | $6.00 | $0.200 | — | $5.00 | cheapest | 128k | src |
| Mistral Large | Mistral | $2.00 | $6.00 | $0.200 | — | $5.00 | cheapest | 128k | src |
| Mistral Large 2407 | — | $2.00 | $6.00 | $0.200 | — | $5.00 | cheapest | 131k | src |
| Mistral Large 2407 | Mistral | $2.00 | $6.00 | $0.200 | — | $5.00 | cheapest | 131k | src |
| Mixtral 8x22B Instruct | — | $2.00 | $6.00 | $0.200 | — | $5.00 | cheapest | 66k | src |
| Mixtral 8x22B Instruct | Mistral | $2.00 | $6.00 | $0.200 | — | $5.00 | cheapest | 66k | src |
| Qwen3.7 Max | Alibaba alibaba/us-east-1 | $2.00 | $6.00 | $0.400 | — | $5.00 | +60% vs Novita | 1M | src |
| Qwen3.8 2.4T A95B | — | $2.00 | $6.00 | $0.250 | — | $5.00 | 0% vs Novita | 1.0M | src |
| Qwen3.8 2.4T A95B | Novita | $2.00 | $6.00 | $0.250 | — | $5.00 | 0% vs Novita | 1M | src |
| Qwen3.8 2.4T A95B | Alibaba | $2.00 | $6.00 | $0.250 | $2.50 | $5.00 | 0% vs Novita | 1M | src |
| Qwen3.8 2.4T A95B | Silicon Flow | $2.00 | $6.00 | $0.250 | — | $5.00 | 0% vs Novita | 1.0M | src |
| Qwen3.8 2.4T A95B | Venice | $2.00 | $6.00 | $0.250 | — | $5.00 | 0% vs Novita | 262k | src |
| Qwen3.8 2.4T A95B | Together | $2.00 | $6.00 | $0.250 | — | $5.00 | 0% vs Novita | 1.0M | src |
| Qwen3.8 Max (0902) | — | $2.00 | $6.00 | $0.250 | — | $5.00 | cheapest | 1M | src |
| Qwen3.8 Max (0902) | Alibaba | $2.00 | $6.00 | $0.250 | — | $5.00 | cheapest | 1M | src |
| Aion 3.5 | — | $3.00 | $6.00 | $0.750 | — | $5.25 | cheapest | 262k | src |
| Aion 3.5 | Aion Labs | $3.00 | $6.00 | $0.750 | — | $5.25 | cheapest | 262k | src |
| Aion-3.0 | — | $3.00 | $6.00 | $0.750 | — | $5.25 | cheapest | 131k | src |
| Aion-3.0 | Aion Labs | $3.00 | $6.00 | $0.750 | — | $5.25 | cheapest | 131k | src |
| GLM 5.2 | Wafer | $0.034 | $7.00 | $0.033 | — | $5.26 | cheapest | 1.0M | src |
| Gemini 3.6 Flash | Google google-vertex/global/priority | $1.35 | $6.75 | $0.135 | $0.075 | $5.40 | cheapest | 1.0M | src |
| Gemini 3.6 Flash | Google AI Studio google-ai-studio/priority | $1.35 | $6.75 | $0.135 | $0.075 | $5.40 | cheapest | 1.0M | src |
| Gemini 3.7 Flash | Google google-vertex/global/priority | $1.35 | $6.75 | $0.135 | $0.075 | $5.40 | cheapest | 1.0M | src |
| Gemini 3.7 Flash | Google AI Studio google-ai-studio/priority | $1.35 | $6.75 | $0.135 | $0.075 | $5.40 | cheapest | 1.0M | src |
| Gemini 3.8 Flash | Google AI Studio google-ai-studio/priority | $1.35 | $6.75 | $0.135 | $0.075 | $5.40 | cheapest | 1.0M | src |
| Gemini 3.8 Flash | Google google-vertex/global/priority | $1.35 | $6.75 | $0.135 | $0.075 | $5.40 | cheapest | 1.0M | src |
| GPT-5.2 | OpenAI | $0.875 | $7.00 | $0.087 | — | $5.47 | cheapest | 400k | src |
| GPT-5.2 | OpenAI | $0.875 | $7.00 | $0.087 | — | $5.47 | cheapest | 400k | src |
| GPT-5.2 (batch) | — | $0.875 | $7.00 | $0.087 | — | $5.47 | cheapest | 400k | src |
| GLM 5.2 | Baseten fp8 | $2.10 | $6.60 | $0.210 | — | $5.47 | cheapest | 1.0M | src |
| GLM 5.3 | Model Run | $2.10 | $6.60 | $0.400 | — | $5.47 | cheapest | 1.0M | src |
| GLM 5.3 | Fireworks fireworks/fast | $2.10 | $6.60 | $0.390 | — | $5.47 | cheapest | 1.0M | src |
| GLM 5.3 | Baseten fp8 | $2.10 | $6.60 | $0.210 | — | $5.47 | cheapest | 1.0M | src |
| Grok 4.6 | xAI xai/zdr/us | $2.20 | $6.60 | $0.550 | — | $5.50 | +10% vs Vercel AI Gateway | 500k | src |
| Grok 4.6 | Bedrock | $2.20 | $6.60 | $0.550 | free | $5.50 | +10% vs Vercel AI Gateway | 500k | src |
| Grok 4.7 | xAI xai/zdr/us | $2.20 | $6.60 | $0.550 | — | $5.50 | +10% vs Vercel AI Gateway | 500k | src |
| Mistral Large | Mistral mistral/eu | $2.20 | $6.60 | $0.220 | — | $5.50 | cheapest | 128k | src |
| Mistral Large 2407 | Mistral mistral/eu | $2.20 | $6.60 | $0.220 | — | $5.50 | cheapest | 131k | src |
| Mixtral 8x22B Instruct | Mistral mistral/eu | $2.20 | $6.60 | $0.220 | — | $5.50 | cheapest | 66k | src |
| GPT-5.4 | OpenAI | $1.25 | $7.50 | $0.125 | — | $5.94 | cheapest | 1.1M | src |
| GPT-5.4 | OpenAI | $1.25 | $7.50 | $0.125 | — | $5.94 | cheapest | 1.1M | src |
| GPT-5.4 (batch) | — | $1.25 | $7.50 | $0.125 | — | $5.94 | cheapest | 1.1M | src |
| Claude Sonnet 4.5 | Anthropic | $1.50 | $7.50 | $0.150 | $1.88 | $6.00 | cheapest | 1M | src |
| Claude Sonnet 4.5 (batch) | — | $1.50 | $7.50 | $0.150 | $1.88 | $6.00 | cheapest | 1M | src |
| Claude Sonnet 4.6 | Anthropic | $1.50 | $7.50 | $0.150 | $1.88 | $6.00 | cheapest | 1M | src |
| Claude Sonnet 4.6 (batch) | — | $1.50 | $7.50 | $0.150 | $1.88 | $6.00 | cheapest | 1M | src |
| Mistral Medium 3.5 | — | $1.50 | $7.50 | — | — | $6.00 | cheapest | 262k | src |
| Mistral Medium 3.5 | Mistral | $1.50 | $7.50 | — | — | $6.00 | cheapest | 262k | src |
| Nano Banana 2.1 | — | $1.50 | $7.50 | — | — | $6.00 | cheapest | 66k | src |
| Nano Banana 2.1 | Google AI Studio | $1.50 | $7.50 | — | — | $6.00 | cheapest | 66k | src |
| DeepSeek Pro Latest | — | $0.120 | $8.00 | $0.120 | — | $6.03 | cheapest | 1.0M | src |
| DeepSeek V4 Pro 0813 | Relace | $0.120 | $8.00 | $0.120 | — | $6.03 | cheapest | 1.0M | src |
| GLM 5.2 | Cloudflare | $0.190 | $8.00 | $0.190 | — | $6.05 | cheapest | 262k | src |
| Kimi K3 | Sail Research | $0.504 | $8.10 | $0.180 | — | $6.20 | cheapest | 1.0M | src |
| Pareto 26.9 | — | $2.50 | $7.50 | $0.250 | — | $6.25 | cheapest | 262k | src |
| Pareto 26.9 | Unbiased | $2.50 | $7.50 | $0.250 | — | $6.25 | cheapest | 262k | src |
| Pareto Latest | — | $2.50 | $7.50 | $0.250 | — | $6.25 | cheapest | 262k | src |
| GLM 5.2 | Baidu fp4 | $2.25 | $7.88 | $0.560 | — | $6.47 | cheapest | 1.0M | src |
| Kimi K2.7 Code | Moonshot AI int4 | $1.90 | $8.00 | $0.380 | — | $6.47 | cheapest | 262k | src |
| GPT-4.1 | — | $2.00 | $8.00 | $0.500 | — | $6.50 | cheapest | 1.0M | src |
| GPT-4.1 | Azure | $2.00 | $8.00 | $0.500 | — | $6.50 | cheapest | 1.0M | src |
| GPT-4.1 | OpenAI | $2.00 | $8.00 | $0.500 | — | $6.50 | cheapest | 1.0M | src |
| o3 | — | $2.00 | $8.00 | $0.500 | — | $6.50 | cheapest | 200k | src |
| o3 | OpenAI | $2.00 | $8.00 | $0.500 | — | $6.50 | cheapest | 200k | src |
| Sonar Deep Research | — | $2.00 | $8.00 | — | — | $6.50 | 0% vs Perplexity | 128k | src |
| Sonar Deep Research | Perplexity | $2.00 | $8.00 | — | — | $6.50 | 0% vs Perplexity | 128k | src |
| Sonar Reasoning Pro | — | $2.00 | $8.00 | — | — | $6.50 | 0% vs Perplexity | 128k | src |
| Sonar Reasoning Pro | Perplexity | $2.00 | $8.00 | — | — | $6.50 | 0% vs Perplexity | 128k | src |
| Kimi K3 | Decart | $1.65 | $8.25 | $0.165 | — | $6.60 | cheapest | 1.0M | src |
| Mistral Medium 3.5 | Mistral mistral/eu | $1.65 | $8.25 | — | — | $6.60 | cheapest | 262k | src |
| Gemini 3.5 Flash | — | $1.50 | $9.00 | $0.150 | $0.083 | $7.13 | cheapest | 1.0M | src |
| Gemini 3.5 Flash | Google google-vertex/global | $1.50 | $9.00 | $0.150 | $0.083 | $7.13 | cheapest | 1.0M | src |
| Gemini 3.5 Flash | Google AI Studio google-ai-studio | $1.50 | $9.00 | $0.150 | $0.083 | $7.13 | cheapest | 1.0M | src |
| GPT-5.4 Mini | OpenAI openai/fast | $1.50 | $9.00 | $0.150 | — | $7.13 | cheapest | 400k | src |
| GPT-4.1 | Azure azure/swedencentral | $2.20 | $8.80 | $0.550 | — | $7.15 | cheapest | 1.0M | src |
| GLM 5.3 | Alibaba alibaba/prime | $2.80 | $8.80 | $0.560 | — | $7.30 | cheapest | 1M | src |
| GLM 5.3 Prime | — | $2.80 | $8.80 | $0.560 | — | $7.30 | cheapest | 1M | src |
| GLM 5.3 Prime | Alibaba | $2.80 | $8.80 | $0.560 | — | $7.30 | cheapest | 1M | src |
| GLM 5.2 | Decart | $2.50 | $9.00 | $0.540 | — | $7.38 | cheapest | 1.0M | src |
| GLM 5.2 | Wafer fp4 | $0.190 | $10.00 | $0.180 | — | $7.55 | cheapest | 1.0M | src |
| Kimi K3 | Chutes | $1.85 | $9.50 | $0.185 | — | $7.59 | cheapest | 1.0M | src |
| MiMo-V2.6-Pro-UltraSpeed | — | $4.35 | $8.70 | $0.036 | — | $7.61 | cheapest | 1.0M | src |
| MiMo-V2.6-Pro-UltraSpeed | Xiaomi | $4.35 | $8.70 | $0.036 | — | $7.61 | cheapest | 1.0M | src |
| Gemini 2.5 Pro | — | $1.25 | $10.00 | $0.125 | $0.375 | $7.81 | cheapest | 1.0M | src |
| Gemini 2.5 Pro | $1.25 | $10.00 | $0.125 | $0.375 | $7.81 | cheapest | 1.0M | src | |
| Gemini 2.5 Pro | Google AI Studio google-ai-studio | $1.25 | $10.00 | $0.125 | $0.375 | $7.81 | cheapest | 1.0M | src |
| Gemini 2.5 Pro Preview 06-05 | — | $1.25 | $10.00 | $0.125 | $0.375 | $7.81 | cheapest | 1.0M | src |
| GPT-5 | — | $1.25 | $10.00 | $0.125 | — | $7.81 | cheapest | 400k | src |
| GPT-5 | Azure | $1.25 | $10.00 | $0.125 | — | $7.81 | cheapest | 400k | src |
| GPT-5 | OpenAI | $1.25 | $10.00 | $0.125 | — | $7.81 | cheapest | 400k | src |
| GPT-5.1 | — | $1.25 | $10.00 | $0.125 | — | $7.81 | cheapest | 400k | src |
| GPT-5.1 | Azure | $1.25 | $10.00 | $0.130 | — | $7.81 | cheapest | 400k | src |
| GPT-5.1 | OpenAI openai | $1.25 | $10.00 | $0.125 | — | $7.81 | cheapest | 400k | src |
| GPT-5.1-Codex | — | $1.25 | $10.00 | $0.130 | — | $7.81 | 0% vs Vercel AI Gateway | 400k | src |
| GPT-5.1-Codex | Azure | $1.25 | $10.00 | $0.130 | — | $7.81 | 0% vs Vercel AI Gateway | 400k | src |
| GPT-5.1-Codex-Max | — | $1.25 | $10.00 | $0.125 | — | $7.81 | cheapest | 400k | src |
| GPT-5.1-Codex-Max | Azure | $1.25 | $10.00 | $0.125 | — | $7.81 | cheapest | 400k | src |
| Gemini 3.5 Flash | Google google-vertex/us | $1.65 | $9.90 | $0.165 | $0.083 | $7.84 | cheapest | 1.0M | src |
| Claude Opus 5.5 | Anthropic | $2.00 | $10.00 | $0.100 | $2.50 | $8.00 | cheapest | 1M | src |
| Claude Opus 5.5 (batch) | — | $2.00 | $10.00 | $0.100 | $2.50 | $8.00 | cheapest | 1M | src |
| Claude Sonnet 5 | — | $2.00 | $10.00 | $0.200 | $2.50 | $8.00 | cheapest | 1M | src |
| Claude Sonnet 5 | Claude Platform On AWS | $2.00 | $10.00 | $0.200 | $2.50 | $8.00 | cheapest | 1M | src |
| Claude Sonnet 5 | Azure | $2.00 | $10.00 | $0.200 | $2.50 | $8.00 | cheapest | 1M | src |
| Claude Sonnet 5 | $2.00 | $10.00 | $0.200 | $2.50 | $8.00 | cheapest | 1M | src | |
| Claude Sonnet 5 | Bedrock | $2.00 | $10.00 | $0.200 | $2.50 | $8.00 | cheapest | 1M | src |
| Claude Sonnet 5 | Anthropic | $2.00 | $10.00 | $0.200 | $2.50 | $8.00 | cheapest | 1M | src |
| Claude Sonnet 5.5 | — | $2.00 | $10.00 | $0.100 | $2.50 | $8.00 | cheapest | 1M | src |
| Claude Sonnet 5.5 | $2.00 | $10.00 | $0.100 | $2.50 | $8.00 | cheapest | 1M | src | |
| Claude Sonnet 5.5 | Bedrock | $2.00 | $10.00 | $0.100 | $2.50 | $8.00 | cheapest | 1M | src |
| Claude Sonnet 5.5 | Azure | $2.00 | $10.00 | $0.100 | $2.50 | $8.00 | cheapest | 1M | src |
| Claude Sonnet 5.5 | Claude Platform On AWS | $2.00 | $10.00 | $0.100 | $2.50 | $8.00 | cheapest | 1M | src |
| Claude Sonnet 5.5 | Anthropic | $2.00 | $10.00 | $0.100 | $2.50 | $8.00 | cheapest | 1M | src |
| Claude Sonnet Latest | — | $2.00 | $10.00 | $0.100 | $2.50 | $8.00 | cheapest | 1M | src |
| Gemini 4 Argon | — | $2.00 | $10.00 | $0.100 | $0.188 | $8.00 | cheapest | 1.0M | src |
| Gemini 4 Argon | $2.00 | $10.00 | $0.100 | $0.188 | $8.00 | cheapest | 1.0M | src | |
| Gemini 4 Argon | Google AI Studio google-ai-studio | $2.00 | $10.00 | $0.100 | $0.188 | $8.00 | cheapest | 1.0M | src |
| Gemini Pro Latest | — | $2.00 | $10.00 | $0.100 | $0.188 | $8.00 | cheapest | 1.0M | src |
| GPT Sol Latest | — | $2.00 | $10.00 | $0.100 | $2.50 | $8.00 | cheapest | 1.1M | src |
| GPT-5.6 Sol | OpenAI | $2.00 | $10.00 | $0.200 | $2.50 | $8.00 | cheapest | 1.1M | src |
| GPT-5.6 Sol | OpenAI | $2.00 | $10.00 | $0.200 | $2.50 | $8.00 | cheapest | 1.1M | src |
| GPT-5.6 Sol (batch) | — | $2.00 | $10.00 | $0.200 | $2.50 | $8.00 | cheapest | 1.1M | src |
| GPT-5.6 Sol Pro | OpenAI | $2.00 | $10.00 | $0.200 | $2.50 | $8.00 | cheapest | 1.1M | src |
| GPT-5.6 Sol Pro | OpenAI | $2.00 | $10.00 | $0.200 | $2.50 | $8.00 | cheapest | 1.1M | src |
| GPT-5.6 Sol Pro (batch) | — | $2.00 | $10.00 | $0.200 | $2.50 | $8.00 | cheapest | 1.1M | src |
| GPT-6 Sol | — | $2.00 | $10.00 | $0.200 | $2.50 | $8.00 | cheapest | 1.1M | src |
| GPT-6 Sol | OpenAI openai | $2.00 | $10.00 | $0.200 | $2.50 | $8.00 | cheapest | 1.1M | src |
| GPT-6 Sol | Azure | $2.00 | $10.00 | $0.200 | $2.50 | $8.00 | cheapest | 1.1M | src |
| GPT-6 Sol Pro | — | $2.00 | $10.00 | $0.200 | $2.50 | $8.00 | cheapest | 1.1M | src |
| GPT-6 Sol Pro | OpenAI openai | $2.00 | $10.00 | $0.200 | $2.50 | $8.00 | cheapest | 1.1M | src |
| GPT-6 Sol Pro | Azure | $2.00 | $10.00 | $0.200 | $2.50 | $8.00 | cheapest | 1.1M | src |
| GPT-6.1 Sol | — | $2.00 | $10.00 | $0.100 | $2.50 | $8.00 | cheapest | 1.1M | src |
| GPT-6.1 Sol | Azure | $2.00 | $10.00 | $0.100 | $2.50 | $8.00 | cheapest | 1.1M | src |
| GPT-6.1 Sol | OpenAI openai | $2.00 | $10.00 | $0.100 | $2.50 | $8.00 | cheapest | 1.1M | src |
| GPT-6.1 Sol Pro | — | $2.00 | $10.00 | $0.100 | $2.50 | $8.00 | cheapest | 1.1M | src |
| GPT-6.1 Sol Pro | Azure | $2.00 | $10.00 | $0.100 | $2.50 | $8.00 | cheapest | 1.1M | src |
| GPT-6.1 Sol Pro | OpenAI openai | $2.00 | $10.00 | $0.100 | $2.50 | $8.00 | cheapest | 1.1M | src |
| Command A | — | $2.50 | $10.00 | — | — | $8.13 | 0% vs Vercel AI Gateway | 256k | src |
| Command A | Cohere | $2.50 | $10.00 | — | — | $8.13 | 0% vs Vercel AI Gateway | 256k | src |
| Command R+ (08-2024) | — | $2.50 | $10.00 | — | — | $8.13 | cheapest | 128k | src |
| Command R+ (08-2024) | Cohere | $2.50 | $10.00 | — | — | $8.13 | cheapest | 128k | src |
| GPT Audio | — | $2.50 | $10.00 | — | — | $8.13 | cheapest | 128k | src |
| GPT Audio | OpenAI | $2.50 | $10.00 | — | — | $8.13 | cheapest | 128k | src |
| GPT-4o | — | $2.50 | $10.00 | $1.25 | — | $8.13 | cheapest | 128k | src |
| GPT-4o | Azure | $2.50 | $10.00 | — | — | $8.13 | cheapest | 128k | src |
| GPT-4o | OpenAI | $2.50 | $10.00 | $1.25 | — | $8.13 | cheapest | 128k | src |
| GPT-4o (2024-08-06) | — | $2.50 | $10.00 | $1.25 | — | $8.13 | cheapest | 128k | src |
| GPT-4o (2024-08-06) | Azure | $2.50 | $10.00 | $1.25 | — | $8.13 | cheapest | 128k | src |
| GPT-4o (2024-08-06) | OpenAI | $2.50 | $10.00 | $1.25 | — | $8.13 | cheapest | 128k | src |
| GPT-4o (2024-11-20) | — | $2.50 | $10.00 | $1.25 | — | $8.13 | cheapest | 128k | src |
| GPT-4o (2024-11-20) | OpenAI | $2.50 | $10.00 | $1.25 | — | $8.13 | cheapest | 128k | src |
| GPT-5 | Azure azure/swedencentral | $1.38 | $11.00 | $0.138 | — | $8.59 | cheapest | 400k | src |
| GPT-5.1 | Azure azure/swedencentral | $1.38 | $11.00 | $0.143 | — | $8.59 | cheapest | 400k | src |
| Claude Sonnet 5 | Bedrock amazon-bedrock/eu-west-1 | $2.20 | $11.00 | $0.220 | $2.75 | $8.80 | cheapest | 1M | src |
| Claude Sonnet 5 | Azure azure/us | $2.20 | $11.00 | $0.220 | $2.75 | $8.80 | cheapest | 1M | src |
| Claude Sonnet 5 | Google google-vertex/us | $2.20 | $11.00 | $0.220 | $2.75 | $8.80 | cheapest | 1M | src |
| Claude Sonnet 5 | Google google-vertex/europe | $2.20 | $11.00 | $0.220 | $2.75 | $8.80 | cheapest | 1M | src |
| Claude Sonnet 5 | Bedrock amazon-bedrock/us-east-1 | $2.20 | $11.00 | $0.220 | $2.75 | $8.80 | cheapest | 1M | src |
| Claude Sonnet 5.5 | Google google-vertex/us | $2.20 | $11.00 | $0.110 | $2.75 | $8.80 | cheapest | 1M | src |
| Claude Sonnet 5.5 | Azure azure/us | $2.20 | $11.00 | $0.110 | $2.75 | $8.80 | cheapest | 1M | src |
| Claude Sonnet 5.5 | Google google-vertex/europe | $2.20 | $11.00 | $0.110 | $2.75 | $8.80 | cheapest | 1M | src |
| Gemini 4 Argon | Google google-vertex/us | $2.20 | $11.00 | $0.110 | $0.188 | $8.80 | cheapest | 1.0M | src |
| GPT-6 Sol | Azure azure/us | $2.20 | $11.00 | $0.220 | $2.75 | $8.80 | cheapest | 1.1M | src |
| GPT-6 Sol | Azure azure/eu | $2.20 | $11.00 | $0.220 | $2.75 | $8.80 | cheapest | 1.1M | src |
| GPT-6 Sol | Bedrock | $2.20 | $11.00 | $0.220 | $2.75 | $8.80 | cheapest | 1.1M | src |
| GPT-6 Sol Pro | Azure azure/us | $2.20 | $11.00 | $0.220 | $2.75 | $8.80 | cheapest | 1.1M | src |
| GPT-6 Sol Pro | Azure azure/eu | $2.20 | $11.00 | $0.220 | $2.75 | $8.80 | cheapest | 1.1M | src |
| GPT-6.1 Sol | Bedrock | $2.20 | $11.00 | $0.110 | $2.75 | $8.80 | cheapest | 1.1M | src |
| GPT-6.1 Sol | Azure azure/eu | $2.20 | $11.00 | $0.110 | $2.75 | $8.80 | cheapest | 1.1M | src |
| GPT-6.1 Sol | Azure azure/us | $2.20 | $11.00 | $0.110 | $2.75 | $8.80 | cheapest | 1.1M | src |
| GPT-6.1 Sol Pro | Azure azure/eu | $2.20 | $11.00 | $0.110 | $2.75 | $8.80 | cheapest | 1.1M | src |
| GPT-6.1 Sol Pro | Azure azure/us | $2.20 | $11.00 | $0.110 | $2.75 | $8.80 | cheapest | 1.1M | src |
| Kimi K3 | — | $0.304 | $11.94 | $0.210 | — | $9.03 | cheapest | 1.0M | src |
| Kimi K3 | Inference Net | $0.304 | $11.94 | $0.210 | — | $9.03 | cheapest | 1.0M | src |
| Kimi K3 | DeepInfra | $2.28 | $11.40 | $0.228 | — | $9.12 | cheapest | 1.0M | src |
| Kimi K3 (batch) | — | $2.28 | $11.40 | $0.228 | — | $9.12 | cheapest | 1.0M | src |
| Gemini 3.1 Pro Preview | — | $2.00 | $12.00 | $0.200 | $0.375 | $9.50 | cheapest | 1.0M | src |
| Gemini 3.1 Pro Preview | Google google-vertex/global | $2.00 | $12.00 | $0.200 | $0.375 | $9.50 | cheapest | 1.0M | src |
| Gemini 3.1 Pro Preview | Google AI Studio google-ai-studio | $2.00 | $12.00 | $0.200 | $0.375 | $9.50 | cheapest | 1.0M | src |
| Gemini 3.1 Pro Preview Custom Tools | — | $2.00 | $12.00 | $0.200 | $0.375 | $9.50 | cheapest | 1.0M | src |
| Gemini 3.1 Pro Preview Custom Tools | Google AI Studio | $2.00 | $12.00 | $0.200 | $0.375 | $9.50 | cheapest | 1.0M | src |
| GPT Terra Latest | — | $2.00 | $12.00 | $0.200 | $2.50 | $9.50 | cheapest | 1.1M | src |
| GPT-5.6 Terra | — | $2.00 | $12.00 | $0.200 | $2.50 | $9.50 | cheapest | 1.1M | src |
| GPT-5.6 Terra | Azure | $2.00 | $12.00 | $0.200 | $2.50 | $9.50 | cheapest | 1.1M | src |
| GPT-5.6 Terra | OpenAI openai | $2.00 | $12.00 | $0.200 | $2.50 | $9.50 | cheapest | 1.1M | src |
| GPT-5.6 Terra Pro | — | $2.00 | $12.00 | $0.200 | $2.50 | $9.50 | cheapest | 1.1M | src |
| GPT-5.6 Terra Pro | Azure | $2.00 | $12.00 | $0.200 | $2.50 | $9.50 | cheapest | 1.1M | src |
| GPT-5.6 Terra Pro | OpenAI openai | $2.00 | $12.00 | $0.200 | $2.50 | $9.50 | cheapest | 1.1M | src |
| Nano Banana Pro (Gemini 3 Pro Image Preview) | — | $2.00 | $12.00 | $0.200 | $0.375 | $9.50 | cheapest | 66k | src |
| Nano Banana Pro (Gemini 3 Pro Image Preview) | Google AI Studio google-ai-studio/global | $2.00 | $12.00 | $0.200 | $0.375 | $9.50 | cheapest | 66k | src |
| Nano Banana Pro (Gemini 3 Pro Image) | — | $2.00 | $12.00 | $0.200 | $0.375 | $9.50 | 0% vs Vercel AI Gateway | 131k | src |
| Nano Banana Pro (Gemini 3 Pro Image) | Google AI Studio | $2.00 | $12.00 | $0.200 | $0.375 | $9.50 | 0% vs Vercel AI Gateway | 131k | src |
| Nano Banana Pro (Gemini 3 Pro Image) | $2.00 | $12.00 | $0.200 | $0.375 | $9.50 | 0% vs Vercel AI Gateway | 66k | src | |
| Kimi K3 | Makora | $1.53 | $12.75 | $0.204 | — | $9.95 | cheapest | 1.0M | src |
| Claude Opus 4.5 | Anthropic | $2.50 | $12.50 | $0.250 | $3.13 | $10.00 | cheapest | 200k | src |
| Claude Opus 4.5 (batch) | — | $2.50 | $12.50 | $0.250 | $3.13 | $10.00 | cheapest | 200k | src |
| Claude Opus 4.6 | Anthropic | $2.50 | $12.50 | $0.250 | $3.13 | $10.00 | cheapest | 1M | src |
| Claude Opus 4.6 (batch) | — | $2.50 | $12.50 | $0.250 | $3.13 | $10.00 | cheapest | 1M | src |
| Claude Opus 4.7 | Anthropic | $2.50 | $12.50 | $0.250 | $3.13 | $10.00 | cheapest | 1M | src |
| Claude Opus 4.7 (batch) | — | $2.50 | $12.50 | $0.250 | $3.13 | $10.00 | cheapest | 1M | src |
| Claude Opus 4.8 | Anthropic | $2.50 | $12.50 | $0.250 | $3.13 | $10.00 | cheapest | 1M | src |
| Claude Opus 4.8 (batch) | — | $2.50 | $12.50 | $0.250 | $3.13 | $10.00 | cheapest | 1M | src |
| Claude Opus 5 | Anthropic | $2.50 | $12.50 | $0.250 | $3.13 | $10.00 | cheapest | 1M | src |
| Claude Opus 5 (batch) | — | $2.50 | $12.50 | $0.250 | $3.13 | $10.00 | cheapest | 1M | src |
| GPT-5 Image | — | $10.00 | $10.00 | $1.25 | — | $10.00 | cheapest | 400k | src |
| GPT-5 Image | OpenAI | $10.00 | $10.00 | $1.25 | — | $10.00 | cheapest | 400k | src |
| Grok 4.5 | xAI xai/zdr/priority | $4.00 | $12.00 | $0.600 | — | $10.00 | +100% vs Vercel AI Gateway | 500k | src |
| Grok 4.5 | xAI xai/priority | $4.00 | $12.00 | $0.600 | — | $10.00 | +100% vs Vercel AI Gateway | 500k | src |
| Grok 4.6 | xAI xai/zdr/priority | $4.00 | $12.00 | $1.00 | — | $10.00 | +100% vs Vercel AI Gateway | 500k | src |
| Grok 4.6 | xAI xai/priority | $4.00 | $12.00 | $1.00 | — | $10.00 | +100% vs Vercel AI Gateway | 500k | src |
| Grok 4.7 | xAI xai/zdr/priority | $4.00 | $12.00 | $1.00 | — | $10.00 | +100% vs Vercel AI Gateway | 500k | src |
| Grok 4.7 | xAI xai/priority | $4.00 | $12.00 | $1.00 | — | $10.00 | +100% vs Vercel AI Gateway | 500k | src |
| Nova Premier 1.0 | — | $2.50 | $12.50 | $0.625 | — | $10.00 | cheapest | 1M | src |
| Nova Premier 1.0 | Bedrock | $2.50 | $12.50 | $0.625 | — | $10.00 | cheapest | 1M | src |
| Qwen3.8 Max Prime | — | $4.00 | $12.00 | $0.500 | — | $10.00 | cheapest | 1M | src |
| Qwen3.8 Max Prime | Alibaba | $4.00 | $12.00 | $0.500 | — | $10.00 | cheapest | 1M | src |
| Kimi K3 | Phala | $2.55 | $12.75 | $0.255 | — | $10.20 | cheapest | 1.0M | src |
| Kimi K3 | Sail Research fp4 | $0.840 | $13.50 | $0.300 | — | $10.34 | cheapest | 1.0M | src |
| Kimi K3 | DigitalOcean | $2.55 | $12.95 | $0.255 | — | $10.35 | cheapest | 1.0M | src |
| GPT-5.6 Terra | Azure azure/us | $2.20 | $13.20 | $0.220 | $2.75 | $10.45 | cheapest | 1.1M | src |
| GPT-5.6 Terra | Bedrock | $2.20 | $13.20 | $0.220 | $2.75 | $10.45 | cheapest | 1.1M | src |
| GPT-5.6 Terra | Azure azure/eu | $2.20 | $13.20 | $0.220 | $2.75 | $10.45 | cheapest | 1.1M | src |
| GPT-5.6 Terra Pro | Azure azure/eu | $2.20 | $13.20 | $0.220 | $2.75 | $10.45 | cheapest | 1.1M | src |
| Kimi K3 | Relace | $0.270 | $14.00 | $0.270 | — | $10.57 | cheapest | 1.0M | src |
| Kimi Latest | — | $0.270 | $14.00 | $0.270 | — | $10.57 | cheapest | 1.0M | src |
| Kimi K3 | AkashML | $1.20 | $14.00 | $1.20 | — | $10.80 | cheapest | 1.0M | src |
| GPT-5.2 | — | $1.75 | $14.00 | $0.175 | — | $10.94 | cheapest | 400k | src |
| GPT-5.2 | Azure | $1.75 | $14.00 | $0.175 | — | $10.94 | cheapest | 400k | src |
| GPT-5.2 | OpenAI openai | $1.75 | $14.00 | $0.175 | — | $10.94 | cheapest | 400k | src |
| GPT-5.2 Chat | — | $1.75 | $14.00 | $0.175 | — | $10.94 | cheapest | 128k | src |
| GPT-5.2 Chat | Azure | $1.75 | $14.00 | $0.175 | — | $10.94 | cheapest | 128k | src |
| GPT-5.2-Codex | — | $1.75 | $14.00 | $0.175 | — | $10.94 | cheapest | 400k | src |
| GPT-5.2-Codex | Azure | $1.75 | $14.00 | $0.175 | — | $10.94 | cheapest | 400k | src |
| GPT-5.3-Codex | — | $1.75 | $14.00 | $0.175 | — | $10.94 | cheapest | 400k | src |
| GPT-5.3-Codex | Azure | $1.75 | $14.00 | $0.175 | — | $10.94 | cheapest | 400k | src |
| GPT-5.3-Codex | OpenAI | $1.75 | $14.00 | $0.175 | — | $10.94 | cheapest | 400k | src |
| Kimi K3 | Wafer mxfp4 | $0.360 | $14.90 | $0.359 | — | $11.27 | cheapest | 1.0M | src |
| Kimi K3 | Morph | $0.800 | $14.90 | $0.290 | — | $11.38 | cheapest | 1.0M | src |
| Kimi K3 | DeepInfra | $2.85 | $14.25 | $0.285 | — | $11.40 | cheapest | 1.0M | src |
| Kimi K3 | Inference Net fp4 | $2.49 | $15.00 | $0.350 | — | $11.87 | cheapest | 1.0M | src |
| GPT-5.4 | — | $2.50 | $15.00 | $0.250 | — | $11.88 | cheapest | 1.1M | src |
| GPT-5.4 | Azure | $2.50 | $15.00 | $0.250 | — | $11.88 | cheapest | 1.1M | src |
| GPT-5.4 | OpenAI openai | $2.50 | $15.00 | $0.250 | — | $11.88 | cheapest | 1.1M | src |
| GPT-5.5 | OpenAI | $2.50 | $15.00 | $0.250 | — | $11.88 | cheapest | 1.1M | src |
| GPT-5.5 | OpenAI | $2.50 | $15.00 | $0.250 | — | $11.88 | cheapest | 1.1M | src |
| GPT-5.5 (batch) | — | $2.50 | $15.00 | $0.250 | — | $11.88 | cheapest | 1.1M | src |
| Claude Sonnet 4.5 | — | $3.00 | $15.00 | $0.300 | $3.75 | $12.00 | cheapest | 1M | src |
| Claude Sonnet 4.5 | Claude Platform On AWS | $3.00 | $15.00 | $0.300 | $3.75 | $12.00 | cheapest | 1M | src |
| Claude Sonnet 4.5 | Azure | $3.00 | $15.00 | $0.300 | $3.75 | $12.00 | cheapest | 200k | src |
| Claude Sonnet 4.5 | Bedrock | $3.00 | $15.00 | $0.300 | $3.75 | $12.00 | cheapest | 1M | src |
| Claude Sonnet 4.5 | Anthropic | $3.00 | $15.00 | $0.300 | $3.75 | $12.00 | cheapest | 1M | src |
| Claude Sonnet 4.5 | $3.00 | $15.00 | $0.300 | $3.75 | $12.00 | cheapest | 1M | src | |
| Claude Sonnet 4.6 | — | $3.00 | $15.00 | $0.300 | $3.75 | $12.00 | cheapest | 1M | src |
| Claude Sonnet 4.6 | Claude Platform On AWS | $3.00 | $15.00 | $0.300 | $3.75 | $12.00 | cheapest | 1M | src |
| Claude Sonnet 4.6 | Azure | $3.00 | $15.00 | $0.300 | $3.75 | $12.00 | cheapest | 1M | src |
| Claude Sonnet 4.6 | Anthropic | $3.00 | $15.00 | $0.300 | $3.75 | $12.00 | cheapest | 1M | src |
| Claude Sonnet 4.6 | Bedrock | $3.00 | $15.00 | $0.300 | $3.75 | $12.00 | cheapest | 1M | src |
| Claude Sonnet 4.6 | $3.00 | $15.00 | $0.300 | $3.75 | $12.00 | cheapest | 1M | src | |
| Ember-1 | — | $3.00 | $15.00 | $0.300 | — | $12.00 | 0% vs Fireworks AI | 1.0M | src |
| Ember-1 | Fireworks | $3.00 | $15.00 | $0.300 | — | $12.00 | 0% vs Fireworks AI | 1.0M | src |
| Kimi K3 | Parasail | $3.00 | $15.00 | $0.300 | — | $12.00 | cheapest | 1M | src |
| Kimi K3 | Bedrock | $3.00 | $15.00 | $0.300 | $3.75 | $12.00 | cheapest | 1.0M | src |
| Kimi K3 | Modal | $3.00 | $15.00 | $0.300 | — | $12.00 | cheapest | 1.0M | src |
| Kimi K3 | Together | $3.00 | $15.00 | $0.300 | — | $12.00 | cheapest | 1.0M | src |
| Kimi K3 | Fireworks | $3.00 | $15.00 | $0.300 | — | $12.00 | cheapest | 1.0M | src |
| Kimi K3 | Baseten | $3.00 | $15.00 | $0.300 | — | $12.00 | cheapest | 1.0M | src |
| Kimi K3 | Moonshot AI | $3.00 | $15.00 | $0.300 | — | $12.00 | cheapest | 1.0M | src |
| Sonar Pro | — | $3.00 | $15.00 | — | — | $12.00 | 0% vs Perplexity | 200k | src |
| Sonar Pro | Perplexity | $3.00 | $15.00 | — | — | $12.00 | 0% vs Perplexity | 200k | src |
| Sonar Pro Search | — | $3.00 | $15.00 | — | — | $12.00 | cheapest | 200k | src |
| Sonar Pro Search | Perplexity | $3.00 | $15.00 | — | — | $12.00 | cheapest | 200k | src |
| GPT-4 Turbo | OpenAI | $5.00 | $15.00 | — | — | $12.50 | cheapest | 128k | src |
| GPT-4 Turbo (batch) | — | $5.00 | $15.00 | — | — | $12.50 | cheapest | 128k | src |
| GPT-4o (2024-05-13) | — | $5.00 | $15.00 | — | — | $12.50 | cheapest | 128k | src |
| GPT-4o (2024-05-13) | Azure | $5.00 | $15.00 | — | — | $12.50 | cheapest | 128k | src |
| GPT-4o (2024-05-13) | OpenAI | $5.00 | $15.00 | — | — | $12.50 | cheapest | 128k | src |
| Gemini 3.5 Flash | Google google-vertex/global/priority | $2.70 | $16.20 | $0.270 | $0.150 | $12.82 | cheapest | 1.0M | src |
| Gemini 3.5 Flash | Google AI Studio google-ai-studio/priority | $2.70 | $16.20 | $0.270 | $0.150 | $12.82 | cheapest | 1.0M | src |
| GPT-5.4 | Azure azure/us | $2.75 | $16.50 | $0.275 | — | $13.06 | cheapest | 1.1M | src |
| GPT-5.4 | Azure azure/eu | $2.75 | $16.50 | $0.275 | — | $13.06 | cheapest | 1.1M | src |
| GPT-5.4 | Bedrock | $2.75 | $16.50 | $0.275 | — | $13.06 | cheapest | 1.1M | src |
| Claude Sonnet 4.5 | Bedrock amazon-bedrock/eu-west-1 | $3.30 | $16.50 | $0.330 | $4.13 | $13.20 | cheapest | 1M | src |
| Claude Sonnet 4.5 | Google google-vertex/us-east5 | $3.30 | $16.50 | $0.330 | $4.13 | $13.20 | cheapest | 1M | src |
| Claude Sonnet 4.6 | Bedrock amazon-bedrock/us | $3.30 | $16.50 | $0.330 | $4.13 | $13.20 | cheapest | 1M | src |
| Claude Sonnet 4.6 | Bedrock amazon-bedrock/eu-west-1 | $3.30 | $16.50 | $0.330 | $4.13 | $13.20 | cheapest | 1M | src |
| Claude Sonnet 4.6 | Google google-vertex/europe | $3.30 | $16.50 | $0.330 | $4.13 | $13.20 | cheapest | 1M | src |
| Claude Sonnet 4.6 | Google google-vertex/us-east5 | $3.30 | $16.50 | $0.330 | $4.13 | $13.20 | cheapest | 1M | src |
| GPT-5.4 Image 2 | — | $8.00 | $15.00 | $2.00 | — | $13.25 | cheapest | 272k | src |
| GPT-5.4 Image 2 | OpenAI | $8.00 | $15.00 | $2.00 | — | $13.25 | cheapest | 272k | src |
| Kimi K3 | Alibaba | $3.45 | $17.25 | $0.345 | — | $13.80 | cheapest | 1.0M | src |
| Gemini 2.5 Pro | Google google-vertex/global/priority | $2.25 | $18.00 | $0.225 | $0.675 | $14.06 | cheapest | 1.0M | src |
| Gemini 2.5 Pro | Google AI Studio google-ai-studio/priority | $2.25 | $18.00 | $0.225 | $0.675 | $14.06 | cheapest | 1.0M | src |
| Gemini 4 Argon | Google google-vertex/global/priority | $3.60 | $18.00 | $0.180 | $0.338 | $14.40 | cheapest | 1.0M | src |
| Gemini 4 Argon | Google AI Studio google-ai-studio/priority | $3.60 | $18.00 | $0.180 | $0.338 | $14.40 | cheapest | 1.0M | src |
| GPT-5.1 | OpenAI openai/fast | $2.50 | $20.00 | $0.250 | — | $15.63 | cheapest | 400k | src |
| Claude Opus 5.5 | — | $4.00 | $20.00 | $0.200 | $5.00 | $16.00 | cheapest | 1M | src |
| Claude Opus 5.5 | Bedrock | $4.00 | $20.00 | $0.200 | $5.00 | $16.00 | cheapest | 1M | src |
| Claude Opus 5.5 | Azure | $4.00 | $20.00 | $0.200 | $5.00 | $16.00 | cheapest | 1M | src |
| Claude Opus 5.5 | $4.00 | $20.00 | $0.200 | $5.00 | $16.00 | cheapest | 1M | src | |
| Claude Opus 5.5 | Claude Platform On AWS | $4.00 | $20.00 | $0.200 | $5.00 | $16.00 | cheapest | 1M | src |
| Claude Opus 5.5 | Anthropic | $4.00 | $20.00 | $0.200 | $5.00 | $16.00 | cheapest | 1M | src |
| Claude Opus Latest | — | $4.00 | $20.00 | $0.200 | $5.00 | $16.00 | cheapest | 1M | src |
| GPT-5.6 Sol | — | $4.00 | $20.00 | $0.400 | $5.00 | $16.00 | cheapest | 1.1M | src |
| GPT-5.6 Sol | Azure | $4.00 | $20.00 | $0.400 | $5.00 | $16.00 | cheapest | 1.1M | src |
| GPT-5.6 Sol | OpenAI openai | $4.00 | $20.00 | $0.400 | $5.00 | $16.00 | cheapest | 1.1M | src |
| GPT-5.6 Sol Pro | — | $4.00 | $20.00 | $0.400 | $5.00 | $16.00 | cheapest | 1.1M | src |
| GPT-5.6 Sol Pro | Azure | $4.00 | $20.00 | $0.400 | $5.00 | $16.00 | cheapest | 1.1M | src |
| GPT-5.6 Sol Pro | OpenAI openai | $4.00 | $20.00 | $0.400 | $5.00 | $16.00 | cheapest | 1.1M | src |
| GPT-6 Sol | OpenAI openai/fast | $4.00 | $20.00 | $0.400 | $5.00 | $16.00 | cheapest | 1.1M | src |
| GPT-6 Sol Pro | OpenAI openai/fast | $4.00 | $20.00 | $0.400 | $5.00 | $16.00 | cheapest | 1.1M | src |
| GPT-6.1 Sol | OpenAI openai/fast | $4.00 | $20.00 | $0.200 | $5.00 | $16.00 | cheapest | 1.1M | src |
| GPT-6.1 Sol Pro | OpenAI openai/fast | $4.00 | $20.00 | $0.200 | $5.00 | $16.00 | cheapest | 1.1M | src |
| Muse Wonder | — | $4.00 | $20.00 | $0.200 | — | $16.00 | 0% vs Vercel AI Gateway | 1.0M | src |
| Muse Wonder | Meta | $4.00 | $20.00 | $0.200 | — | $16.00 | 0% vs Vercel AI Gateway | 1.0M | src |
| Gemini 3.1 Pro Preview | Google google-vertex/global/priority | $3.60 | $21.60 | $0.360 | $0.675 | $17.10 | cheapest | 1.0M | src |
| Gemini 3.1 Pro Preview | Google AI Studio google-ai-studio/priority | $3.60 | $21.60 | $0.360 | $0.675 | $17.10 | cheapest | 1.0M | src |
| Claude Opus 5.5 | Bedrock amazon-bedrock/eu-west-1 | $4.40 | $22.00 | $0.220 | $5.50 | $17.60 | cheapest | 1M | src |
| Claude Opus 5.5 | Bedrock amazon-bedrock/us-east-1 | $4.40 | $22.00 | $0.220 | $5.50 | $17.60 | cheapest | 1M | src |
| Claude Opus 5.5 | Azure azure/us | $4.40 | $22.00 | $0.220 | $5.50 | $17.60 | cheapest | 1M | src |
| Claude Opus 5.5 | Google google-vertex/us | $4.40 | $22.00 | $0.220 | $5.50 | $17.60 | cheapest | 1M | src |
| Claude Opus 5.5 | Google google-vertex/europe | $4.40 | $22.00 | $0.220 | $5.50 | $17.60 | cheapest | 1M | src |
| GPT-5.6 Sol | Azure azure/us | $4.40 | $22.00 | $0.440 | $5.50 | $17.60 | cheapest | 1.1M | src |
| GPT-5.6 Sol | Bedrock | $4.40 | $22.00 | $0.440 | $5.50 | $17.60 | cheapest | 1.1M | src |
| GPT-5.6 Sol | Azure azure/eu | $4.40 | $22.00 | $0.440 | $5.50 | $17.60 | cheapest | 1.1M | src |
| GPT-5.6 Sol Pro | Azure azure/eu | $4.40 | $22.00 | $0.440 | $5.50 | $17.60 | cheapest | 1.1M | src |
| Kimi K3 | Fireworks fireworks/us | $4.50 | $22.50 | $0.450 | — | $18.00 | cheapest | 1.0M | src |
| Kimi K3 | Fireworks fireworks/fast | $4.50 | $22.50 | $0.450 | — | $18.00 | cheapest | 1.0M | src |
| Kimi K3 | Wafer | $0.280 | $24.00 | $0.270 | — | $18.07 | cheapest | 1.0M | src |
| GPT-5.6 Terra | OpenAI openai/fast | $4.00 | $24.00 | $0.400 | $5.00 | $19.00 | cheapest | 1.1M | src |
| GPT-5.6 Terra Pro | OpenAI openai/fast | $4.00 | $24.00 | $0.400 | $5.00 | $19.00 | cheapest | 1.1M | src |
| Claude Fable 5 | Anthropic | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 1M | src |
| Claude Fable 5 (batch) | — | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 1M | src |
| Claude Fable 5.1 | Anthropic | $5.00 | $25.00 | $0.125 | $6.25 | $20.00 | cheapest | 1M | src |
| Claude Fable 5.1 (batch) | — | $5.00 | $25.00 | $0.125 | $6.25 | $20.00 | cheapest | 1M | src |
| Claude Opus 4.5 | — | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 200k | src |
| Claude Opus 4.5 | Claude Platform On AWS | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 200k | src |
| Claude Opus 4.5 | Azure | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 200k | src |
| Claude Opus 4.5 | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 200k | src | |
| Claude Opus 4.5 | Bedrock | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 200k | src |
| Claude Opus 4.5 | Anthropic | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 200k | src |
| Claude Opus 4.6 | — | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 1M | src |
| Claude Opus 4.6 | Claude Platform On AWS | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 1M | src |
| Claude Opus 4.6 | Azure | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 1M | src |
| Claude Opus 4.6 | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 1M | src | |
| Claude Opus 4.6 | Bedrock | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 1M | src |
| Claude Opus 4.6 | Anthropic | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 1M | src |
| Claude Opus 4.7 | — | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 1M | src |
| Claude Opus 4.7 | Claude Platform On AWS | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 1M | src |
| Claude Opus 4.7 | Azure | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 1M | src |
| Claude Opus 4.7 | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 1M | src | |
| Claude Opus 4.7 | Bedrock | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 1M | src |
| Claude Opus 4.7 | Anthropic | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 1M | src |
| Claude Opus 4.8 | — | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 1M | src |
| Claude Opus 4.8 | Claude Platform On AWS | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 1M | src |
| Claude Opus 4.8 | Azure | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 1M | src |
| Claude Opus 4.8 | Bedrock | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 1M | src |
| Claude Opus 4.8 | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 1M | src | |
| Claude Opus 4.8 | Anthropic | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 1M | src |
| Claude Opus 5 | — | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 1M | src |
| Claude Opus 5 | Claude Platform On AWS | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 1M | src |
| Claude Opus 5 | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 1M | src | |
| Claude Opus 5 | Bedrock | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 1M | src |
| Claude Opus 5 | Azure | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 1M | src |
| Claude Opus 5 | Anthropic | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 1M | src |
| GPT-6 Astra | OpenAI | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 1.1M | src |
| GPT-6 Astra | OpenAI | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 1.1M | src |
| GPT-6 Astra (batch) | — | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 1.1M | src |
| GPT-6 Astra Pro | OpenAI | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 1.1M | src |
| GPT-6 Astra Pro | OpenAI | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 1.1M | src |
| GPT-6 Astra Pro (batch) | — | $5.00 | $25.00 | $0.500 | $6.25 | $20.00 | cheapest | 1.1M | src |
| GPT-5.2 | OpenAI openai/fast | $3.50 | $28.00 | $0.350 | — | $21.88 | cheapest | 400k | src |
| GPT-5.3-Codex | OpenAI openai/fast | $3.50 | $28.00 | $0.350 | — | $21.88 | cheapest | 400k | src |
| Claude Opus 4.5 | Bedrock amazon-bedrock/eu-west-1 | $5.50 | $27.50 | $0.550 | $6.88 | $22.00 | cheapest | 200k | src |
| Claude Opus 4.6 | Google google-vertex/europe | $5.50 | $27.50 | $0.550 | $6.88 | $22.00 | cheapest | 1M | src |
| Claude Opus 4.7 | Google google-vertex/us | $5.50 | $27.50 | $0.550 | $6.88 | $22.00 | cheapest | 1M | src |
| Claude Opus 4.7 | Bedrock amazon-bedrock/eu-west-1 | $5.50 | $27.50 | $0.550 | $6.88 | $22.00 | cheapest | 1M | src |
| Claude Opus 4.7 | Google google-vertex/europe | $5.50 | $27.50 | $0.550 | $6.88 | $22.00 | cheapest | 1M | src |
| Claude Opus 4.8 | Azure azure/us | $5.50 | $27.50 | $0.550 | $6.88 | $22.00 | cheapest | 1M | src |
| Claude Opus 4.8 | Bedrock amazon-bedrock/us | $5.50 | $27.50 | $0.550 | $6.88 | $22.00 | cheapest | 1M | src |
| Claude Opus 4.8 | Google google-vertex/us | $5.50 | $27.50 | $0.550 | $6.88 | $22.00 | cheapest | 1M | src |
| Claude Opus 4.8 | Bedrock amazon-bedrock/eu-west-1 | $5.50 | $27.50 | $0.550 | $6.88 | $22.00 | cheapest | 1M | src |
| Claude Opus 4.8 | Google google-vertex/europe | $5.50 | $27.50 | $0.550 | $6.88 | $22.00 | cheapest | 1M | src |
| Claude Opus 5 | Bedrock amazon-bedrock/eu-west-1 | $5.50 | $27.50 | $0.550 | $6.88 | $22.00 | cheapest | 1M | src |
| Claude Opus 5 | Azure azure/us | $5.50 | $27.50 | $0.550 | $6.88 | $22.00 | cheapest | 1M | src |
| Claude Opus 5 | Google google-vertex/us | $5.50 | $27.50 | $0.550 | $6.88 | $22.00 | cheapest | 1M | src |
| Claude Opus 5 | Google google-vertex/europe | $5.50 | $27.50 | $0.550 | $6.88 | $22.00 | cheapest | 1M | src |
| Claude Opus 5 | Bedrock amazon-bedrock/us-east-1 | $5.50 | $27.50 | $0.550 | $6.88 | $22.00 | cheapest | 1M | src |
| Fugu Ultra | — | $5.00 | $30.00 | $0.500 | — | $23.75 | 0% vs Vercel AI Gateway | 1M | src |
| Fugu Ultra | Sakana AI | $5.00 | $30.00 | $0.500 | — | $23.75 | 0% vs Vercel AI Gateway | 1M | src |
| Fugu Ultra v2 | — | $5.00 | $30.00 | $0.500 | — | $23.75 | 0% vs Vercel AI Gateway | 1M | src |
| Fugu Ultra v2 | Sakana AI | $5.00 | $30.00 | $0.500 | — | $23.75 | 0% vs Vercel AI Gateway | 1M | src |
| GPT Chat Latest | — | $5.00 | $30.00 | $0.500 | — | $23.75 | cheapest | 400k | src |
| GPT Chat Latest | OpenAI | $5.00 | $30.00 | $0.500 | — | $23.75 | cheapest | 400k | src |
| GPT-5.4 | OpenAI openai/fast | $5.00 | $30.00 | $0.500 | — | $23.75 | cheapest | 1.1M | src |
| GPT-5.5 | — | $5.00 | $30.00 | $0.500 | — | $23.75 | cheapest | 1.1M | src |
| GPT-5.5 | Azure | $5.00 | $30.00 | $0.500 | — | $23.75 | cheapest | 1.1M | src |
| GPT-5.5 | OpenAI openai | $5.00 | $30.00 | $0.500 | — | $23.75 | cheapest | 1.1M | src |
| GPT-4 Turbo | — | $10.00 | $30.00 | — | — | $25.00 | cheapest | 128k | src |
| GPT-4 Turbo | OpenAI | $10.00 | $30.00 | — | — | $25.00 | cheapest | 128k | src |
| GPT-5.5 | Azure azure/us | $5.50 | $33.00 | $0.550 | — | $26.13 | cheapest | 1.1M | src |
| GPT-5.5 | Azure azure/eu | $5.50 | $33.00 | $0.550 | — | $26.13 | cheapest | 1.1M | src |
| GPT-5.5 | Bedrock | $5.50 | $33.00 | $0.550 | — | $26.13 | cheapest | 1.1M | src |
| Claude Opus 4.1 | Anthropic | $7.50 | $37.50 | $0.750 | $9.38 | $30.00 | cheapest | 200k | src |
| Claude Opus 4.1 (batch) | — | $7.50 | $37.50 | $0.750 | $9.38 | $30.00 | cheapest | 200k | src |
| Claude Opus 5.5 | Anthropic anthropic/fast | $8.00 | $40.00 | $0.400 | $10.00 | $32.00 | cheapest | 1M | src |
| GPT-5.6 Sol | OpenAI openai/fast | $8.00 | $40.00 | $0.800 | $10.00 | $32.00 | cheapest | 1.1M | src |
| GPT-5.6 Sol Pro | OpenAI openai/fast | $8.00 | $40.00 | $0.800 | $10.00 | $32.00 | cheapest | 1.1M | src |
| Claude Fable 5 | — | $10.00 | $50.00 | $1.00 | $12.50 | $40.00 | cheapest | 1M | src |
| Claude Fable 5 | Claude Platform On AWS | $10.00 | $50.00 | $1.00 | $12.50 | $40.00 | cheapest | 1M | src |
| Claude Fable 5 | Azure | $10.00 | $50.00 | $1.00 | $12.50 | $40.00 | cheapest | 1M | src |
| Claude Fable 5 | Bedrock | $10.00 | $50.00 | $1.00 | $12.50 | $40.00 | cheapest | 1M | src |
| Claude Fable 5 | $10.00 | $50.00 | $1.00 | $12.50 | $40.00 | cheapest | 1M | src | |
| Claude Fable 5 | Anthropic | $10.00 | $50.00 | $1.00 | $12.50 | $40.00 | cheapest | 1M | src |
| Claude Fable 5.1 | — | $10.00 | $50.00 | $0.250 | $12.50 | $40.00 | cheapest | 1M | src |
| Claude Fable 5.1 | Azure | $10.00 | $50.00 | $0.250 | $12.50 | $40.00 | cheapest | 1M | src |
| Claude Fable 5.1 | Anthropic | $10.00 | $50.00 | $0.250 | $12.50 | $40.00 | cheapest | 1M | src |
| Claude Fable 5.1 | Bedrock | $10.00 | $50.00 | $0.250 | $12.50 | $40.00 | cheapest | 1M | src |
| Claude Fable 5.1 | $10.00 | $50.00 | $0.250 | $12.50 | $40.00 | cheapest | 1M | src | |
| Claude Fable Latest | — | $10.00 | $50.00 | $0.250 | $12.50 | $40.00 | cheapest | 1M | src |
| Claude Opus 4.8 | Anthropic anthropic/fast | $10.00 | $50.00 | $1.00 | $12.50 | $40.00 | cheapest | 1M | src |
| Claude Opus 5 | Anthropic anthropic/fast | $10.00 | $50.00 | $1.00 | $12.50 | $40.00 | cheapest | 1M | src |
| GPT Astra Latest | — | $10.00 | $50.00 | $1.00 | $12.50 | $40.00 | cheapest | 1.1M | src |
| GPT-6 Astra | — | $10.00 | $50.00 | $1.00 | $12.50 | $40.00 | cheapest | 1.1M | src |
| GPT-6 Astra | Azure | $10.00 | $50.00 | $1.00 | $12.50 | $40.00 | cheapest | 1.1M | src |
| GPT-6 Astra | OpenAI openai | $10.00 | $50.00 | $1.00 | $12.50 | $40.00 | cheapest | 1.1M | src |
| GPT-6 Astra Pro | — | $10.00 | $50.00 | $1.00 | $12.50 | $40.00 | cheapest | 1.1M | src |
| GPT-6 Astra Pro | Azure | $10.00 | $50.00 | $1.00 | $12.50 | $40.00 | cheapest | 1.1M | src |
| GPT-6 Astra Pro | OpenAI openai | $10.00 | $50.00 | $1.00 | $12.50 | $40.00 | cheapest | 1.1M | src |
| Claude Fable 5 | Google google-vertex/europe | $11.00 | $55.00 | $1.10 | $13.75 | $44.00 | cheapest | 1M | src |
| GPT-6 Astra | Bedrock | $11.00 | $55.00 | $1.10 | $13.75 | $44.00 | cheapest | 1.1M | src |
| GPT-6 Astra | Azure azure/us | $11.00 | $55.00 | $1.10 | $13.75 | $44.00 | cheapest | 1.1M | src |
| GPT-6 Astra Pro | Azure azure/us | $11.00 | $55.00 | $1.10 | $13.75 | $44.00 | cheapest | 1.1M | src |
| GPT-5 Pro | OpenAI | $7.50 | $60.00 | — | — | $46.88 | cheapest | 400k | src |
| GPT-5 Pro (batch) | — | $7.50 | $60.00 | — | — | $46.88 | cheapest | 400k | src |
| GPT-6.1 Sol | OpenAI openai/ultrafast | $12.00 | $60.00 | $0.600 | $15.00 | $48.00 | cheapest | 1.1M | src |
| GPT-6.1 Sol Pro | OpenAI openai/ultrafast | $12.00 | $60.00 | $0.600 | $15.00 | $48.00 | cheapest | 1.1M | src |
| o1 | — | $15.00 | $60.00 | $7.50 | — | $48.75 | 0% vs OpenAI | 200k | src |
| o1 | OpenAI | $15.00 | $60.00 | $7.50 | — | $48.75 | 0% vs OpenAI | 200k | src |
| GPT-4 | — | $30.00 | $60.00 | — | — | $52.50 | cheapest | 8k | src |
| GPT-4 | Azure | $30.00 | $60.00 | — | — | $52.50 | cheapest | 8k | src |
| GPT-4 | OpenAI | $30.00 | $60.00 | — | — | $52.50 | cheapest | 8k | src |
| GPT-5.5 | OpenAI openai/fast | $12.50 | $75.00 | $1.25 | — | $59.38 | cheapest | 1.1M | src |
| Claude Opus 4.1 | — | $15.00 | $75.00 | $1.50 | $18.75 | $60.00 | cheapest | 200k | src |
| Claude Opus 4.1 | Bedrock | $15.00 | $75.00 | $1.50 | $18.75 | $60.00 | cheapest | 200k | src |
| o3 Pro | — | $20.00 | $80.00 | — | — | $65.00 | 0% vs Vercel AI Gateway | 200k | src |
| o3 Pro | OpenAI | $20.00 | $80.00 | — | — | $65.00 | 0% vs Vercel AI Gateway | 200k | src |
| GPT-5.2 Pro | OpenAI | $10.50 | $84.00 | — | — | $65.63 | cheapest | 400k | src |
| GPT-5.2 Pro (batch) | — | $10.50 | $84.00 | — | — | $65.63 | cheapest | 400k | src |
| GPT-5.4 Pro | OpenAI | $15.00 | $90.00 | — | — | $71.25 | cheapest | 1.1M | src |
| GPT-5.4 Pro | OpenAI | $15.00 | $90.00 | — | — | $71.25 | cheapest | 1.1M | src |
| GPT-5.4 Pro (batch) | — | $15.00 | $90.00 | — | — | $71.25 | cheapest | 1.1M | src |
| GPT-5.5 Pro | OpenAI | $15.00 | $90.00 | — | — | $71.25 | cheapest | 1.1M | src |
| GPT-5.5 Pro | OpenAI | $15.00 | $90.00 | — | — | $71.25 | cheapest | 1.1M | src |
| GPT-5.5 Pro (batch) | — | $15.00 | $90.00 | — | — | $71.25 | cheapest | 1.1M | src |
| GPT-6 Astra | OpenAI openai/fast | $20.00 | $100.00 | $2.00 | $25.00 | $80.00 | cheapest | 1.1M | src |
| GPT-6 Astra Pro | OpenAI openai/fast | $20.00 | $100.00 | $2.00 | $25.00 | $80.00 | cheapest | 1.1M | src |
| GPT-5 Pro | — | $15.00 | $120.00 | — | — | $93.75 | cheapest | 400k | src |
| GPT-5 Pro | OpenAI | $15.00 | $120.00 | — | — | $93.75 | cheapest | 400k | src |
| GPT-5.2 Pro | — | $21.00 | $168.00 | — | — | $131.25 | cheapest | 400k | src |
| GPT-5.2 Pro | OpenAI | $21.00 | $168.00 | — | — | $131.25 | cheapest | 400k | src |
| GPT-5.4 Pro | — | $30.00 | $180.00 | — | — | $142.50 | cheapest | 1.1M | src |
| GPT-5.4 Pro | Azure | $30.00 | $180.00 | — | — | $142.50 | cheapest | 1.1M | src |
| GPT-5.4 Pro | OpenAI openai | $30.00 | $180.00 | — | — | $142.50 | cheapest | 1.1M | src |
| GPT-5.5 Pro | — | $30.00 | $180.00 | — | — | $142.50 | cheapest | 1.1M | src |
| GPT-5.5 Pro | OpenAI openai | $30.00 | $180.00 | — | — | $142.50 | cheapest | 1.1M | src |
| GPT-6 Astra | OpenAI openai/ultrafast | $60.00 | $300.00 | $6.00 | $75.00 | $240.00 | cheapest | 1.1M | src |
| GPT-6 Astra Pro | OpenAI openai/ultrafast | $60.00 | $300.00 | $6.00 | $75.00 | $240.00 | cheapest | 1.1M | src |
| o1-pro | — | $150.00 | $600.00 | — | — | $487.50 | 0% vs OpenAI | 200k | src |
| o1-pro | OpenAI | $150.00 | $600.00 | — | — | $487.50 | 0% vs OpenAI | 200k | src |