inspired by: gputable.dev · Brandon @burcs
ModelTable - LLM prices · all providers
139 rows. Prices USD / 1M tokens.
| Model | Via | $/M in | $/M out | Cache R | Cache W | Blend | vs cheapest | Ctx | |
|---|---|---|---|---|---|---|---|---|---|
| Llama 3.2 1B Instruct | — | $0.020 | $0.020 | — | — | $0.020 | cheapest | 131k | src |
| Qwen3 4B | — | $0.030 | $0.030 | — | — | $0.030 | cheapest | 128k | src |
| Llama 3 8B Instruct | — | $0.040 | $0.040 | — | — | $0.040 | cheapest | 8k | src |
| Llama 3.1 8B Instruct | — | $0.020 | $0.050 | — | — | $0.043 | cheapest | 16k | src |
| Llama 3.2 3B Instruct | — | $0.030 | $0.050 | — | — | $0.045 | cheapest | 33k | src |
| L3 8B Stheno V3.2 | — | $0.050 | $0.050 | — | — | $0.050 | cheapest | 8k | src |
| Sao10k L3 8B Lunaris | — | $0.050 | $0.050 | — | — | $0.050 | cheapest | 8k | src |
| Qwen 2 7B Instruct | — | $0.054 | $0.054 | — | — | $0.054 | cheapest | 33k | src |
| OpenChat 7B | — | $0.060 | $0.060 | — | — | $0.060 | cheapest | 4k | src |
| BaiChuan M2 32B | — | $0.070 | $0.070 | — | — | $0.070 | cheapest | 131k | src |
| Qwen2.5 7B Instruct | — | $0.070 | $0.070 | — | — | $0.070 | cheapest | 32k | src |
| DeepSeek R1 0528 Qwen3 8B | — | $0.060 | $0.090 | — | — | $0.083 | cheapest | 128k | src |
| Gemma3 12B | — | $0.050 | $0.100 | — | — | $0.087 | cheapest | 131k | src |
| Mythomax L2 13B | — | $0.090 | $0.090 | — | — | $0.090 | cheapest | 4k | src |
| AutoGLM-Phone-9B-Multilingual | — | $0.035 | $0.138 | — | — | $0.112 | cheapest | 66k | src |
| Qwen3 8B | — | $0.035 | $0.138 | — | — | $0.112 | cheapest | 128k | src |
| OpenAI: GPT OSS 20B | — | $0.040 | $0.150 | — | — | $0.122 | cheapest | 131k | src |
| Mistral Nemo | — | $0.040 | $0.170 | — | — | $0.138 | +405% vs OpenRouter | 60k | src |
| Hermes 2 Pro Llama 3 8B | — | $0.140 | $0.140 | — | — | $0.140 | cheapest | 8k | src |
| DeepSeek R1 Distill Qwen 14B | — | $0.150 | $0.150 | — | — | $0.150 | cheapest | 33k | src |
| Ling 3.0 Flash | — | $0.060 | $0.180 | $0.012 | — | $0.150 | cheapest | 262k | src |
| Ling 3.0 Flash Fast | — | $0.060 | $0.180 | $0.012 | — | $0.150 | cheapest | 262k | src |
| Nemotron 3 Nano 30B A3B | — | $0.050 | $0.200 | — | — | $0.163 | cheapest | 262k | src |
| Nous Hermes Llama2 13B | — | $0.170 | $0.170 | — | — | $0.170 | cheapest | 4k | src |
| Openhermes2.5 Mistral 7B | — | $0.170 | $0.170 | — | — | $0.170 | cheapest | 4k | src |
| Gemma 3 27B | — | $0.119 | $0.200 | — | — | $0.180 | cheapest | 98k | src |
| OpenAI GPT OSS 120B | — | $0.050 | $0.250 | — | — | $0.200 | cheapest | 131k | src |
| GLM 5.3 Flash | — | $0.075 | $0.250 | $0.015 | — | $0.206 | +50% vs OpenRouter | 1.0M | src |
| Qwen3 Coder 30b A3B Instruct | — | $0.070 | $0.270 | — | — | $0.220 | cheapest | 160k | src |
| ERNIE 4.5 21B A3B | — | $0.070 | $0.280 | — | — | $0.228 | cheapest | 120k | src |
| ERNIE-4.5-21B-A3B-Thinking | — | $0.070 | $0.280 | — | — | $0.228 | cheapest | 131k | src |
| Deepseek V4 Flash | — | $0.140 | $0.280 | $0.028 | — | $0.245 | cheapest | 1.0M | src |
| Ling-2.6-flash | — | $0.100 | $0.300 | $0.020 | — | $0.250 | cheapest | 262k | src |
| Ling-2.6-flash | — | $0.100 | $0.300 | $0.020 | — | $0.250 | cheapest | 262k | src |
| XiaomiMiMo/MiMo-V2-Flash | — | $0.110 | $0.330 | $0.024 | — | $0.275 | cheapest | 262k | src |
| XiaomiMiMo/MiMo-V2.5 | — | $0.168 | $0.336 | $0.0034 | — | $0.294 | cheapest | 1.0M | src |
| DeepSeek R1 Distill Qwen 32B | — | $0.300 | $0.300 | — | — | $0.300 | cheapest | 64k | src |
| GLM-4.7-Flash | — | $0.070 | $0.400 | $0.010 | — | $0.318 | +1% vs DeepInfra | 200k | src |
| Gemma 4 26B A4B | — | $0.130 | $0.400 | — | — | $0.333 | cheapest | 262k | src |
| Llama 3.3 70B Instruct | — | $0.135 | $0.400 | — | — | $0.334 | cheapest | 12k | src |
| Gemma 4 31B | — | $0.140 | $0.400 | — | — | $0.335 | +21% vs OpenRouter | 262k | src |
| Qwen3 30B A3B | — | $0.090 | $0.450 | — | — | $0.360 | cheapest | 41k | src |
| Qwen3 32B | — | $0.100 | $0.450 | — | — | $0.362 | +58% vs OpenRouter | 41k | src |
| Deepseek V3.2 | — | $0.269 | $0.400 | $0.135 | — | $0.367 | cheapest | 164k | src |
| Deepseek V3.2 Exp | — | $0.270 | $0.410 | — | — | $0.375 | cheapest | 164k | src |
| ERNIE-4.5-VL-28B-A3B-Thinking | — | $0.390 | $0.390 | — | — | $0.390 | cheapest | 131k | src |
| Qwen3.8 Flash | — | $0.150 | $0.470 | $0.016 | — | $0.390 | cheapest | 1M | src |
| Qwen 2.5 72B Instruct | — | $0.380 | $0.400 | — | — | $0.395 | cheapest | 32k | src |
| qwen/qwen3-vl-8b-instruct | — | $0.080 | $0.500 | — | — | $0.395 | cheapest | 131k | src |
| Qwen 2 VL 72B Instruct | — | $0.450 | $0.450 | — | — | $0.450 | cheapest | 33k | src |
| ERNIE 4.5 VL 28B A3B | — | $0.140 | $0.560 | — | — | $0.455 | cheapest | 30k | src |
| Qwen3 235B A22B Instruct 2507 | — | $0.090 | $0.580 | — | — | $0.458 | +61% vs OpenRouter | 131k | src |
| Hy3 | — | $0.140 | $0.580 | $0.035 | — | $0.470 | +75% vs OpenRouter | 262k | src |
| Llama 4 Scout Instruct | — | $0.180 | $0.590 | — | — | $0.487 | cheapest | 131k | src |
| qwen/qwen3-vl-30b-a3b-instruct | — | $0.200 | $0.700 | — | — | $0.575 | cheapest | 131k | src |
| Wizardlm 2 8x22B | — | $0.620 | $0.620 | — | — | $0.620 | cheapest | 66k | src |
| Qwen MT Plus | — | $0.250 | $0.750 | — | — | $0.625 | cheapest | 16k | src |
| Qwen3 235B A22B | — | $0.200 | $0.800 | — | — | $0.650 | cheapest | 41k | src |
| zai-org/glm-4.5-air | — | $0.130 | $0.850 | $0.025 | — | $0.670 | cheapest | 131k | src |
| Llama3 70B Instruct | — | $0.510 | $0.740 | — | — | $0.682 | cheapest | 8k | src |
| Llama 4 Maverick Instruct | — | $0.270 | $0.850 | — | — | $0.705 | cheapest | 1.0M | src |
| GLM 4.6V | — | $0.300 | $0.900 | $0.055 | — | $0.750 | cheapest | 131k | src |
| Qwen3 Omni 30B A3B Instruct | — | $0.250 | $0.970 | — | — | $0.790 | cheapest | 66k | src |
| Qwen3 Omni 30B A3B Thinking | — | $0.250 | $0.970 | — | — | $0.790 | cheapest | 66k | src |
| DeepSeek R1 Distill LLama 70B | — | $0.800 | $0.800 | — | — | $0.800 | cheapest | 8k | src |
| qwen/qwen3-vl-30b-a3b-thinking | — | $0.200 | $1.00 | — | — | $0.800 | cheapest | 131k | src |
| Qwen2.5 VL 72B Instruct | — | $0.800 | $0.800 | — | — | $0.800 | +28% vs OpenRouter | 33k | src |
| DeepSeek V3.1 | — | $0.270 | $1.00 | $0.135 | — | $0.818 | +5% vs Vercel AI Gateway | 131k | src |
| Deepseek V3.1 Terminus | — | $0.270 | $1.00 | $0.135 | — | $0.818 | cheapest | 131k | src |
| DeepSeek V3 | — | $0.890 | $0.890 | — | — | $0.890 | +6% vs OpenRouter | 64k | src |
| DeepSeek V3 | — | $0.890 | $0.890 | — | — | $0.890 | +6% vs OpenRouter | 64k | src |
| ERNIE 4.5 300B A47B | — | $0.280 | $1.10 | — | — | $0.895 | cheapest | 123k | src |
| DeepSeek V3 0324 | — | $0.270 | $1.12 | $0.135 | — | $0.907 | +12% vs OpenRouter | 164k | src |
| Step 3.7 Flash | — | $0.200 | $1.15 | $0.040 | — | $0.912 | cheapest | 262k | src |
| XiaomiMiMo/MiMo-V2.5-Pro | — | $0.522 | $1.04 | $0.0043 | — | $0.913 | cheapest | 1.0M | src |
| CoBuddy | — | $0.280 | $1.13 | $0.070 | — | $0.917 | cheapest | 131k | src |
| Kat Coder Pro | — | $0.300 | $1.20 | $0.060 | — | $0.975 | cheapest | 256k | src |
| Minimax M2.1 | — | $0.300 | $1.20 | $0.030 | — | $0.975 | cheapest | 205k | src |
| MiniMax M2.5 | — | $0.300 | $1.20 | $0.030 | — | $0.975 | +11% vs OpenRouter | 205k | src |
| MiniMax M2.7 | — | $0.300 | $1.20 | $0.060 | — | $0.975 | cheapest | 205k | src |
| MiniMax M3 | — | $0.300 | $1.20 | $0.060 | — | $0.975 | cheapest | 1M | src |
| MiniMax-M2 | — | $0.300 | $1.20 | $0.030 | — | $0.975 | cheapest | 205k | src |
| ERNIE 4.5 VL 424B A47B | — | $0.420 | $1.25 | — | — | $1.04 | cheapest | 123k | src |
| DeepSeek V3 (Turbo) | — | $0.400 | $1.30 | — | — | $1.07 | cheapest | 64k | src |
| Deepseek V4 Flash 0731 | — | $0.440 | $1.32 | $0.028 | — | $1.10 | cheapest | 1.0M | src |
| DeepSeek V4 Flash Vision Exp | — | $0.440 | $1.32 | $0.028 | — | $1.10 | +100% vs Vercel AI Gateway | 1.0M | src |
| Qwen3 Next 80B A3B Instruct | — | $0.150 | $1.50 | — | — | $1.16 | +37% vs OpenRouter | 131k | src |
| Qwen3 Next 80B A3B Thinking | — | $0.150 | $1.50 | — | — | $1.16 | +24% vs Vercel AI Gateway | 131k | src |
| Qwen3 Coder Next | — | $0.200 | $1.50 | — | — | $1.18 | +87% vs OpenRouter | 262k | src |
| Qwen3.6-35B-A3B | — | $0.248 | $1.49 | — | — | $1.18 | +59% vs DeepInfra | 262k | src |
| Qwen3 VL 235B A22B Instruct | — | $0.300 | $1.50 | — | — | $1.20 | cheapest | 131k | src |
| Qwen3 Coder 480B A35B Instruct | — | $0.380 | $1.55 | — | — | $1.26 | cheapest | 262k | src |
| GLM-4-32B-0414 | — | $0.550 | $1.66 | — | — | $1.38 | cheapest | 32k | src |
| L3 70B Euryale V2.1 | — | $1.48 | $1.48 | — | — | $1.48 | cheapest | 8k | src |
| L31 70B Euryale V2.2 | — | $1.48 | $1.48 | — | — | $1.48 | cheapest | 8k | src |
| GLM 4.5V | — | $0.600 | $1.80 | $0.110 | — | $1.50 | cheapest | 66k | src |
| Qwen3.5-35B-A3B | — | $0.250 | $2.00 | — | — | $1.56 | +99% vs DeepInfra | 262k | src |
| GLM 4.6 | — | $0.550 | $2.20 | $0.110 | — | $1.79 | +26% vs OpenRouter | 205k | src |
| MiniMax M1 | — | $0.550 | $2.20 | — | — | $1.79 | cheapest | 1M | src |
| GLM-4.5 | — | $0.600 | $2.20 | $0.110 | — | $1.80 | cheapest | 131k | src |
| GLM-4.7 | — | $0.600 | $2.20 | $0.110 | — | $1.80 | +27% vs DeepInfra | 205k | src |
| GLM-4.7 | — | $0.600 | $2.20 | $0.110 | — | $1.80 | +27% vs DeepInfra | 205k | src |
| Kimi K2 Instruct | — | $0.570 | $2.30 | — | — | $1.87 | cheapest | 131k | src |
| Qwen3.5-27B | — | $0.300 | $2.40 | — | — | $1.88 | +54% vs OpenRouter | 262k | src |
| Ling-2.6-1T | — | $0.300 | $2.50 | $0.060 | — | $1.95 | cheapest | 262k | src |
| MiniMax M2.5-highspeed | — | $0.600 | $2.40 | $0.030 | — | $1.95 | cheapest | 205k | src |
| MiniMax M2.7-highspeed | — | $0.600 | $2.40 | $0.060 | — | $1.95 | cheapest | 205k | src |
| Ring-2.6-1T | — | $0.300 | $2.50 | $0.060 | — | $1.95 | cheapest | 262k | src |
| Kimi K2 0905 | — | $0.600 | $2.50 | — | — | $2.02 | cheapest | 262k | src |
| Kimi K2 Thinking | — | $0.600 | $2.50 | $0.150 | — | $2.02 | +25% vs Vercel AI Gateway | 262k | src |
| Deepseek Prover V2 671B | — | $0.700 | $2.50 | — | — | $2.05 | cheapest | 160k | src |
| DeepSeek R1 (Turbo) | — | $0.700 | $2.50 | — | — | $2.05 | cheapest | 64k | src |
| DeepSeek R1 0528 | — | $0.700 | $2.50 | $0.350 | — | $2.05 | cheapest | 164k | src |
| Macaron V1 Tall | — | $0.450 | $2.60 | $0.080 | — | $2.06 | cheapest | 262k | src |
| Qwen3 235B A22b Thinking 2507 | — | $0.300 | $3.00 | — | — | $2.33 | cheapest | 131k | src |
| Qwen3.8 27B | — | $0.420 | $3.00 | $0.085 | — | $2.35 | +18% vs OpenRouter | 1M | src |
| Kimi K2.5 | — | $0.600 | $3.00 | $0.100 | — | $2.40 | cheapest | 262k | src |
| Qwen3.5-122B-A10B | — | $0.400 | $3.20 | — | — | $2.50 | +34% vs DeepInfra | 262k | src |
| GLM-5 | — | $1.00 | $3.20 | $0.200 | — | $2.65 | +55% vs DeepInfra | 203k | src |
| Kimi K2.6 | — | $0.800 | $3.40 | $0.160 | — | $2.75 | cheapest | 262k | src |
| Deepseek V4 Pro | — | $1.60 | $3.20 | $0.135 | — | $2.80 | cheapest | 1.0M | src |
| Qwen3.5-397B-A17B | — | $0.600 | $3.60 | — | — | $2.85 | +21% vs DeepInfra | 262k | src |
| Qwen3.6-27B | — | $0.600 | $3.60 | — | — | $2.85 | +15% vs DeepInfra | 262k | src |
| Qwen3.7-Max | — | $1.25 | $3.75 | $0.250 | — | $3.13 | cheapest | 1M | src |
| Qwen3 VL 235B A22B Thinking | — | $0.980 | $3.95 | — | — | $3.21 | +3% vs Vercel AI Gateway | 131k | src |
| Kimi K2.7 Code | — | $0.950 | $4.00 | $0.190 | — | $3.24 | +19% vs OpenRouter | 262k | src |
| DeepSeek V4 Pro 0813 | — | $1.32 | $3.96 | $0.132 | — | $3.30 | +128% vs OpenRouter | 1.0M | src |
| GLM-5-Turbo | — | $1.20 | $4.00 | $0.240 | — | $3.30 | cheapest | 203k | src |
| GLM-5V-Turbo | — | $1.20 | $4.00 | $0.240 | — | $3.30 | cheapest | 205k | src |
| GLM-5.1 | — | $1.38 | $4.40 | $0.260 | — | $3.65 | +26% vs DeepInfra | 205k | src |
| GLM 5.2 | — | $1.40 | $4.40 | $0.260 | — | $3.65 | +73% vs Vercel AI Gateway | 1.0M | src |
| GLM 5.3 | — | $1.40 | $4.40 | $0.260 | — | $3.65 | +11% vs OpenRouter | 1.0M | src |
| Macaron V1 Venti | — | $1.50 | $4.50 | $0.300 | — | $3.75 | cheapest | 1.0M | src |
| DeepSeek R1 | — | $4.00 | $4.00 | — | — | $4.00 | cheapest | 64k | src |
| Qwen3.8 2.4T A95B | — | $2.00 | $6.00 | $0.250 | — | $5.00 | cheapest | 1M | src |
| Qwen3.8 Max | — | $2.00 | $6.00 | $0.250 | — | $5.00 | cheapest | 1M | src |
| XiaomiMiMo/MiMo-V2-Pro | — | $2.00 | $6.00 | $0.400 | — | $5.00 | cheapest | 1.0M | src |
| Qwen3 Max | — | $2.11 | $8.45 | — | — | $6.87 | +120% vs OpenRouter | 262k | src |
| Kimi K3 | — | $3.00 | $15.00 | $0.300 | — | $12.00 | cheapest | 1.0M | src |
created by: @dunder_bird