inspired by: gputable.dev · Brandon @burcs
ModelTable - LLM prices · all providers
20 rows. Prices USD / 1M tokens.
| Model | Via | $/M in | $/M out | Cache R | Cache W | Blend | vs cheapest | Ctx | |
|---|---|---|---|---|---|---|---|---|---|
| Ternary Bonsai 27B | — | free | free | — | — | free | — | 262k | src |
| GPT-OSS 20B | — | $0.050 | $0.200 | — | — | $0.163 | cheapest | 128k | src |
| Qwen3.5 9B | — | $0.170 | $0.250 | — | — | $0.230 | cheapest | 262k | src |
| DeepSeek-V4-Flash-0731 | — | $0.140 | $0.280 | $0.030 | — | $0.245 | +58% vs DeepInfra | 1M | src |
| GLM-5.3 Flash | — | $0.150 | $0.500 | $0.030 | — | $0.412 | cheapest | 1M | src |
| GPT-OSS 120B | — | $0.150 | $0.600 | — | — | $0.487 | cheapest | 128k | src |
| Gemma 4 31B Instruct | — | $0.390 | $0.970 | — | — | $0.825 | cheapest | 262k | src |
| Minimax M3 | — | $0.300 | $1.20 | $0.060 | — | $0.975 | cheapest | 524k | src |
| Inkling Small | — | $0.500 | $1.20 | — | — | $1.02 | +1% vs OpenRouter | 524k | src |
| Llama 3.3 70B Instruct Turbo | — | $1.04 | $1.04 | — | — | $1.04 | cheapest | 131k | src |
| Qwen3.7 Plus | — | $0.320 | $1.28 | — | — | $1.04 | cheapest | 1M | src |
| Muse Glimmer 30B | — | $0.350 | $1.50 | $0.040 | — | $1.21 | +35% vs OpenRouter | 131k | src |
| Qwen3.6 Plus | — | $0.500 | $3.00 | — | — | $2.38 | +54% vs OpenRouter | 1M | src |
| Inkling | — | $1.00 | $4.05 | $0.170 | — | $3.29 | +0% vs DeepInfra | 524k | src |
| DeepSeek V4 Pro 0813 | — | $1.32 | $3.96 | $0.130 | — | $3.30 | +128% vs OpenRouter | 1.0M | src |
| GLM-5.2 | — | $1.40 | $4.40 | $0.260 | — | $3.65 | +84% vs DeepInfra | 1M | src |
| GLM-5.3 | — | $1.40 | $4.40 | $0.260 | — | $3.65 | +11% vs DeepInfra | 1M | src |
| Qwen3.8-2.4T-A95B | — | $2.50 | $6.25 | $0.500 | — | $5.31 | +6% vs DeepInfra | src | |
| Qwen3.7 Max | — | $2.50 | $7.50 | — | — | $6.25 | +69% vs OpenRouter | 1M | src |
| Kimi K3 | — | $3.00 | $15.00 | $0.300 | — | $12.00 | 0% vs Novita | 1.0M | src |
created by: @dunder_bird