Models & pricing
Every open-weight model available through the gateway, with final prices.
Prices are per 1M tokens, all-inclusive, and billed from your prepaid credits — no subscriptions, no minimums. Add credits →
| Model | Context | Input | Output |
|---|---|---|---|
| cognitivecomputations/dolphin-mistral-24b-venice-edition | 128k | $0.260 | $1.17 |
| deepseek/deepseek-chat | 164k | $0.335 | $1.34 |
| deepseek/deepseek-chat-v3-0324 | 164k | $0.377 | $1.48 |
| deepseek/deepseek-chat-v3.1 | 164k | $0.325 | $1.23 |
| deepseek/deepseek-r1-0528 | 164k | $0.650 | $2.80 |
| deepseek/deepseek-v3.1-terminus | 164k | $0.351 | $1.30 |
| deepseek/deepseek-v3.2 | 164k | $0.364 | $0.546 |
| deepseek/deepseek-v3.2-exp | 164k | $0.351 | $0.533 |
| deepseek/deepseek-v4-flash | 1.048576M | $0.118 | $0.237 |
| deepseek/deepseek-v4-flash-0731 | 1.048576M | $0.572 | $1.72 |
| deepseek/deepseek-v4-flash-vision-exp | 1.048576M | $0.280 | $0.841 |
| deepseek/deepseek-v4-pro | 1.048576M | $1.24 | $2.48 |
| deepseek/deepseek-v4-pro-0813 | 1.048576M | $0.858 | $2.57 |
| deepseek/deepseek-v4.1-flash | 1.048576M | $0.073 | $0.156 |
| deepseek/deepseek-v4.1-flash-1017 | 1.048576M | $0.390 | $1.56 |
| google/gemma-2-27b-it | 8k | $0.845 | $0.845 |
| google/gemma-3-12b-it | 131k | $0.065 | $0.195 |
| google/gemma-3-27b-it | 131k | $0.104 | $0.455 |
| google/gemma-3-4b-it | 131k | $0.052 | $0.065 |
| google/gemma-4-26b-a4b-it | 262k | $0.117 | $0.390 |
| google/gemma-4-31b-it | 262k | $0.260 | $0.520 |
| gryphe/mythomax-l2-13b | 8k | $0.104 | $0.143 |
| meta-llama/llama-3.1-70b-instruct | 131k | $0.520 | $0.520 |
| meta-llama/llama-3.1-8b-instruct | 131k | $0.065 | $0.104 |
| meta-llama/llama-3.2-1b-instruct | 60k | $0.035 | $0.261 |
| meta-llama/llama-3.2-3b-instruct | 131k | $0.066 | $0.436 |
| meta-llama/llama-3.3-70b-instruct | 131k | $0.130 | $0.416 |
| meta-llama/llama-4-maverick | 524k | $0.244 | $0.848 |
| meta-llama/llama-4-scout | 1.31072M | $0.130 | $0.390 |
| meta-llama/llama-guard-4-12b | 164k | $0.234 | $0.234 |
| microsoft/phi-4 | 16k | $0.091 | $0.182 |
| mistralai/codestral-2508 | 256k | $0.390 | $1.17 |
| mistralai/devstral-2512 | 262k | $0.520 | $2.60 |
| mistralai/ministral-14b-2512 | 262k | $0.260 | $0.260 |
| mistralai/ministral-3b-2512 | 131k | $0.130 | $0.130 |
| mistralai/ministral-8b-2512 | 262k | $0.195 | $0.195 |
| mistralai/mistral-large | 128k | $2.60 | $7.80 |
| mistralai/mistral-large-2407 | 131k | $2.60 | $7.80 |
| mistralai/mistral-large-2512 | 262k | $0.650 | $1.95 |
| mistralai/mistral-large-4-0 | 1.048576M | $0.884 | $2.72 |
| mistralai/mistral-medium-3 | 131k | $0.520 | $2.60 |
| mistralai/mistral-medium-3-5 | 262k | $1.95 | $9.75 |
| mistralai/mistral-medium-3.1 | 131k | $0.520 | $2.60 |
| mistralai/mistral-nemo | 131k | $0.038 | $0.039 |
| mistralai/mistral-saba | 33k | $0.260 | $0.780 |
| mistralai/mistral-small-24b-instruct-2501 | 33k | $0.065 | $0.104 |
| mistralai/mistral-small-2603 | 262k | $0.195 | $0.780 |
| mistralai/mistral-small-3.1-24b-instruct | 128k | $0.456 | $0.721 |
| mistralai/mistral-small-3.2-24b-instruct | 256k | $0.122 | $0.325 |
| mistralai/mixtral-8x22b-instruct | 66k | $2.60 | $7.80 |
| mistralai/voxtral-small-24b-2507 | 33k | $0.130 | $0.390 |
| moonshotai/kimi-k2 | 131k | $0.741 | $2.99 |
| moonshotai/kimi-k2-0905 | 262k | $0.780 | $3.25 |
| moonshotai/kimi-k2-thinking | 262k | $0.780 | $3.25 |
| moonshotai/kimi-k2.5 | 262k | $0.650 | $3.25 |
| moonshotai/kimi-k2.6 | 262k | $0.845 | $4.43 |
| moonshotai/kimi-k2.7-code | 262k | $0.873 | $4.36 |
| moonshotai/kimi-k3 | 1.048576M | $0.311 | $15.5 |
| nousresearch/hermes-3-llama-3.1-405b | 131k | $1.30 | $1.30 |
| nousresearch/hermes-3-llama-3.1-70b | 131k | $0.910 | $0.910 |
| nousresearch/hermes-4-405b | 131k | $1.30 | $3.90 |
| nvidia/nemotron-3-nano-30b-a3b | 262k | $0.078 | $0.312 |
| nvidia/nemotron-3-super-120b-a12b | 262k | $0.104 | $0.585 |
| nvidia/nemotron-3-ultra-550b-a55b | 262k | $0.780 | $3.12 |
| nvidia/nemotron-3.5-content-safety | 131k | $0.260 | $0.260 |
| nvidia/nemotron-3.5-lightning | 262k | $0.091 | $0.260 |
| nvidia/nemotron-3.5-super-vl | 1.048576M | $0.195 | $0.650 |
| nvidia/switchyard | 1M | $-1300000.000 | $-1300000.000 |
| qwen/qwen-2.5-72b-instruct | 33k | $0.468 | $0.520 |
| qwen/qwen-2.5-7b-instruct | 33k | $0.130 | $0.260 |
| qwen/qwen-2.5-coder-32b-instruct | 33k | $0.858 | $1.30 |
| qwen/qwen-plus | 1M | $0.338 | $1.01 |
| qwen/qwen2.5-vl-72b-instruct | 128k | $1.04 | $1.30 |
| qwen/qwen3-14b | 41k | $0.156 | $0.312 |
| qwen/qwen3-235b-a22b-2507 | 262k | $0.117 | $0.715 |
| qwen/qwen3-235b-a22b-thinking-2507 | 128k | $0.585 | $4.55 |
| qwen/qwen3-30b-a3b | 41k | $0.156 | $0.650 |
| qwen/qwen3-30b-a3b-instruct-2507 | 262k | $0.117 | $0.390 |
| qwen/qwen3-32b | 131k | $0.104 | $0.364 |
| qwen/qwen3-coder | 262k | $0.390 | $1.30 |
| qwen/qwen3-coder-30b-a3b-instruct | 262k | $0.091 | $0.364 |
| qwen/qwen3-coder-flash | 1M | $0.254 | $1.27 |
| qwen/qwen3-coder-next | 262k | $0.156 | $1.04 |
| qwen/qwen3-next-80b-a3b-instruct | 262k | $0.117 | $1.43 |
| qwen/qwen3-next-80b-a3b-thinking | 262k | $0.195 | $1.56 |
| qwen/qwen3-vl-235b-a22b-instruct | 262k | $0.273 | $2.47 |
| qwen/qwen3-vl-30b-a3b-instruct | 262k | $0.195 | $0.780 |
| qwen/qwen3-vl-30b-a3b-thinking | 262k | $0.377 | $1.30 |
| qwen/qwen3-vl-8b-instruct | 262k | $0.325 | $0.975 |
| qwen/qwen3.5-122b-a10b | 262k | $0.338 | $2.70 |
| qwen/qwen3.5-27b | 262k | $0.351 | $2.81 |
| qwen/qwen3.5-35b-a3b | 262k | $0.195 | $1.30 |
| qwen/qwen3.5-397b-a17b | 262k | $0.507 | $3.04 |
| qwen/qwen3.5-9b | 262k | $0.130 | $0.195 |
| qwen/qwen3.5-flash-02-23 | 1M | $0.085 | $0.338 |
| qwen/qwen3.5-plus-02-15 | 1M | $0.338 | $2.03 |
| qwen/qwen3.5-plus-20260420 | 1M | $0.390 | $2.34 |
| qwen/qwen3.6-27b | 262k | $0.325 | $2.60 |
| qwen/qwen3.6-35b-a3b | 262k | $0.130 | $1.23 |
| qwen/qwen3.6-flash | 1M | $0.244 | $1.46 |
| qwen/qwen3.6-plus | 1M | $0.423 | $2.54 |
| qwen/qwen3.7-flash | 1M | $0.039 | $0.169 |
| qwen/qwen3.7-max | 1M | $1.92 | $5.75 |
| qwen/qwen3.7-plus | 1M | $0.416 | $1.66 |
| qwen/qwen3.8-2.4t-a95b | 1.048576M | $2.60 | $7.80 |
| qwen/qwen3.8-27b | 1M | $0.052 | $1.76 |
| qwen/qwen3.8-flash | 1M | $0.195 | $0.611 |
| qwen/qwen3.8-max-0902 | 1M | $2.60 | $7.80 |
| qwen/qwen3.8-max-prime | 1M | $5.20 | $15.6 |
| qwen/qwen3.8-omni-flash | 1M | $0.195 | $0.611 |
| z-ai/glm-4.5 | 131k | $0.780 | $2.86 |
| z-ai/glm-4.5-air | 131k | $0.169 | $1.10 |
| z-ai/glm-4.5v | 66k | $0.780 | $2.34 |
| z-ai/glm-4.6 | 205k | $0.715 | $2.86 |
| z-ai/glm-4.6v | 131k | $0.390 | $1.17 |
| z-ai/glm-4.7 | 205k | $0.702 | $2.57 |
| z-ai/glm-4.7-flash | 200k | $0.079 | $0.520 |
| z-ai/glm-5 | 205k | $0.780 | $2.50 |
| z-ai/glm-5-turbo | 203k | $1.56 | $5.20 |
| z-ai/glm-5.1 | 205k | $1.26 | $3.95 |
| z-ai/glm-5.2 | 1.048576M | $0.806 | $3.15 |
| z-ai/glm-5.3 | 1.048576M | $0.103 | $1.82 |
| z-ai/glm-5.3-flash | 1.048576M | $0.061 | $0.208 |
| z-ai/glm-5.3-flashx | 1.048576M | $0.481 | $1.63 |
| z-ai/glm-5.3-prime | 1M | $3.64 | $11.4 |
| z-ai/glm-5v-turbo | 203k | $1.56 | $5.20 |
Prices per 1M tokens · 126 models