Models

68 models · prices per 1M tokens

• baai/bge-m3 — input $0.010/1M, output $0.000/1M, 8K context
• baai/bge-reranker-v2-m3 — input $0.010/1M, output $0.000/1M, 8K context
• baidu/ernie-4.5-vl — input $0.420/1M, output $1.25/1M, 131K context
• black-forest-labs/flux-2-dev — input $0.000/1M, output $0.000/1M
• black-forest-labs/flux-2-flex — input $0.000/1M, output $0.000/1M
• black-forest-labs/flux-2-max — input $0.000/1M, output $0.000/1M
• black-forest-labs/flux-2-pro — input $0.000/1M, output $0.000/1M
• bytedance/seed-1.6 — input $0.300/1M, output $2.00/1M, 262K context
• bytedance/seed-1.6-flash — input $0.080/1M, output $0.300/1M, 262K context
• deepseek/deepseek-r1-0528 — input $0.500/1M, output $2.18/1M, 131K context
• deepseek/deepseek-v3-0324 — input $0.250/1M, output $1.00/1M, 131K context
• deepseek/deepseek-v3.1 — input $0.270/1M, output $1.00/1M, 131K context
• deepseek/deepseek-v3.2 — input $0.260/1M, output $0.380/1M, 131K context
• deepseek/deepseek-v4-flash — input $0.140/1M, output $0.280/1M, 1000K context
• deepseek/deepseek-v4-flash-0731 — input $0.440/1M, output $1.32/1M, 1000K context
• deepseek/deepseek-v4-flash-vision-exp — input $0.440/1M, output $1.32/1M, 1000K context
• deepseek/deepseek-v4-pro — input $1.74/1M, output $3.48/1M, 1000K context
• deepseek/deepseek-v4-pro-0813 — input $1.32/1M, output $3.96/1M, 1000K context
• deepseek/deepseek-v4.1-flash — input $0.150/1M, output $1.20/1M
• google/flash-image-2.5 — input $0.000/1M, output $0.000/1M
• google/gemma-3-12b-it — input $0.060/1M, output $0.200/1M, 131K context
• google/gemma-3-27b-it — input $0.090/1M, output $0.160/1M, 131K context
• meta/llama-4-scout — input $0.180/1M, output $0.590/1M, 10000K context
• minimax/minimax-m1 — input $0.550/1M, output $2.20/1M, 1000K context
• minimax/minimax-m2 — input $0.300/1M, output $1.20/1M, 205K context
• minimax/minimax-m2.1 — input $0.300/1M, output $1.20/1M, 205K context
• minimax/minimax-m2.5 — input $0.300/1M, output $1.20/1M, 205K context
• minimax/minimax-m3 — input $0.600/1M, output $2.40/1M, 1000K context
• mistral/devstral-2-123b — input $0.050/1M, output $0.220/1M, 262K context
• mistral/ministral-3-14b — input $0.200/1M, output $0.200/1M, 131K context
• mistral/ministral-3-3b — input $0.100/1M, output $0.100/1M, 131K context
• mistral/ministral-3-8b — input $0.150/1M, output $0.150/1M, 131K context
• mistral/mistral-large-3-675b — input $0.500/1M, output $1.50/1M, 262K context
• mistral/mistral-small-4-119b — input $0.150/1M, output $0.600/1M, 262K context
• moonshot/kimi-k2.5 — input $0.600/1M, output $3.00/1M, 262K context
• moonshot/kimi-k2.6 — input $0.950/1M, output $4.00/1M, 262K context
• moonshot/kimi-k2.7-code — input $0.950/1M, output $4.00/1M, 262K context
• moonshot/kimi-k2.7-code-highspeed — input $1.90/1M, output $8.00/1M, 262K context
• moonshot/kimi-k3 — input $3.00/1M, output $15.00/1M, 1000K context
• nvidia/nemotron-3-embed-1b — input $0.010/1M, output $0.000/1M, 8K context
• nvidia/nemotron-3-embed-8b — input $0.030/1M, output $0.000/1M, 8K context
• nvidia/nemotron-3-super — input $0.200/1M, output $0.800/1M, 1000K context
• nvidia/nemotron-3-ultra — input $0.800/1M, output $2.60/1M, 1000K context
• nvidia/nemotron-3.5-lightning — input $0.100/1M, output $0.950/1M, 262K context
• openai/gpt-oss-20b — input $0.040/1M, output $0.200/1M, 131K context
• qwen/qwen3-235b — input $0.200/1M, output $0.600/1M, 131K context
• qwen/qwen3-30b — input $0.090/1M, output $0.300/1M, 262K context
• qwen/qwen3-coder-plus — input $1.40/1M, output $5.00/1M, 262K context
• qwen/qwen3-max — input $1.60/1M, output $6.40/1M, 262K context
• qwen/qwen3-next-80b — input $0.140/1M, output $1.40/1M, 262K context
• qwen/qwen3-vl-235b — input $0.220/1M, output $0.880/1M, 262K context
• qwen/qwen3-vl-32b — input $0.500/1M, output $1.50/1M, 262K context
• qwen/qwen3.5-397b — input $0.600/1M, output $3.55/1M, 262K context
• qwen/qwen3.8-2.4t — input $1.90/1M, output $5.70/1M, 262K context
• qwen/qwen3.8-27b — input $0.350/1M, output $2.75/1M, 262K context
• tencent/hy-mt2-lite — input $0.044/1M, output $0.177/1M, 8K context
• tencent/hy-mt2-plus — input $0.074/1M, output $0.295/1M, 8K context
• tencent/hy-mt2-pro — input $0.074/1M, output $0.295/1M, 8K context
• tencent/hy3 — input $0.132/1M, output $0.528/1M, 262K context
• xiaomi/mimo-v2.5-pro — input $0.435/1M, output $0.870/1M, 1000K context
• zhipu/glm-4.5v — input $0.600/1M, output $1.80/1M, 66K context
• zhipu/glm-4.6v — input $0.300/1M, output $0.900/1M, 131K context
• zhipu/glm-4.7 — input $0.450/1M, output $2.00/1M, 131K context
• zhipu/glm-5 — input $0.800/1M, output $2.55/1M, 205K context
• zhipu/glm-5.1 — input $1.26/1M, output $3.96/1M, 205K context
• zhipu/glm-5.2 — input $1.40/1M, output $4.40/1M, 1000K context
• zhipu/glm-5.3 — input $1.40/1M, output $4.40/1M, 1049K context
• zhipu/glm-5.3-flash — input $0.150/1M, output $0.500/1M, 1049K context