# OpenRouter API pricing and models

OpenRouter publishes per-token prices for 422 text models, plus 19 free variants, as of October 20, 2026. The lowest output rate is $0.03 per million tokens, on Mistral Nemo, and the highest-scoring model it serves is Claude Opus 5, at 88 on our 100-point score.

OpenRouter is a router, not a host: one API key reaches models served by many providers, and it bills the provider’s rate plus a fee when you buy credits.

Source: [OpenRouter model catalog (public API)](https://openrouter.ai/models), read 2026-10-20. Prices in US dollars per million tokens.

## Models we score

| Model | Score | Input | Output | Cached input | Context | vs maker |
|---|---|---|---|---|---|---|
| Claude Opus 5 (`anthropic/claude-opus-5`) | 88 | $5.00 | $25.00 | $0.50 | 1M | Same |
| GPT-6 Astra (`openai/gpt-6-astra`) | 85 | $10.00 | $50.00 | $1.00 | 1.05M | Same |
| Claude Sonnet 5.5 (`anthropic/claude-sonnet-5.5`) | 83 | $2.00 | $10.00 | $0.10 | 1M | Same |
| Claude Fable 5 (`anthropic/claude-fable-5`) | 83 | $10.00 | $50.00 | $1.00 | 1M | Same |
| GPT-6.1 Sol (`openai/gpt-6.1-sol`) | 82 | $2.00 | $10.00 | $0.10 | 1.05M | Same |
| Claude Opus 5.5 (`anthropic/claude-opus-5.5`) | 82 | $4.00 | $20.00 | $0.20 | 1M | Same |
| Claude Fable 5.1 (`anthropic/claude-fable-5.1`) | 80 | $10.00 | $50.00 | $0.25 | 1M | Same |
| Kimi K3 (`moonshotai/kimi-k3`) | 79 | $0.24 | $11.94 | $0.21 | 1.05M | -20% |
| GPT-5.6 Sol (`openai/gpt-5.6-sol`) | 79 | $4.00 | $20.00 | $0.40 | 1.05M | Same |
| Gemini 4 Argon (`google/gemini-4-argon`) | 78 | $2.00 | $10.00 | $0.10 | 1.05M | Same |
| GPT-5.5 Pro (`openai/gpt-5.5-pro`) | 78 | $30.00 | $180.00 | — | 1.05M | Same |
| Step 5 Preview (`stepfun/step-5-preview`) | 77 | $1.00 | $2.70 | $0.10 | 1.05M | Same |
| Gemini 3.7 Flash (`google/gemini-3.7-flash`) | 77 | $0.75 | $3.75 | $0.075 | 1.05M | Same |
| Gemini 3.8 Flash (`google/gemini-3.8-flash`) | 77 | $0.82 | $4.13 | $0.083 | 1.05M | +10% |
| Claude Opus 4.8 (`anthropic/claude-opus-4.8`) | 77 | $5.00 | $25.00 | $0.50 | 1M | Same |
| Fugu Ultra (`sakana/fugu-ultra`) | 77 | $5.00 | $30.00 | $0.50 | 1M | — |
| GPT-5.4 Pro (`openai/gpt-5.4-pro`) | 77 | $30.00 | $180.00 | — | 1.05M | Same |
| Qwen3.7 Max (`qwen/qwen3.7-max`) | 76 | $1.48 | $4.42 | $0.29 | 1M | — |
| Claude Sonnet 5 (`anthropic/claude-sonnet-5`) | 76 | $2.00 | $10.00 | $0.20 | 1M | Same |
| GPT-6 Sol (`openai/gpt-6-sol`) | 76 | $2.00 | $10.00 | $0.20 | 1.05M | Same |
| GPT-5.6 Terra (`openai/gpt-5.6-terra`) | 75 | $2.00 | $12.00 | $0.20 | 1.05M | Same |
| GPT-5.2-Codex (`openai/gpt-5.2-codex`) | 75 | $1.75 | $14.00 | $0.17 | 400K | Same |
| GPT-5.3-Codex (`openai/gpt-5.3-codex`) | 75 | $1.75 | $14.00 | $0.17 | 400K | Same |
| MiniMax M3.1 Flash (free) (`minimax/minimax-m3.1-flash:free`) | 74 | $0 | $0 | — | 1M | — |
| Ling 3.1 Flash (`inclusionai/ling-3.1-flash`) | 74 | $0.075 | $0.23 | $0.015 | 262K | — |
| GPT-5.5 (`openai/gpt-5.5`) | 74 | $5.00 | $30.00 | $0.50 | 1.05M | Same |
| Dots3-Note Preview (free) (`dots-studio/dots-3-note-preview:free`) | 73 | $0 | $0 | — | 512K | — |
| DeepSeek V4.1 Flash (`deepseek/deepseek-v4.1-flash`) | 73 | $0.028 | $0.12 | $0.001 | 1.05M | -90% |
| DeepSeek V4.1 Flash 1017 (`deepseek/deepseek-v4.1-flash-1017`) | 73 | $0.15 | $0.60 | $0.003 | 1.05M | -50% |
| MiMo-V2.6-Pro (`xiaomi/mimo-v2.6-pro`) | 73 | $0.43 | $0.87 | $0.004 | 1.05M | Same |
| Qwen3.8 27B (`qwen/qwen3.8-27b`) | 73 | $0.04 | $1.35 | $0.018 | 1M | — |
| Gemini 3.6 Flash (`google/gemini-3.6-flash`) | 73 | $0.75 | $3.75 | $0.075 | 1.05M | Same |
| Muse Spark 1.1 (`meta/muse-spark-1.1`) | 73 | $1.25 | $4.25 | $0.15 | 1.05M | — |
| Hy4 preview (`tencent/hy4-preview`) | 72 | $0.75 | $2.25 | $0.038 | 1.05M | — |
| Muse Spark 1.2 (`meta/muse-spark-1.2`) | 72 | $1.25 | $4.25 | $0.15 | 1.05M | Same |
| Muse Spark 1.3 (`meta/muse-spark-1.3`) | 72 | $1.25 | $4.25 | $0.15 | 1.05M | Same |
| Muse Spark Open (`meta/muse-spark-open`) | 72 | $1.25 | $4.25 | $0.15 | 1.05M | — |
| GPT-5.1 (`openai/gpt-5.1`) | 72 | $1.25 | $10.00 | $0.13 | 400K | Same |
| Qwen3.7 Plus (`qwen/qwen3.7-plus`) | 71 | $0.32 | $1.28 | $0.064 | 1M | — |
| Grok 4.6 (`x-ai/grok-4.6`) | 71 | $2.00 | $6.00 | $0.50 | 500K | Same |
| Gemini 3.1 Pro Preview (`google/gemini-3.1-pro-preview`) | 71 | $2.00 | $12.00 | $0.20 | 1.05M | Same |
| Gemini 3.5 Flash (`google/gemini-3.5-flash`) | 70 | $1.50 | $9.00 | $0.15 | 1.05M | Same |
| GPT-5.1-Codex (`openai/gpt-5.1-codex`) | 70 | $1.25 | $10.00 | $0.13 | 400K | Same |
| GPT-5.4 (`openai/gpt-5.4`) | 70 | $2.50 | $15.00 | $0.25 | 1.05M | Same |
| Muse Wonder (`meta/muse-wonder`) | 70 | $4.00 | $20.00 | $0.20 | 1.05M | Same |
| GLM 5.3 Flash (`z-ai/glm-5.3-flash`) | 69 | $0.047 | $0.12 | $0.006 | 1.05M | — |
| MiMo-V2.6-Flash (`xiaomi/mimo-v2.6-flash`) | 69 | $0.14 | $0.28 | $0.003 | 1.05M | Same |
| Qwen3.8 Omni Flash (`qwen/qwen3.8-omni-flash`) | 69 | $0.15 | $0.47 | $0.016 | 1M | — |
| DeepSeek V4 Pro 0813 (`deepseek/deepseek-v4-pro-0813`) | 69 | $0.66 | $1.98 | $0.022 | 1.05M | -50% |
| Gemini 3 Flash Preview (`google/gemini-3-flash-preview`) | 69 | $0.50 | $3.00 | $0.05 | 1.05M | Same |
| Grok 4.5 (`x-ai/grok-4.5`) | 69 | $2.00 | $6.00 | $0.30 | 500K | Same |
| GPT-6 Luna (`openai/gpt-6-luna`) | 68 | $0.10 | $0.50 | $0.01 | 1.05M | Same |
| MiMo-V2.5-Pro (`xiaomi/mimo-v2.5-pro`) | 68 | $0.43 | $0.87 | $0.004 | 1.05M | — |
| Beam 1.0 501B A23B (`reflection/beam-1.0-501b-a23b`) | 68 | $0.30 | $1.00 | $0.04 | 1.05M | — |
| GLM 5.3 (`z-ai/glm-5.3`) | 68 | $0.079 | $1.40 | $0.078 | 1.05M | — |
| Qwen3.6 Plus (`qwen/qwen3.6-plus`) | 68 | $0.33 | $1.95 | — | 1M | — |
| Grok 4.3 (`x-ai/grok-4.3`) | 68 | $1.25 | $2.50 | $0.20 | 1M | Same |
| Mistral Large 4 (`mistralai/mistral-large-4-0`) | 68 | $1.36 | $4.18 | $0.14 | 1.05M | +100% |
| Inkling (free) (`thinkingmachines/inkling:free`) | 67 | $0 | $0 | — | 1.05M | — |
| Hy3 (`tencent/hy3`) | 67 | $0.083 | $0.33 | $0.021 | 262K | — |
| GPT-5.6 Luna (`openai/gpt-5.6-luna`) | 67 | $0.20 | $1.20 | $0.02 | 1.05M | Same |
| Kimi K2.6 (`moonshotai/kimi-k2.6`) | 67 | $0.65 | $3.41 | $0.15 | 262K | -15% |
| GLM 5 Turbo (`z-ai/glm-5-turbo`) | 67 | $1.20 | $4.00 | $0.24 | 203K | Same |
| Inkling (`thinkingmachines/inkling`) | 67 | $1.00 | $4.05 | $0.17 | 524K | -13% |
| o3 (`openai/o3`) | 67 | $2.00 | $8.00 | $0.50 | 200K | Same |
| Ling 3.0 Flash VL (`inclusionai/ling-3.0-flash-vl`) | 66 | $0.06 | $0.18 | $0.012 | 131K | — |
| Ternary Bonsai 2 27B (`prism-ml/ternary-bonsai-2-27b`) | 66 | $0.075 | $0.50 | $0.037 | 262K | — |
| GLM 5V Turbo (`z-ai/glm-5v-turbo`) | 66 | $1.20 | $4.00 | $0.24 | 203K | Same |
| MiniMax M3 (`minimax/minimax-m3`) | 65 | $0.30 | $1.20 | $0.06 | 1.05M | Same |
| GLM 5.2 (`z-ai/glm-5.2`) | 65 | $0.62 | $2.42 | $0.14 | 1.05M | -45% |
| Grok 4.7 (`x-ai/grok-4.7`) | 65 | $2.00 | $6.00 | $0.50 | 500K | Same |
| GPT-5.1-Codex-Max (`openai/gpt-5.1-codex-max`) | 65 | $1.25 | $10.00 | $0.13 | 400K | Same |
| Claude Opus 4.6 (`anthropic/claude-opus-4.6`) | 65 | $5.00 | $25.00 | $0.50 | 1M | Same |
| Inkling Small (free) (`thinkingmachines/inkling-small:free`) | 64 | $0 | $0 | — | 1.05M | — |
| Claude Haiku 5.5 (`anthropic/claude-haiku-5.5`) | 64 | $0.10 | $0.50 | $0.01 | 1M | Same |
| Inkling Small (`thinkingmachines/inkling-small`) | 64 | $0.45 | $1.20 | $0.10 | 524K | -17% |
| GLM 5.1 (`z-ai/glm-5.1`) | 64 | $0.97 | $3.04 | $0.18 | 205K | -31% |
| o4 Mini (`openai/o4-mini`) | 64 | $1.10 | $4.40 | $0.28 | 200K | Same |
| o1 (`openai/o1`) | 64 | $15.00 | $60.00 | $7.50 | 200K | Same |
| Step 3.5 Flash (`stepfun/step-3.5-flash`) | 63 | $0.10 | $0.30 | — | 262K | Same |
| Kimi K2.7 Code (`moonshotai/kimi-k2.7-code`) | 63 | $0.67 | $3.35 | $0.18 | 262K | -16% |
| Claude Sonnet 4.6 (`anthropic/claude-sonnet-4.6`) | 63 | $3.00 | $15.00 | $0.30 | 1M | Same |
| MiMo-V2.5 (`xiaomi/mimo-v2.5`) | 62 | $0.14 | $0.28 | $0.003 | 1.05M | — |
| DeepSeek V4 Flash 0731 (`deepseek/deepseek-v4-flash-0731`) | 62 | $0.13 | $0.39 | $0.004 | 1.05M | +39% |
| Step 3.7 Flash (`stepfun/step-3.7-flash`) | 62 | $0.20 | $1.15 | $0.04 | 262K | Same |
| Qwen3.6 27B (`qwen/qwen3.6-27b`) | 62 | $0.25 | $2.00 | $0.025 | 262K | — |
| Gemini 3.5 Flash Lite (`google/gemini-3.5-flash-lite`) | 62 | $0.30 | $2.50 | $0.03 | 1.05M | Same |
| GLM 5 (`z-ai/glm-5`) | 62 | $1.00 | $3.20 | $0.20 | 205K | Same |
| Qwen3.5-Flash (`qwen/qwen3.5-flash-02-23`) | 61 | $0.065 | $0.26 | — | 1M | -35% |
| Llama 3.3 70B Instruct (`meta-llama/llama-3.3-70b-instruct`) | 61 | $0.10 | $0.32 | — | 131K | — |
| DeepSeek V3.2 Exp (`deepseek/deepseek-v3.2-exp`) | 61 | $0.27 | $0.41 | — | 164K | -2% |
| DeepSeek V3.2 (`deepseek/deepseek-v3.2`) | 61 | $0.28 | $0.42 | $0.028 | 164K | Same |
| Muse Glimmer 30B (`meta/muse-glimmer-30b`) | 61 | $0.30 | $1.20 | $0.04 | 131K | — |
| Qwen3.5-122B-A10B (`qwen/qwen3.5-122b-a10b`) | 61 | $0.26 | $2.08 | — | 262K | — |
| GPT-5.4 Mini (`openai/gpt-5.4-mini`) | 61 | $0.75 | $4.50 | $0.075 | 400K | Same |
| Ling 3.0 Flash (`inclusionai/ling-3.0-flash`) | 60 | $0.021 | $0.063 | $0.004 | 262K | — |
| Llama 3.1 70B Instruct (`meta-llama/llama-3.1-70b-instruct`) | 60 | $0.40 | $0.40 | — | 131K | — |
| MiniMax M2.7 (`minimax/minimax-m2.7`) | 60 | $0.30 | $1.20 | $0.06 | 205K | Same |
| R1 0528 (`deepseek/deepseek-r1-0528`) | 60 | $0.50 | $2.15 | $0.35 | 164K | — |
| Kimi K2.5 (`moonshotai/kimi-k2.5`) | 60 | $0.50 | $2.50 | $0.15 | 262K | -17% |
| Claude Opus 4.5 (`anthropic/claude-opus-4.5`) | 60 | $5.00 | $25.00 | $0.50 | 200K | Same |
| Qwen3.5-27B (`qwen/qwen3.5-27b`) | 59 | $0.27 | $2.16 | $0.27 | 262K | — |
| Gemma 4 26B A4B (free) (`google/gemma-4-26b-a4b-it:free`) | 58 | $0 | $0 | — | 262K | — |
| Gemma 4 26B A4B (`google/gemma-4-26b-a4b-it`) | 58 | $0.076 | $0.26 | $0.043 | 262K | — |
| Gemini 2.5 Pro (`google/gemini-2.5-pro`) | 58 | $1.25 | $10.00 | $0.13 | 1.05M | Same |
| Gemini 2.5 Pro Preview 06-05 (`google/gemini-2.5-pro-preview`) | 58 | $1.25 | $10.00 | $0.13 | 1.05M | Same |
| GPT-5.2 (`openai/gpt-5.2`) | 58 | $1.75 | $14.00 | $0.17 | 400K | Same |
| Laguna S 2.1 (free) (`poolside/laguna-s-2.1:free`) | 57 | $0 | $0 | — | 262K | — |
| Nemotron 3 Ultra (free) (`nvidia/nemotron-3-ultra-550b-a55b:free`) | 57 | $0 | $0 | — | 1M | — |
| Mercury 2.5 (`inception/mercury-2.5`) | 57 | $0.04 | $0.15 | $0.004 | 260K | Same |
| Laguna S 2.1 (`poolside/laguna-s-2.1`) | 57 | $0.09 | $0.18 | $0.009 | 1.05M | -10% |
| Qwen3 32B (`qwen/qwen3-32b`) | 57 | $0.08 | $0.28 | — | 131K | — |
| Gemini 3.1 Flash Lite (`google/gemini-3.1-flash-lite`) | 57 | $0.25 | $1.50 | $0.025 | 1.05M | Same |
| Gemini 3.1 Flash Lite Preview (`google/gemini-3.1-flash-lite-preview`) | 57 | $0.25 | $1.50 | $0.025 | 1.05M | Same |
| Nemotron 3 Ultra (`nvidia/nemotron-3-ultra-550b-a55b`) | 57 | $0.60 | $2.40 | $0.12 | 262K | — |
| Gemini 2.5 Flash (`google/gemini-2.5-flash`) | 57 | $0.30 | $2.50 | $0.03 | 1.05M | Same |
| Claude Opus 4.7 (`anthropic/claude-opus-4.7`) | 57 | $5.00 | $25.00 | $0.50 | 1M | Same |
| Gemma 4 31B (free) (`google/gemma-4-31b-it:free`) | 56 | $0 | $0 | — | 262K | — |
| Gemma 4 31B (`google/gemma-4-31b-it`) | 56 | $0.20 | $0.40 | — | 262K | — |
| GLM 4.7 Flash (`z-ai/glm-4.7-flash`) | 56 | $0.06 | $0.40 | — | 200K | — |
| Llama 4 Maverick (`meta-llama/llama-4-maverick`) | 56 | $0.19 | $0.65 | $0.05 | 524K | — |
| gpt-oss-120b (`openai/gpt-oss-120b`) | 55 | $0.15 | $0.60 | $0.075 | 131K | — |
| Mistral Small 4 (`mistralai/mistral-small-2603`) | 55 | $0.15 | $0.60 | $0.015 | 262K | Same |
| Solar Pro 3 (`upstage/solar-pro-3`) | 55 | $0.15 | $0.60 | $0.015 | 131K | Same |
| Qwen3.6 35B A3B (`qwen/qwen3.6-35b-a3b`) | 55 | $0.10 | $0.95 | $0.05 | 262K | — |
| Qwen3.5-35B-A3B (`qwen/qwen3.5-35b-a3b`) | 55 | $0.14 | $1.00 | $0.05 | 262K | — |
| Qwen3 Coder 480B A35B (`qwen/qwen3-coder`) | 54 | $0.30 | $1.00 | $0.10 | 262K | — |
| DeepSeek V3 0324 (`deepseek/deepseek-chat-v3-0324`) | 54 | $0.29 | $1.14 | $0.11 | 164K | — |
| o4 Mini High (`openai/o4-mini-high`) | 54 | $1.10 | $4.40 | $0.28 | 200K | — |
| Hy3 preview (`tencent/hy3-preview`) | 53 | $0.18 | $0.60 | $0.06 | 262K | — |
| GLM 4.5 Air (`z-ai/glm-4.5-air`) | 53 | $0.13 | $0.85 | $0.025 | 131K | -23% |
| DeepSeek V3.1 (`deepseek/deepseek-chat-v3.1`) | 53 | $0.25 | $0.95 | $0.13 | 164K | — |
| Command A+ (`cohere/command-a-plus`) | 53 | $0.30 | $1.50 | $0.15 | 192K | -85% |
| GLM 4.7 (`z-ai/glm-4.7`) | 53 | $0.54 | $1.98 | $0.099 | 205K | — |
| GLM 4.6 (`z-ai/glm-4.6`) | 53 | $0.55 | $2.20 | $0.11 | 205K | — |
| GPT-4.1 (`openai/gpt-4.1`) | 53 | $2.00 | $8.00 | $0.50 | 1.05M | Same |
| Command A (`cohere/command-a`) | 53 | $2.50 | $10.00 | — | 256K | Same |
| Kimi K2 0711 (`moonshotai/kimi-k2`) | 52 | $0.57 | $2.30 | — | 131K | -8% |
| Llama 3.1 8B Instruct (`meta-llama/llama-3.1-8b-instruct`) | 51 | $0.05 | $0.08 | $0.025 | 131K | — |
| Trinity Large Thinking (`arcee-ai/trinity-large-thinking`) | 51 | $0.25 | $0.80 | $0.06 | 262K | -11% |
| o3 Mini (`openai/o3-mini`) | 51 | $1.10 | $4.40 | $0.55 | 200K | Same |
| gpt-oss-20b (`openai/gpt-oss-20b`) | 50 | $0.018 | $0.09 | $0.009 | 131K | — |
| Qwen3.7 Flash (`qwen/qwen3.7-flash`) | 50 | $0.03 | $0.13 | $0.006 | 1M | Same |
| Granite 4.2 8B (`ibm-granite/granite-4.2-8b`) | 50 | $0.06 | $0.25 | $0.015 | 131K | — |
| GPT-5.4 Nano (`openai/gpt-5.4-nano`) | 50 | $0.20 | $1.25 | $0.02 | 400K | Same |
| Claude Sonnet 4.5 (`anthropic/claude-sonnet-4.5`) | 50 | $3.00 | $15.00 | $0.30 | 1M | Same |
| Mistral Medium 3 (`mistralai/mistral-medium-3`) | 49 | $0.40 | $2.00 | $0.04 | 131K | Same |
| Grok 4.20 (`x-ai/grok-4.20`) | 49 | $1.25 | $2.50 | $0.20 | 2M | Same |
| GPT-4o (`openai/gpt-4o`) | 48 | $2.50 | $10.00 | $1.25 | 128K | Same |
| Llama 4 Scout (`meta-llama/llama-4-scout`) | 47 | $0.10 | $0.30 | — | 1.31M | — |
| Claude Haiku 4.5 (`anthropic/claude-haiku-4.5`) | 47 | $1.00 | $5.00 | $0.10 | 200K | Same |
| GPT-4.1 Mini (`openai/gpt-4.1-mini`) | 46 | $0.40 | $1.60 | $0.10 | 1.05M | Same |
| GPT-4.1 Nano (`openai/gpt-4.1-nano`) | 44 | $0.10 | $0.40 | $0.025 | 1.05M | Same |
| GPT-4o-mini (`openai/gpt-4o-mini`) | 44 | $0.15 | $0.60 | $0.075 | 128K | Same |
| LFM2.5-24B-A2B (`liquid/lfm-2.5-24b-a2b`) | 44 | $0.05 | $0.70 | $0.025 | 128K | -30% |
| GLM 4.5 (`z-ai/glm-4.5`) | 44 | $0.60 | $2.20 | $0.11 | 131K | Same |
| Nova Pro 1.0 (`amazon/nova-pro-v1`) | 44 | $0.80 | $3.20 | — | 300K | — |
| Gemini 2.5 Flash Lite (`google/gemini-2.5-flash-lite`) | 43 | $0.10 | $0.40 | $0.01 | 1.05M | Same |
| DeepSeek V3 (`deepseek/deepseek-chat`) | 43 | $0.26 | $1.03 | — | 164K | -6% |
| LFM2.5-2.6B (free) (`liquid/lfm-2.5-2.6b:free`) | 42 | $0 | $0 | — | 66K | — |
| Gemma 3 27B (`google/gemma-3-27b-it`) | 41 | $0.08 | $0.35 | $0.04 | 131K | — |
| Phi 4 (`microsoft/phi-4`) | 37 | $0.07 | $0.14 | — | 16K | — |
| Extract (`scaledown/extract`) | 0 | $0.04 | $0 | — | 1M | — |
| Laguna XS 2.1 (free) (`poolside/laguna-xs-2.1:free`) | 0 | $0 | $0 | — | 262K | — |
| Nemotron 3 Super (free) (`nvidia/nemotron-3-super-120b-a12b:free`) | 0 | $0 | $0 | — | 262K | — |
| North Mini Code (free) (`cohere/north-mini-code:free`) | 0 | $0 | $0 | — | 256K | — |
| Summarize (`scaledown/summarize`) | 0 | $0.04 | $0 | — | 1M | — |
| Laguna XS 2.1 (`poolside/laguna-xs-2.1`) | 0 | $0.06 | $0.12 | $0.03 | 262K | -40% |
| Hy-MT2-1.8B (`tencent/hy-mt2-1.8b`) | 0 | $0.044 | $0.18 | — | 8K | — |
| Hy-MT2-30B-A3B (`tencent/hy-mt2-30b-a3b`) | 0 | $0.074 | $0.29 | — | 8K | — |
| Seed 1.6 Flash (`bytedance-seed/seed-1.6-flash`) | 0 | $0.075 | $0.30 | — | 262K | — |
| Mercury 3 (`inception/mercury-3`) | 0 | $0.10 | $0.35 | $0.01 | 1M | Same |
| GPT-5 Nano (`openai/gpt-5-nano`) | 0 | $0.05 | $0.40 | $0.005 | 400K | Same |
| Qwen2.5 72B Instruct (`qwen/qwen-2.5-72b-instruct`) | 0 | $0.36 | $0.40 | — | 33K | — |
| Seed-2.0-Mini (`bytedance-seed/seed-2.0-mini`) | 0 | $0.10 | $0.40 | — | 262K | — |
| Nemotron 3 Super (`nvidia/nemotron-3-super-120b-a12b`) | 0 | $0.08 | $0.45 | — | 262K | — |
| Solar Pro 4 (`upstage/solar-pro4`) | 0 | $0.15 | $0.60 | $0.03 | 524K | -50% |
| Gemma 2 27B (`google/gemma-2-27b-it`) | 0 | $0.65 | $0.65 | — | 8K | — |
| Mercury 2 (`inception/mercury-2`) | 0 | $0.25 | $0.75 | $0.025 | 128K | Same |
| MiniMax M2.5 (`minimax/minimax-m2.5`) | 0 | $0.27 | $0.95 | $0.03 | 205K | -21% |
| Qwen2.5 Coder 32B Instruct (`qwen/qwen-2.5-coder-32b-instruct`) | 0 | $0.66 | $1.00 | — | 33K | — |
| LongCat 2.0 (`meituan/longcat-2.0`) | 0 | $0.30 | $1.20 | $0.006 | 1.05M | — |
| Aion-2.0 (`aion-labs/aion-2.0`) | 0 | $0.80 | $1.60 | $0.20 | 131K | Same |
| GPT-5 Mini (`openai/gpt-5-mini`) | 0 | $0.25 | $2.00 | $0.025 | 400K | Same |
| Grok Build 0.1 (`x-ai/grok-build-0.1`) | 0 | $1.00 | $2.00 | $0.20 | 256K | Same |
| Seed 1.6 (`bytedance-seed/seed-1.6`) | 0 | $0.25 | $2.00 | — | 262K | — |
| Seed-2.0-Lite (`bytedance-seed/seed-2.0-lite`) | 0 | $0.25 | $2.00 | — | 262K | — |
| Grok 4.20 Multi-Agent (`x-ai/grok-4.20-multi-agent`) | 0 | $1.25 | $2.50 | $0.20 | 2M | — |
| Nova 2 Lite (`amazon/nova-2-lite-v1`) | 0 | $0.30 | $2.50 | — | 1M | — |
| Seed 2.1 Turbo (`bytedance-seed/seed-2-1-turbo`) | 0 | $0.50 | $2.50 | — | 262K | — |
| Pareto 26.10 (`unbiased/pareto-26.10`) | 0 | $0.80 | $3.20 | $0.03 | 1.05M | -57% |
| Sakana Namazu (`sakana/sakana-namazu`) | 0 | $0.95 | $4.00 | $0.15 | 262K | Same |
| Pareto 26.9 (`unbiased/pareto-26.9`) | 0 | $2.50 | $7.50 | $0.25 | 262K | Same |
| Ember-1 (`fireworks/ember-1`) | 0 | $3.00 | $15.00 | $0.30 | 1.05M | Same |
| GPT-4 Turbo (`openai/gpt-4-turbo`) | 0 | $10.00 | $30.00 | — | 128K | Same |
| o3 Pro (`openai/o3-pro`) | 0 | $20.00 | $80.00 | — | 200K | Same |
| GPT-5.2 Pro (`openai/gpt-5.2-pro`) | 0 | $21.00 | $168.00 | — | 400K | Same |
| o1-pro (`openai/o1-pro`) | 0 | $150.00 | $600.00 | — | 200K | Same |

## Other models

| Model | Input | Output | Cached input | Context |
|---|---|---|---|---|
| Lyria 3 Clip Preview (`google/lyria-3-clip-preview`) | $0 | $0 | — | 1.05M |
| Lyria 3 Pro Preview (`google/lyria-3-pro-preview`) | $0 | $0 | — | 1.05M |
| Nemotron 3 Nano Omni (free) (`nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free`) | $0 | $0 | — | 256K |
| Nemotron 3.5 Content Safety (free) (`nvidia/nemotron-3.5-content-safety:free`) | $0 | $0 | — | 128K |
| Nemotron 3.5 Lightning (free) (`nvidia/nemotron-3.5-lightning:free`) | $0 | $0 | — | 1M |
| Nemotron 3.5 Super VL (free) (`nvidia/nemotron-3.5-super-vl:free`) | $0 | $0 | — | 1M |
| Xing4.0 29B A4B (free) (`xingchen-agi/xing4.0-29b-a4b:free`) | $0 | $0 | — | 262K |
| Mistral Nemo (`mistralai/mistral-nemo`) | $0.029 | $0.03 | — | 131K |
| Gemma 3 4B (`google/gemma-3-4b-it`) | $0.04 | $0.05 | $0.02 | 131K |
| Llama 3 8B Lunaris (`sao10k/l3-lunaris-8b`) | $0.04 | $0.05 | — | 8K |
| Ministral 3 8B 2512 (batch) (`mistralai/ministral-8b-2512:batch`) | $0.075 | $0.075 | $0.007 | 262K |
| Mistral Small 3 (`mistralai/mistral-small-24b-instruct-2501`) | $0.05 | $0.08 | — | 33K |
| Ministral 3 3B 2512 (`mistralai/ministral-3b-2512`) | $0.10 | $0.10 | $0.01 | 131K |
| Nex-N2.5-Mini (`nex-agi/nex-n2.5-mini`) | $0.025 | $0.10 | $0.003 | 262K |
| Reka Edge (`rekaai/reka-edge`) | $0.10 | $0.10 | — | 16K |
| MythoMax 13B (`gryphe/mythomax-l2-13b`) | $0.08 | $0.11 | — | 8K |
| gpt-oss-20b (batch) (`openai/gpt-oss-20b:batch`) | $0.024 | $0.11 | — | 131K |
| Granite 4.0 Micro (`ibm-granite/granite-4.0-h-micro`) | $0.017 | $0.11 | — | 131K |
| gpt-oss-120b (batch) (`openai/gpt-oss-120b:batch`) | $0.03 | $0.14 | — | 131K |
| Nova Micro 1.0 (`amazon/nova-micro-v1`) | $0.035 | $0.14 | — | 128K |
| Command R7B (12-2024) (`cohere/command-r7b-12-2024`) | $0.037 | $0.15 | — | 128K |
| DeepSeek V4.1 Flash (batch) (`deepseek/deepseek-v4.1-flash:batch`) | $0.05 | $0.15 | $0.004 | 1.05M |
| Gemma 3 12B (`google/gemma-3-12b-it`) | $0.05 | $0.15 | — | 131K |
| Ministral 3 8B 2512 (`mistralai/ministral-8b-2512`) | $0.15 | $0.15 | $0.015 | 262K |
| Qwen3.5-9B (`qwen/qwen3.5-9b`) | $0.10 | $0.15 | — | 262K |
| Schematron V2 Turbo (`inference-net/schematron-v2-turbo`) | $0.03 | $0.15 | $0.03 | 128K |
| GLM 5.3 Flash (batch) (`z-ai/glm-5.3-flash:batch`) | $0.05 | $0.18 | $0.01 | 1.05M |
| Llama Guard 4 12B (`meta-llama/llama-guard-4-12b`) | $0.18 | $0.18 | — | 164K |
| DeepSeek V4 Flash 0423 (`deepseek/deepseek-v4-flash`) | $0.091 | $0.18 | $0.018 | 1.05M |
| Gemini 2.5 Flash Lite (batch) (`google/gemini-2.5-flash-lite:batch`) | $0.05 | $0.20 | $0.01 | 1.05M |
| GPT-4.1 Nano (batch) (`openai/gpt-4.1-nano:batch`) | $0.05 | $0.20 | $0.013 | 1.05M |
| GPT-5 Nano (batch) (`openai/gpt-5-nano:batch`) | $0.025 | $0.20 | $0.003 | 400K |
| Ministral 3 14B 2512 (`mistralai/ministral-14b-2512`) | $0.20 | $0.20 | $0.02 | 262K |
| Muse Spark 1.2 Contributor (`meta/muse-spark-1.2-contributor`) | $0.10 | $0.20 | $0.002 | 1.05M |
| Muse Spark 1.3 Contributor (`meta/muse-spark-1.3-contributor`) | $0.10 | $0.20 | $0.002 | 1.05M |
| Nemotron 3.5 Content Safety (`nvidia/nemotron-3.5-content-safety`) | $0.20 | $0.20 | — | 131K |
| Nemotron 3.5 Lightning (`nvidia/nemotron-3.5-lightning`) | $0.07 | $0.20 | $0.04 | 262K |
| Qwen2.5 7B Instruct (`qwen/qwen-2.5-7b-instruct`) | $0.10 | $0.20 | — | 33K |
| Reka Flash 3 (`rekaai/reka-flash-3`) | $0.10 | $0.20 | — | 66K |
| Solar Mini 4 (`upstage/solar-mini4`) | $0.05 | $0.20 | $0.005 | 524K |
| UI-TARS 7B (`bytedance/ui-tars-1.5-7b`) | $0.10 | $0.20 | $0.10 | 128K |
| Llama 3.2 1B Instruct (`meta-llama/llama-3.2-1b-instruct`) | $0.027 | $0.20 | — | 60K |
| Schematron V2 Small (`inference-net/schematron-v2-small`) | $0.05 | $0.23 | $0.05 | 128K |
| Nemotron 3 Nano 30B A3B (`nvidia/nemotron-3-nano-30b-a3b`) | $0.06 | $0.24 | — | 262K |
| Nova Lite 1.0 (`amazon/nova-lite-v1`) | $0.06 | $0.24 | — | 300K |
| Qwen3 14B (`qwen/qwen3-14b`) | $0.12 | $0.24 | — | 41K |
| Claude Haiku 5.5 (batch) (`anthropic/claude-haiku-5.5:batch`) | $0.05 | $0.25 | $0.005 | 1M |
| GPT-6 Luna (batch) (`openai/gpt-6-luna:batch`) | $0.05 | $0.25 | $0.005 | 1.05M |
| GPT-6 Luna Pro (batch) (`openai/gpt-6-luna-pro:batch`) | $0.05 | $0.25 | $0.005 | 1.05M |
| Mistral Small 3.2 24B (`mistralai/mistral-small-3.2-24b-instruct`) | $0.094 | $0.25 | — | 256K |
| Nex-N2.5-Pro (`nex-agi/nex-n2.5-pro`) | $0.075 | $0.25 | $0.015 | 262K |
| Qwen3 Coder 30B A3B Instruct (`qwen/qwen3-coder-30b-a3b-instruct`) | $0.07 | $0.28 | — | 262K |
| Hy-MT2-7B (`tencent/hy-mt2-7b`) | $0.074 | $0.29 | — | 8K |
| GPT-4o-mini (batch) (`openai/gpt-4o-mini:batch`) | $0.075 | $0.30 | $0.037 | 128K |
| gpt-oss-safeguard-20b (`openai/gpt-oss-safeguard-20b`) | $0.075 | $0.30 | $0.037 | 131K |
| Mistral Small 4 (batch) (`mistralai/mistral-small-2603:batch`) | $0.075 | $0.30 | $0.007 | 262K |
| Qwen3 30B A3B Instruct 2507 (`qwen/qwen3-30b-a3b-instruct-2507`) | $0.09 | $0.30 | — | 262K |
| Voxtral Small 24B 2507 (`mistralai/voxtral-small-24b-2507`) | $0.10 | $0.30 | $0.01 | 33K |
| Llama 3.2 3B Instruct (`meta-llama/llama-3.2-3b-instruct`) | $0.051 | $0.34 | — | 131K |
| UnslopNemo 12B (`thedrummer/unslopnemo-12b`) | $0.40 | $0.40 | — | 1.02M |
| Codestral 2508 (batch) (`mistralai/codestral-2508:batch`) | $0.15 | $0.45 | $0.015 | 256K |
| Qwen3.8 Flash (`qwen/qwen3.8-flash`) | $0.15 | $0.47 | $0.016 | 1M |
| Cydonia 24B V4.1 (`thedrummer/cydonia-24b-v4.1`) | $0.30 | $0.50 | $0.15 | 131K |
| GPT-6 Luna Pro (`openai/gpt-6-luna-pro`) | $0.10 | $0.50 | $0.01 | 1.05M |
| Nemotron 3.5 Super VL (`nvidia/nemotron-3.5-super-vl`) | $0.15 | $0.50 | $0.02 | 1.05M |
| Qwen3 30B A3B (`qwen/qwen3-30b-a3b`) | $0.12 | $0.50 | — | 41K |
| Qwen3 235B A22B Instruct 2507 (`qwen/qwen3-235b-a22b-2507`) | $0.09 | $0.55 | — | 262K |
| Mistral Small 3.1 24B (`mistralai/mistral-small-3.1-24b-instruct`) | $0.35 | $0.56 | — | 128K |
| Hunyuan A13B Instruct (`tencent/hunyuan-a13b-instruct`) | $0.14 | $0.57 | — | 131K |
| Command R (08-2024) (`cohere/command-r-08-2024`) | $0.15 | $0.60 | — | 128K |
| GPT-4o-mini (2024-07-18) (`openai/gpt-4o-mini-2024-07-18`) | $0.15 | $0.60 | $0.075 | 128K |
| GPT-5.6 Luna (batch) (`openai/gpt-5.6-luna:batch`) | $0.10 | $0.60 | $0.01 | 1.05M |
| GPT-5.6 Luna Pro (batch) (`openai/gpt-5.6-luna-pro:batch`) | $0.10 | $0.60 | $0.01 | 1.05M |
| Qwen3 VL 30B A3B Instruct (`qwen/qwen3-vl-30b-a3b-instruct`) | $0.15 | $0.60 | — | 262K |
| Saba (`mistralai/mistral-saba`) | $0.20 | $0.60 | $0.02 | 33K |
| GPT-5.4 Nano (batch) (`openai/gpt-5.4-nano:batch`) | $0.10 | $0.63 | $0.01 | 400K |
| DeepSeek V4 Flash Vision Exp (`deepseek/deepseek-v4-flash-vision-exp`) | $0.22 | $0.65 | $0.007 | 1.05M |
| ReMM SLERP 13B (`undi95/remm-slerp-l2-13b`) | $0.35 | $0.65 | — | 6K |
| Hermes 3 70B Instruct (`nousresearch/hermes-3-llama-3.1-70b`) | $0.70 | $0.70 | — | 131K |
| DeepSeek V4 Pro 0423 (`deepseek/deepseek-v4-pro`) | $0.36 | $0.72 | $0.03 | 1.05M |
| Gemini 3.1 Flash Lite (batch) (`google/gemini-3.1-flash-lite:batch`) | $0.13 | $0.75 | $0.013 | 1.05M |
| GPT-3.5 Turbo (batch) (`openai/gpt-3.5-turbo:batch`) | $0.25 | $0.75 | — | 16K |
| Mistral Large 3 2512 (batch) (`mistralai/mistral-large-2512:batch`) | $0.25 | $0.75 | $0.025 | 262K |
| Qwen3 VL 8B Instruct (`qwen/qwen3-vl-8b-instruct`) | $0.25 | $0.75 | $0.12 | 262K |
| Weaver (alpha) (`mancer/weaver`) | $0.40 | $0.75 | — | 8K |
| Qwen-Plus (`qwen/qwen-plus`) | $0.26 | $0.78 | $0.052 | 1M |
| GPT-4.1 Mini (batch) (`openai/gpt-4.1-mini:batch`) | $0.20 | $0.80 | $0.05 | 1.05M |
| Qwen3 Coder Next (`qwen/qwen3-coder-next`) | $0.12 | $0.80 | $0.07 | 262K |
| Skyfall 36B V2 (`thedrummer/skyfall-36b-v2`) | $0.55 | $0.80 | $0.25 | 33K |
| Llama 3.1 Euryale 70B v2.2 (`sao10k/l3.1-euryale-70b`) | $0.85 | $0.85 | — | 131K |
| Codestral 2508 (`mistralai/codestral-2508`) | $0.30 | $0.90 | $0.03 | 256K |
| GLM 4.6V (`z-ai/glm-4.6v`) | $0.30 | $0.90 | $0.055 | 131K |
| Uncensored (`cognitivecomputations/dolphin-mistral-24b-venice-edition`) | $0.20 | $0.90 | — | 128K |
| Qwen3.7 Plus (batch) (`qwen/qwen3.7-plus:batch`) | $0.23 | $0.92 | — | 262K |
| Qwen3 Coder Flash (`qwen/qwen3-coder-flash`) | $0.20 | $0.97 | $0.039 | 1M |
| DeepSeek V3.1 Terminus (`deepseek/deepseek-v3.1-terminus`) | $0.27 | $1.00 | — | 164K |
| GPT-5 Mini (batch) (`openai/gpt-5-mini:batch`) | $0.13 | $1.00 | $0.013 | 400K |
| Hermes 3 405B Instruct (`nousresearch/hermes-3-llama-3.1-405b`) | $1.00 | $1.00 | — | 131K |
| Mistral Medium 3.1 (batch) (`mistralai/mistral-medium-3.1:batch`) | $0.20 | $1.00 | $0.02 | 131K |
| Qwen2.5 VL 72B Instruct (`qwen/qwen2.5-vl-72b-instruct`) | $0.80 | $1.00 | $0.40 | 128K |
| Qwen3 VL 30B A3B Thinking (`qwen/qwen3-vl-30b-a3b-thinking`) | $0.29 | $1.00 | — | 262K |
| Sonar (`perplexity/sonar`) | $1.00 | $1.00 | — | 127K |
| MiniMax M2 (`minimax/minimax-m2`) | $0.26 | $1.02 | — | 205K |
| MiniMax-01 (`minimax/minimax-01`) | $0.20 | $1.10 | — | 1M |
| Qwen3 Next 80B A3B Instruct (`qwen/qwen3-next-80b-a3b-instruct`) | $0.10 | $1.10 | $0.07 | 262K |
| Qwen3.6 Flash (`qwen/qwen3.6-flash`) | $0.19 | $1.13 | — | 1M |
| GPT-5.6 Luna Pro (`openai/gpt-5.6-luna-pro`) | $0.20 | $1.20 | $0.02 | 1.05M |
| MiniMax M2-her (`minimax/minimax-m2-her`) | $0.30 | $1.20 | $0.03 | 66K |
| MiniMax M2.1 (`minimax/minimax-m2.1`) | $0.30 | $1.20 | $0.03 | 205K |
| Morph V3 Fast (`morph/morph-v3-fast`) | $0.80 | $1.20 | — | 262K |
| Qwen3 Next 80B A3B Thinking (`qwen/qwen3-next-80b-a3b-thinking`) | $0.15 | $1.20 | — | 262K |
| Gemini 3.5 Flash Lite (batch) (`google/gemini-3.5-flash-lite:batch`) | $0.15 | $1.25 | $0.015 | 1.05M |
| GLM 5.3 FlashX (`z-ai/glm-5.3-flashx`) | $0.37 | $1.25 | $0.09 | 1.05M |
| Relace Apply 3 (`relace/relace-apply-3`) | $0.85 | $1.25 | — | 256K |
| Aion 3.5 Mini (`aion-labs/aion-3.5-mini`) | $0.70 | $1.40 | $0.18 | 262K |
| Aion-3.0-Mini (`aion-labs/aion-3.0-mini`) | $0.70 | $1.40 | $0.18 | 131K |
| Gemini 3 Flash Preview (batch) (`google/gemini-3-flash-preview:batch`) | $0.25 | $1.50 | — | 1.05M |
| GPT-3.5 Turbo (`openai/gpt-3.5-turbo`) | $0.50 | $1.50 | — | 16K |
| Mistral Large 3 2512 (`mistralai/mistral-large-2512`) | $0.50 | $1.50 | $0.05 | 262K |
| Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) (`google/gemini-3.1-flash-lite-image`) | $0.25 | $1.50 | — | 66K |
| Perceptron Mk1 (`perceptron/perceptron-mk1`) | $0.15 | $1.50 | — | 33K |
| Perceptron Mk1.5 (`perceptron/perceptron-mk1.5`) | $0.15 | $1.50 | — | 37K |
| Qwen3.5 Plus 2026-02-15 (`qwen/qwen3.5-plus-02-15`) | $0.26 | $1.56 | — | 1M |
| Aion-RP 1.0 (8B) (`aion-labs/aion-rp-llama-3.1-8b`) | $0.80 | $1.60 | — | 33K |
| GLM 4.5V (`z-ai/glm-4.5v`) | $0.60 | $1.80 | $0.11 | 66K |
| Qwen3.5 Plus 2026-04-20 (`qwen/qwen3.5-plus-20260420`) | $0.30 | $1.80 | — | 1M |
| Gemini 3.6 Flash (batch) (`google/gemini-3.6-flash:batch`) | $0.38 | $1.88 | $0.037 | 1.05M |
| Gemini 3.7 Flash (batch) (`google/gemini-3.7-flash:batch`) | $0.38 | $1.88 | $0.037 | 1.05M |
| Gemini 3.8 Flash (batch) (`google/gemini-3.8-flash:batch`) | $0.38 | $1.88 | $0.037 | 1.05M |
| Morph V3 Large (`morph/morph-v3-large`) | $0.90 | $1.90 | — | 262K |
| Qwen3 VL 235B A22B Instruct (`qwen/qwen3-vl-235b-a22b-instruct`) | $0.21 | $1.90 | $0.10 | 262K |
| Devstral 2 2512 (`mistralai/devstral-2512`) | $0.40 | $2.00 | $0.04 | 262K |
| GLM 5.3 (batch) (`z-ai/glm-5.3:batch`) | $0.45 | $2.00 | $0.10 | 1.05M |
| GPT-3.5 Turbo (older v0613) (`openai/gpt-3.5-turbo-0613`) | $1.00 | $2.00 | — | 4K |
| GPT-3.5 Turbo Instruct (`openai/gpt-3.5-turbo-instruct`) | $1.50 | $2.00 | — | 4K |
| GPT-5 Image Mini (`openai/gpt-5-image-mini`) | $2.50 | $2.00 | $0.25 | 400K |
| GPT-5.1-Codex-Mini (`openai/gpt-5.1-codex-mini`) | $0.25 | $2.00 | $0.03 | 400K |
| Grok 4.3 (batch) (`x-ai/grok-4.3:batch`) | $1.00 | $2.00 | $0.16 | 1M |
| Mistral Medium 3.1 (`mistralai/mistral-medium-3.1`) | $0.40 | $2.00 | $0.04 | 131K |
| MiniMax M1 (`minimax/minimax-m1`) | $0.55 | $2.20 | — | 1M |
| o3 Mini (batch) (`openai/o3-mini:batch`) | $0.55 | $2.20 | $0.28 | 200K |
| o4 Mini (batch) (`openai/o4-mini:batch`) | $0.55 | $2.20 | $0.14 | 200K |
| GPT-5.4 Mini (batch) (`openai/gpt-5.4-mini:batch`) | $0.38 | $2.25 | $0.037 | 400K |
| Qwen3.5 397B A17B (`qwen/qwen3.5-397b-a17b`) | $0.39 | $2.34 | — | 262K |
| GPT Audio Mini (`openai/gpt-audio-mini`) | $0.60 | $2.40 | — | 128K |
| Claude Haiku 4.5 (batch) (`anthropic/claude-haiku-4.5:batch`) | $0.50 | $2.50 | $0.05 | 200K |
| Kimi K2 0905 (`moonshotai/kimi-k2-0905`) | $0.60 | $2.50 | — | 262K |
| Kimi K2 Thinking (`moonshotai/kimi-k2-thinking`) | $0.60 | $2.50 | $0.15 | 262K |
| Moondream 3 Preview (`moondream/moondream3-preview`) | $0.30 | $2.50 | — | 32K |
| Moondream 3.1 (`moondream/moondream3.1-9b-a2b`) | $0.30 | $2.50 | — | 32K |
| Nano Banana (Gemini 2.5 Flash Image) (`google/gemini-2.5-flash-image`) | $0.30 | $2.50 | $0.03 | 33K |
| Glimpse (`elorian/glimpse`) | $0.60 | $3.00 | $0.06 | 262K |
| Hermes 4 405B (`nousresearch/hermes-4-405b`) | $1.00 | $3.00 | — | 131K |
| Nano Banana 2 (Gemini 3.1 Flash Image Preview) (`google/gemini-3.1-flash-image-preview`) | $0.50 | $3.00 | — | 66K |
| Nano Banana 2 (Gemini 3.1 Flash Image) (`google/gemini-3.1-flash-image`) | $0.50 | $3.00 | — | 131K |
| Relace Search (`relace/relace-search`) | $1.00 | $3.00 | — | 256K |
| Seed-2.0-Code (`bytedance-seed/seed-2.0-code`) | $0.50 | $3.00 | — | 262K |
| Qwen3 235B A22B Thinking 2507 (`qwen/qwen3-235b-a22b-thinking-2507`) | $0.45 | $3.50 | — | 128K |
| Mistral Medium 3.5 (batch) (`mistralai/mistral-medium-3-5:batch`) | $0.75 | $3.75 | — | 262K |
| GPT-3.5 Turbo 16k (`openai/gpt-3.5-turbo-16k`) | $3.00 | $4.00 | — | 16K |
| GPT-4.1 (batch) (`openai/gpt-4.1:batch`) | $1.00 | $4.00 | $0.25 | 1.05M |
| o3 (batch) (`openai/o3:batch`) | $1.00 | $4.00 | $0.25 | 200K |
| o3 Mini High (`openai/o3-mini-high`) | $1.10 | $4.40 | $0.55 | 200K |
| Gemini 3.5 Flash (batch) (`google/gemini-3.5-flash:batch`) | $0.75 | $4.50 | $0.075 | 1.05M |
| Claude Sonnet 5 (batch) (`anthropic/claude-sonnet-5:batch`) | $1.00 | $5.00 | $0.10 | 1M |
| Claude Sonnet 5.5 (batch) (`anthropic/claude-sonnet-5.5:batch`) | $1.00 | $5.00 | $0.05 | 1M |
| Gemini 4 Argon (batch) (`google/gemini-4-argon:batch`) | $1.00 | $5.00 | $0.05 | 1.05M |
| GPT-4o (batch) (`openai/gpt-4o:batch`) | $1.25 | $5.00 | $0.63 | 128K |
| GPT-5 (batch) (`openai/gpt-5:batch`) | $0.63 | $5.00 | $0.063 | 400K |
| GPT-5.1 (batch) (`openai/gpt-5.1:batch`) | $0.63 | $5.00 | $0.063 | 400K |
| GPT-6 Sol (batch) (`openai/gpt-6-sol:batch`) | $1.00 | $5.00 | $0.10 | 1.05M |
| GPT-6 Sol Pro (batch) (`openai/gpt-6-sol-pro:batch`) | $1.00 | $5.00 | $0.10 | 1.05M |
| GPT-6.1 Sol (batch) (`openai/gpt-6.1-sol:batch`) | $1.00 | $5.00 | $0.05 | 1.05M |
| GPT-6.1 Sol Pro (batch) (`openai/gpt-6.1-sol-pro:batch`) | $1.00 | $5.00 | $0.05 | 1.05M |
| Magnum v4 72B (`anthracite-org/magnum-v4-72b`) | $2.50 | $5.00 | — | 33K |
| Aion 3.5 (`aion-labs/aion-3.5`) | $3.00 | $6.00 | $0.75 | 262K |
| Aion-3.0 (`aion-labs/aion-3.0`) | $3.00 | $6.00 | $0.75 | 131K |
| Fugu Max (`sakana/fugu-max`) | $2.00 | $6.00 | $0.25 | 1M |
| Gemini 3.1 Pro Preview (batch) (`google/gemini-3.1-pro-preview:batch`) | $1.00 | $6.00 | — | 1.05M |
| GPT-5.6 Terra (batch) (`openai/gpt-5.6-terra:batch`) | $1.00 | $6.00 | $0.10 | 1.05M |
| GPT-5.6 Terra Pro (batch) (`openai/gpt-5.6-terra-pro:batch`) | $1.00 | $6.00 | $0.10 | 1.05M |
| Mistral Large (`mistralai/mistral-large`) | $2.00 | $6.00 | $0.20 | 128K |
| Mistral Large 2407 (`mistralai/mistral-large-2407`) | $2.00 | $6.00 | $0.20 | 131K |
| Mixtral 8x22B Instruct (`mistralai/mixtral-8x22b-instruct`) | $2.00 | $6.00 | $0.20 | 66K |
| Palmyra X5 (`writer/palmyra-x5`) | $0.60 | $6.00 | — | 1.04M |
| Qwen3.8 2.4T A95B (`qwen/qwen3.8-2.4t-a95b`) | $2.00 | $6.00 | $0.25 | 1.05M |
| Qwen3.8 Max (0902) (`qwen/qwen3.8-max-0902`) | $2.00 | $6.00 | $0.25 | 1M |
| GPT-5.2 (batch) (`openai/gpt-5.2:batch`) | $0.88 | $7.00 | $0.087 | 400K |
| Claude Sonnet 4.5 (batch) (`anthropic/claude-sonnet-4.5:batch`) | $1.50 | $7.50 | $0.15 | 1M |
| Claude Sonnet 4.6 (batch) (`anthropic/claude-sonnet-4.6:batch`) | $1.50 | $7.50 | $0.15 | 1M |
| GPT-5.4 (batch) (`openai/gpt-5.4:batch`) | $1.25 | $7.50 | $0.13 | 1.05M |
| Mistral Medium 3.5 (`mistralai/mistral-medium-3-5`) | $1.50 | $7.50 | — | 262K |
| Nano Banana 2.1 (`google/gemini-nano-banana-2.1`) | $1.50 | $7.50 | — | 66K |
| Sonar Deep Research (`perplexity/sonar-deep-research`) | $2.00 | $8.00 | — | 128K |
| Sonar Reasoning Pro (`perplexity/sonar-reasoning-pro`) | $2.00 | $8.00 | — | 128K |
| MiMo-V2.6-Pro-UltraSpeed (`xiaomi/mimo-v2.6-pro-ultraspeed`) | $4.35 | $8.70 | $0.036 | 1.05M |
| GLM 5.3 Prime (`z-ai/glm-5.3-prime`) | $2.80 | $8.80 | $0.56 | 1M |
| Claude Opus 5.5 (batch) (`anthropic/claude-opus-5.5:batch`) | $2.00 | $10.00 | $0.10 | 1M |
| Command R+ (08-2024) (`cohere/command-r-plus-08-2024`) | $2.50 | $10.00 | — | 128K |
| GPT Audio (`openai/gpt-audio`) | $2.50 | $10.00 | — | 128K |
| GPT-4o (2024-08-06) (`openai/gpt-4o-2024-08-06`) | $2.50 | $10.00 | $1.25 | 128K |
| GPT-4o (2024-11-20) (`openai/gpt-4o-2024-11-20`) | $2.50 | $10.00 | $1.25 | 128K |
| GPT-5 (`openai/gpt-5`) | $1.25 | $10.00 | $0.13 | 400K |
| GPT-5 Image (`openai/gpt-5-image`) | $10.00 | $10.00 | $1.25 | 400K |
| GPT-5.6 Sol (batch) (`openai/gpt-5.6-sol:batch`) | $2.00 | $10.00 | $0.20 | 1.05M |
| GPT-5.6 Sol Pro (batch) (`openai/gpt-5.6-sol-pro:batch`) | $2.00 | $10.00 | $0.20 | 1.05M |
| GPT-6 Sol Pro (`openai/gpt-6-sol-pro`) | $2.00 | $10.00 | $0.20 | 1.05M |
| GPT-6.1 Sol Pro (`openai/gpt-6.1-sol-pro`) | $2.00 | $10.00 | $0.10 | 1.05M |
| Kimi K3 (batch) (`moonshotai/kimi-k3:batch`) | $2.28 | $11.40 | $0.23 | 1.05M |
| Gemini 3.1 Pro Preview Custom Tools (`google/gemini-3.1-pro-preview-customtools`) | $2.00 | $12.00 | $0.20 | 1.05M |
| GPT-5.6 Terra Pro (`openai/gpt-5.6-terra-pro`) | $2.00 | $12.00 | $0.20 | 1.05M |
| Nano Banana Pro (Gemini 3 Pro Image Preview) (`google/gemini-3-pro-image-preview`) | $2.00 | $12.00 | $0.20 | 66K |
| Nano Banana Pro (Gemini 3 Pro Image) (`google/gemini-3-pro-image`) | $2.00 | $12.00 | $0.20 | 131K |
| Qwen3.8 Max Prime (`qwen/qwen3.8-max-prime`) | $4.00 | $12.00 | $0.50 | 1M |
| Claude Opus 4.5 (batch) (`anthropic/claude-opus-4.5:batch`) | $2.50 | $12.50 | $0.25 | 200K |
| Claude Opus 4.6 (batch) (`anthropic/claude-opus-4.6:batch`) | $2.50 | $12.50 | $0.25 | 1M |
| Claude Opus 4.7 (batch) (`anthropic/claude-opus-4.7:batch`) | $2.50 | $12.50 | $0.25 | 1M |
| Claude Opus 4.8 (batch) (`anthropic/claude-opus-4.8:batch`) | $2.50 | $12.50 | $0.25 | 1M |
| Claude Opus 5 (batch) (`anthropic/claude-opus-5:batch`) | $2.50 | $12.50 | $0.25 | 1M |
| Nova Premier 1.0 (`amazon/nova-premier-v1`) | $2.50 | $12.50 | $0.63 | 1M |
| GPT-5.2 Chat (`openai/gpt-5.2-chat`) | $1.75 | $14.00 | $0.17 | 128K |
| GPT-4 Turbo (batch) (`openai/gpt-4-turbo:batch`) | $5.00 | $15.00 | — | 128K |
| GPT-4o (2024-05-13) (`openai/gpt-4o-2024-05-13`) | $5.00 | $15.00 | — | 128K |
| GPT-5.4 Image 2 (`openai/gpt-5.4-image-2`) | $8.00 | $15.00 | $2.00 | 272K |
| GPT-5.5 (batch) (`openai/gpt-5.5:batch`) | $2.50 | $15.00 | $0.25 | 1.05M |
| Sonar Pro (`perplexity/sonar-pro`) | $3.00 | $15.00 | — | 200K |
| Sonar Pro Search (`perplexity/sonar-pro-search`) | $3.00 | $15.00 | — | 200K |
| GPT-5.6 Sol Pro (`openai/gpt-5.6-sol-pro`) | $4.00 | $20.00 | $0.40 | 1.05M |
| Claude Fable 5 (batch) (`anthropic/claude-fable-5:batch`) | $5.00 | $25.00 | $0.50 | 1M |
| Claude Fable 5.1 (batch) (`anthropic/claude-fable-5.1:batch`) | $5.00 | $25.00 | $0.13 | 1M |
| GPT-6 Astra (batch) (`openai/gpt-6-astra:batch`) | $5.00 | $25.00 | $0.50 | 1.05M |
| GPT-6 Astra Pro (batch) (`openai/gpt-6-astra-pro:batch`) | $5.00 | $25.00 | $0.50 | 1.05M |
| Fugu Ultra v2 (`sakana/fugu-ultra-v2`) | $5.00 | $30.00 | $0.50 | 1M |
| GPT Chat Latest (`openai/gpt-chat-latest`) | $5.00 | $30.00 | $0.50 | 400K |
| Claude Opus 4.1 (batch) (`anthropic/claude-opus-4.1:batch`) | $7.50 | $37.50 | $0.75 | 200K |
| GPT-6 Astra Pro (`openai/gpt-6-astra-pro`) | $10.00 | $50.00 | $1.00 | 1.05M |
| GPT-4 (`openai/gpt-4`) | $30.00 | $60.00 | — | 8K |
| GPT-5 Pro (batch) (`openai/gpt-5-pro:batch`) | $7.50 | $60.00 | — | 400K |
| Claude Opus 4.1 (`anthropic/claude-opus-4.1`) | $15.00 | $75.00 | $1.50 | 200K |
| GPT-5.2 Pro (batch) (`openai/gpt-5.2-pro:batch`) | $10.50 | $84.00 | — | 400K |
| GPT-5.4 Pro (batch) (`openai/gpt-5.4-pro:batch`) | $15.00 | $90.00 | — | 1.05M |
| GPT-5.5 Pro (batch) (`openai/gpt-5.5-pro:batch`) | $15.00 | $90.00 | — | 1.05M |
| GPT-5 Pro (`openai/gpt-5-pro`) | $15.00 | $120.00 | — | 400K |

## Billing notes

- Per-token prices follow the provider OpenRouter routes the request to, so the rate in its catalog is the default route’s rate, not a fixed OpenRouter price.
- Credits are prepaid. Models whose ID ends in :free cost nothing per token and run under request caps described on our free-tier page.

## What we measured (2026-09-01)

OpenRouter posted the fastest median latency on both reference models, the lowest invoiced cost per million tokens on DeepSeek Flash, and GLM-5.2 within 23% of the cheapest platform. No alternative in this run was both cheaper and faster on either model.

| Model run | Invoiced /1M blended | Median latency | p95 latency | Succeeded |
|---|---|---|---|---|
| DeepSeek V4 Flash | $0.044 | 0.76 s | 2.59 s | 99.8% |
| GLM-5.2 | $0.464 | 1.20 s | 3.69 s | 100.0% |

Method and invoices: https://benchlm.ai/openrouter-alternatives

## Hosts that sell the same models

- [DeepInfra](https://benchlm.ai/hosts/deepinfra): 57 shared, 12 cheaper per output token (GPT-OSS 120B: $0.17 vs $0.60)
- [Novita AI](https://benchlm.ai/hosts/novita): 48 shared, 6 cheaper per output token (GPT-OSS 120B: $0.25 vs $0.60)
- [Together AI](https://benchlm.ai/hosts/together): 18 shared, 1 cheaper per output token (DeepSeek V4 Flash 0731: $0.28 vs $0.39)
- [Nebius Token Factory](https://benchlm.ai/hosts/nebius): 17 shared, 2 cheaper per output token (DeepSeek V4 Flash 0731: $0.28 vs $0.39)
- [Baseten](https://benchlm.ai/hosts/baseten): 9 shared, 2 cheaper per output token (DeepSeek V4 Flash 0731: $0.26 vs $0.39)
- [Fireworks AI](https://benchlm.ai/hosts/fireworks): 9 shared, 0 cheaper per output token

## FAQ

### How much does the OpenRouter API cost?

OpenRouter bills per million tokens, with separate input and output rates for each model. On October 20, 2026 its output rates ran from $0.03 on Mistral Nemo to $600.00 across 422 paid models. Input is usually cheaper than output, so a long prompt with a short reply costs less than the output rate suggests.

### Which models can you run on OpenRouter?

441 text models are listed, and 185 of them match a model we score. The highest-scoring is Claude Opus 5 at 88. The table on this page has every model with its input, output and cached-input rate, the context window, and the date we read the price.

### Is OpenRouter fast?

In our paid September 1, 2026 run, OpenRouter returned a median of 0.76 seconds on DeepSeek V4 Flash and 1.20 seconds on GLM-5.2, over 450 requests per model. That is one workload on one date, so check your own prompts before you rely on it.

### What are the alternatives to OpenRouter?

DeepInfra lists 57 of the same models and charges less output per token on 12 of them. Novita AI and Together AI also overlap. Price is only part of the choice: speed, rate limits and which model snapshot a host serves differ too.

Canonical page: https://benchlm.ai/hosts/openrouter