surp/best-chat $0.012 ↓ │
surp/best-coding $0.034 ↑ │
usdc/base $1.00 │
tps 847 ↑ │
ttft 120ms ↓ │
cache 20.69% hist / 0 live │
models live 224 │
srp pool 2.4M ↑ │
surp/best-chat $0.012 ↓ │
surp/best-coding $0.034 ↑ │
usdc/base $1.00 │
tps 847 ↑ │
ttft 120ms ↓ │
cache 20.69% hist / 0 live │
models live 224 │
srp pool 2.4M ↑ │
compare models
surp --diff model-a model-b
Compare AI model pricing side by side. Pick 2-4 models and see their strengths, weaknesses, cost per token , and which is cheapest for your task. All models are OpenAI-compatible and available via our x402 gateway with pay-per-request pricing.
Need a recommendation instead? Find the right model for your task · See top 5 leaderboards · Browse all 150+ models
model A
choose... openai-gpt-oss-20b ($0.0010/1M) deepseek-v4.1-flash ($0.0010/1M) gemma-3-4b-it ($0.0011/1M) minimax-m2.1 ($0.0018/1M) gemma-4-26b-a4b-it ($0.0019/1M) gemma-3-12b-it ($0.0020/1M) ministral-3-3b-instruct ($0.0020/1M) glm-4.7-flash ($0.0023/1M) glm-5.2 ($0.0027/1M) deepseek-v4-flash-0731 ($0.0027/1M) gemma-3-27b-it ($0.0028/1M) muse-spark-1.3-contributor ($0.0030/1M) gemini-2.5-flash-image ($0.0033/1M) openai-gpt-oss-120b ($0.0033/1M) qwen3-coder-30b-a3b-instruct ($0.0035/1M) openai-gpt-oss-safeguard-20b ($0.0035/1M) qwen3-32b ($0.0036/1M) gemma-4-31b ($0.0036/1M) gemma-4-31b-it ($0.0036/1M) ministral-3-8b-instruct ($0.0037/1M) nvidia-nemotron-3-nano-30b-a3b ($0.0037/1M) ministral-3-14b-instruct ($0.0040/1M) qwen3-235b-a22b-2507 ($0.0040/1M) glm-4.5-air ($0.0052/1M) glm-5.3-flash ($0.0053/1M) nvidia-nemotron-3-super-120b ($0.0053/1M) nvidia-nemotron-nano-9b-v2 ($0.0054/1M) gemma-4-e2b ($0.0059/1M) kimi-k2.6 ($0.0061/1M) qwen3.8-flash ($0.0061/1M) hy3 ($0.0062/1M) deepseek-v3.2 ($0.0065/1M) qwen3.8-max-0902 ($0.0069/1M) glm-5.3 ($0.0074/1M) muse-spark-1.2-contributor ($0.0075/1M) qwen3.8-omni-flash ($0.0077/1M) nvidia-nemotron-nano-12b-v2 ($0.0089/1M) qwen3.8-2.4t-a95b ($0.0089/1M) qwen3-coder-next ($0.0091/1M) qwen3-next-80b-a3b-instruct ($0.0103/1M) qwen-3-8-27b ($0.0108/1M) minimax-m2 ($0.0116/1M) deepseek-v3.1 ($0.0119/1M) minimax-m2.5 ($0.0121/1M) qwen3-coder ($0.0129/1M) openai-gpt-oss-safeguard-120b ($0.0129/1M) glm-4.7 ($0.0132/1M) mistral-small-3.2-24b-instruct ($0.0138/1M) gpt-5.6-luna ($0.0141/1M) minimax-m3 ($0.0158/1M) palmyra-vision-7b ($0.0168/1M) gemini-3.1-flash-lite ($0.0173/1M) gpt-6-luna ($0.0178/1M) deepseek-v4-pro ($0.0190/1M) qwen3-vl-235b-a22b-instruct ($0.0209/1M) glm-4.6 ($0.0216/1M) gpt-4o-mini ($0.0223/1M) glm-5 ($0.0229/1M) kimi-k2.5 ($0.0249/1M) glm-4.5 ($0.0277/1M) gemini-2.5-flash ($0.0280/1M) magistral-small-2509 ($0.0293/1M) nvidia-nemotron-3-ultra-550b-a55b ($0.0300/1M) kimi-k2-thinking ($0.0307/1M) claude-opus-4.6 ($0.0328/1M) llama-3.3-70b-instruct ($0.0349/1M) gemini-3-flash-preview ($0.0350/1M) grok-4.3 ($0.0371/1M) qwen3.7-flash ($0.0400/1M) deepseek-v4-flash ($0.0449/1M) gemini-3.7-flash ($0.0450/1M) glm-5.1 ($0.0458/1M) devstral-2-123b ($0.0494/1M) inkling ($0.0495/1M) minimax-m2.7 ($0.0503/1M) e2ee-qwen-2-5-7b-p ($0.0514/1M) glm-5-turbo ($0.0515/1M) gpt-5-nano ($0.0540/1M) muse-spark-1.3 ($0.0550/1M) claude-haiku-5.5 ($0.0600/1M) e2ee-gpt-oss-20b-p ($0.0600/1M) mimo-v2.6-flash ($0.0629/1M) deepseek-v4-pro-0813 ($0.0633/1M) gemini-3.8-flash ($0.0723/1M) grok-4.7 ($0.0730/1M) deepseek-v4.1-flash-1017 ($0.0742/1M) kimi-k3 ($0.0801/1M) mistral-large-3 ($0.0990/1M) qwen3-6-35b-a3b ($0.1035/1M) grok-4.5 ($0.1036/1M) gemini-3-5-flash ($0.1050/1M) muse-spark-1.1 ($0.1100/1M) muse-spark-1.2 ($0.1100/1M) claude-sonnet-4.6 ($0.1124/1M) qwen3-5-9b ($0.1250/1M) kimi-k2.7-code ($0.1260/1M) gpt-5.3-codex ($0.1268/1M) gpt-5-mini ($0.1349/1M) glm-5.3-prime ($0.1413/1M) gpt-5-image-mini ($0.1446/1M) gpt-5.6-terra ($0.1449/1M) qwen3.5-397b-a17b ($0.1579/1M) glm-4.7-flash-heretic ($0.1742/1M) qwen3-235b-a22b-thinking-2507 ($0.1820/1M) llama-3.2-3b-instruct ($0.1900/1M) mercury-2.5 ($0.1995/1M) nvidia-nemotron-3-5-lightning-30b-a3b ($0.2240/1M) mistral-small-4 ($0.2344/1M) claude-opus-4.7 ($0.2414/1M) e2ee-gemma-3-27b ($0.2560/1M) mimo-v2.6-pro ($0.2576/1M) mistral-small-3.2-24b-instruct:web ($0.2578/1M) xiaomi-mimo-v2-5 ($0.2620/1M) gpt-6-sol ($0.2692/1M) qwen3.6-27b ($0.2711/1M) openai-gpt-oss-120b:web ($0.2775/1M) gpt-5.4-nano ($0.2900/1M) deepseek-v4.1-flash-uncensored ($0.2968/1M) e2ee-gpt-oss-120b-p ($0.3025/1M) gemma-4-uncensored ($0.3312/1M) claude-haiku-4.5 ($0.3564/1M) qwen3-5-35b-a3b ($0.3624/1M) venice-uncensored-1.2 ($0.3626/1M) mistral-large ($0.3712/1M) gpt-4o ($0.3725/1M) gpt-5.6-sol ($0.3750/1M) deepseek-v4-flash:web ($0.3900/1M) mimo-v2.5-pro ($0.3915/1M) e2ee-gemma-4-31b ($0.4000/1M) gpt-6.1-sol ($0.4170/1M) e2ee-qwen3-6-35b-a3b ($0.4197/1M) qwen3.5-flash ($0.4250/1M) gpt-5.4 ($0.4251/1M) e2ee-gemma-4-26b-a4b-uncensored-p ($0.4276/1M) qwen3-30b-a3b ($0.4297/1M) e2ee-deepseek-v4-flash ($0.4384/1M) gpt-5.4-image-2 ($0.4701/1M) muse-wonder ($0.4800/1M) gemma-4-26b-a4b-it:web ($0.4969/1M) glm-4.7-flash:web ($0.5100/1M) gpt-5.4-mini ($0.5240/1M) grok-4.20-multi-agent-beta ($0.5250/1M) grok-4.20-beta ($0.5250/1M) qwen3-vl-30b-a3b-thinking ($0.5500/1M) llama-3.2-3b-instruct:web ($0.5625/1M) gpt-5-image ($0.5800/1M) deepseek-v4-flash-0731-fast ($0.6195/1M) mercury-2 ($0.6225/1M) gpt-6-astra ($0.6419/1M) qwen3-235b-a22b-2507:web ($0.6750/1M) gpt-5.6-luna-pro ($0.6944/1M) claude-sonnet-5 ($0.7092/1M) minimax-m3-1-flash ($0.7500/1M) qwen3-vl-235b-a22b-thinking ($0.7558/1M) hermes-3-llama-3.1-405b ($0.7992/1M) e2ee-qwen3-6-35b-a3b-uncensored-p ($0.8000/1M) qwen-3-7-plus ($0.8242/1M) venice-uncensored ($0.8250/1M) trinity-large-thinking ($0.8295/1M) gpt-5.5 ($0.8749/1M) qwen3-coder-turbo ($0.9250/1M) gpt-5.2 ($0.9434/1M) venice-uncensored-role-play ($0.9740/1M) qwen-3-8-max ($1.0187/1M) claude-opus-5 ($1.0500/1M) trinity-large-thinking:web ($1.0781/1M) minimax-m3-preview ($1.1250/1M) minimax-m2.5:web ($1.1475/1M) seed-2-1-turbo ($1.1857/1M) claude-sonnet-5.5 ($1.2406/1M) grok-4.6 ($1.3491/1M) glm-5.3-flashx ($1.3770/1M) gemini-3-5-flash-lite ($1.3857/1M) minimax-m2.7:web ($1.4062/1M) gemini-3.1-pro ($1.5369/1M) qwen3.5-plus ($1.5470/1M) aion-labs-aion-3-0-mini ($1.5750/1M) qwen3-next-80b-a3b-instruct:web ($1.6875/1M) qwen3.6-plus-uncensored ($1.7063/1M) glm-4.7-thinking ($1.8375/1M) glm-4.7-thinking:web ($1.8375/1M) glm-5v-turbo ($1.8801/1M) grok-build-0-1 ($1.9481/1M) kimi-k2 ($2.0090/1M) aion-labs.aion-2-0 ($2.0400/1M) e2ee-glm-5.1 ($2.1000/1M) claude-opus-4.5 ($2.2032/1M) claude-opus-4.8 ($2.3730/1M) gemini-3-6-flash ($2.4498/1M) claude-opus-5.5 ($2.4704/1M) minimax-m2.7-highspeed ($2.5500/1M) llama-3.3-70b-instruct:web ($2.6250/1M) gemini-2.5-pro ($2.7000/1M) e2ee-glm-5-2-p ($2.9940/1M) kimi-k2.5:web ($3.0450/1M) hermes-3-llama-3.1-405b:web ($3.0750/1M) gemini-4-argon ($3.5856/1M) gpt-5.2-codex ($3.9375/1M) glm-5:web ($3.9375/1M) glm-4.7:web ($3.9375/1M) qwen-3-7-max ($4.0000/1M) kimi-k2.6:web ($4.1288/1M) deepseek-v4-pro:web ($4.1445/1M) claude-sonnet-4.5 ($4.3667/1M) muse-spark-open ($4.4000/1M) aion-labs-aion-3-0 ($4.5000/1M) abliteration-abliterated-model-large-v2 ($4.8152/1M) glm-5.1-non-thinking:web ($4.8750/1M) glm-5.1-non-thinking ($4.8750/1M) glm-5.1:web ($5.4375/1M) gemini-3.1-pro-preview ($5.4531/1M) claude-fable-5.1 ($6.6000/1M) gpt-5.6-terra-pro ($8.6627/1M) gpt-5.6-sol-pro ($9.4800/1M) mimo-v2.6-pro-ultraspeed ($9.6570/1M) claude-fable-5 ($9.8654/1M) qwen3.8-max-prime ($13.6000/1M) kimi-k3-fast-api ($19.9773/1M) claude-opus-5-fast ($23.4050/1M) claude-opus-4-8-fast ($24.8268/1M) gpt-5.4-pro ($29.0430/1M) gpt-5.5-pro ($62.8112/1M) claude-opus-4.6-fast ($162.0000/1M) claude-opus-4-7-fast ($162.0000/1M)
model B
choose... openai-gpt-oss-20b ($0.0010/1M) deepseek-v4.1-flash ($0.0010/1M) gemma-3-4b-it ($0.0011/1M) minimax-m2.1 ($0.0018/1M) gemma-4-26b-a4b-it ($0.0019/1M) gemma-3-12b-it ($0.0020/1M) ministral-3-3b-instruct ($0.0020/1M) glm-4.7-flash ($0.0023/1M) glm-5.2 ($0.0027/1M) deepseek-v4-flash-0731 ($0.0027/1M) gemma-3-27b-it ($0.0028/1M) muse-spark-1.3-contributor ($0.0030/1M) gemini-2.5-flash-image ($0.0033/1M) openai-gpt-oss-120b ($0.0033/1M) qwen3-coder-30b-a3b-instruct ($0.0035/1M) openai-gpt-oss-safeguard-20b ($0.0035/1M) qwen3-32b ($0.0036/1M) gemma-4-31b ($0.0036/1M) gemma-4-31b-it ($0.0036/1M) ministral-3-8b-instruct ($0.0037/1M) nvidia-nemotron-3-nano-30b-a3b ($0.0037/1M) ministral-3-14b-instruct ($0.0040/1M) qwen3-235b-a22b-2507 ($0.0040/1M) glm-4.5-air ($0.0052/1M) glm-5.3-flash ($0.0053/1M) nvidia-nemotron-3-super-120b ($0.0053/1M) nvidia-nemotron-nano-9b-v2 ($0.0054/1M) gemma-4-e2b ($0.0059/1M) kimi-k2.6 ($0.0061/1M) qwen3.8-flash ($0.0061/1M) hy3 ($0.0062/1M) deepseek-v3.2 ($0.0065/1M) qwen3.8-max-0902 ($0.0069/1M) glm-5.3 ($0.0074/1M) muse-spark-1.2-contributor ($0.0075/1M) qwen3.8-omni-flash ($0.0077/1M) nvidia-nemotron-nano-12b-v2 ($0.0089/1M) qwen3.8-2.4t-a95b ($0.0089/1M) qwen3-coder-next ($0.0091/1M) qwen3-next-80b-a3b-instruct ($0.0103/1M) qwen-3-8-27b ($0.0108/1M) minimax-m2 ($0.0116/1M) deepseek-v3.1 ($0.0119/1M) minimax-m2.5 ($0.0121/1M) qwen3-coder ($0.0129/1M) openai-gpt-oss-safeguard-120b ($0.0129/1M) glm-4.7 ($0.0132/1M) mistral-small-3.2-24b-instruct ($0.0138/1M) gpt-5.6-luna ($0.0141/1M) minimax-m3 ($0.0158/1M) palmyra-vision-7b ($0.0168/1M) gemini-3.1-flash-lite ($0.0173/1M) gpt-6-luna ($0.0178/1M) deepseek-v4-pro ($0.0190/1M) qwen3-vl-235b-a22b-instruct ($0.0209/1M) glm-4.6 ($0.0216/1M) gpt-4o-mini ($0.0223/1M) glm-5 ($0.0229/1M) kimi-k2.5 ($0.0249/1M) glm-4.5 ($0.0277/1M) gemini-2.5-flash ($0.0280/1M) magistral-small-2509 ($0.0293/1M) nvidia-nemotron-3-ultra-550b-a55b ($0.0300/1M) kimi-k2-thinking ($0.0307/1M) claude-opus-4.6 ($0.0328/1M) llama-3.3-70b-instruct ($0.0349/1M) gemini-3-flash-preview ($0.0350/1M) grok-4.3 ($0.0371/1M) qwen3.7-flash ($0.0400/1M) deepseek-v4-flash ($0.0449/1M) gemini-3.7-flash ($0.0450/1M) glm-5.1 ($0.0458/1M) devstral-2-123b ($0.0494/1M) inkling ($0.0495/1M) minimax-m2.7 ($0.0503/1M) e2ee-qwen-2-5-7b-p ($0.0514/1M) glm-5-turbo ($0.0515/1M) gpt-5-nano ($0.0540/1M) muse-spark-1.3 ($0.0550/1M) claude-haiku-5.5 ($0.0600/1M) e2ee-gpt-oss-20b-p ($0.0600/1M) mimo-v2.6-flash ($0.0629/1M) deepseek-v4-pro-0813 ($0.0633/1M) gemini-3.8-flash ($0.0723/1M) grok-4.7 ($0.0730/1M) deepseek-v4.1-flash-1017 ($0.0742/1M) kimi-k3 ($0.0801/1M) mistral-large-3 ($0.0990/1M) qwen3-6-35b-a3b ($0.1035/1M) grok-4.5 ($0.1036/1M) gemini-3-5-flash ($0.1050/1M) muse-spark-1.1 ($0.1100/1M) muse-spark-1.2 ($0.1100/1M) claude-sonnet-4.6 ($0.1124/1M) qwen3-5-9b ($0.1250/1M) kimi-k2.7-code ($0.1260/1M) gpt-5.3-codex ($0.1268/1M) gpt-5-mini ($0.1349/1M) glm-5.3-prime ($0.1413/1M) gpt-5-image-mini ($0.1446/1M) gpt-5.6-terra ($0.1449/1M) qwen3.5-397b-a17b ($0.1579/1M) glm-4.7-flash-heretic ($0.1742/1M) qwen3-235b-a22b-thinking-2507 ($0.1820/1M) llama-3.2-3b-instruct ($0.1900/1M) mercury-2.5 ($0.1995/1M) nvidia-nemotron-3-5-lightning-30b-a3b ($0.2240/1M) mistral-small-4 ($0.2344/1M) claude-opus-4.7 ($0.2414/1M) e2ee-gemma-3-27b ($0.2560/1M) mimo-v2.6-pro ($0.2576/1M) mistral-small-3.2-24b-instruct:web ($0.2578/1M) xiaomi-mimo-v2-5 ($0.2620/1M) gpt-6-sol ($0.2692/1M) qwen3.6-27b ($0.2711/1M) openai-gpt-oss-120b:web ($0.2775/1M) gpt-5.4-nano ($0.2900/1M) deepseek-v4.1-flash-uncensored ($0.2968/1M) e2ee-gpt-oss-120b-p ($0.3025/1M) gemma-4-uncensored ($0.3312/1M) claude-haiku-4.5 ($0.3564/1M) qwen3-5-35b-a3b ($0.3624/1M) venice-uncensored-1.2 ($0.3626/1M) mistral-large ($0.3712/1M) gpt-4o ($0.3725/1M) gpt-5.6-sol ($0.3750/1M) deepseek-v4-flash:web ($0.3900/1M) mimo-v2.5-pro ($0.3915/1M) e2ee-gemma-4-31b ($0.4000/1M) gpt-6.1-sol ($0.4170/1M) e2ee-qwen3-6-35b-a3b ($0.4197/1M) qwen3.5-flash ($0.4250/1M) gpt-5.4 ($0.4251/1M) e2ee-gemma-4-26b-a4b-uncensored-p ($0.4276/1M) qwen3-30b-a3b ($0.4297/1M) e2ee-deepseek-v4-flash ($0.4384/1M) gpt-5.4-image-2 ($0.4701/1M) muse-wonder ($0.4800/1M) gemma-4-26b-a4b-it:web ($0.4969/1M) glm-4.7-flash:web ($0.5100/1M) gpt-5.4-mini ($0.5240/1M) grok-4.20-multi-agent-beta ($0.5250/1M) grok-4.20-beta ($0.5250/1M) qwen3-vl-30b-a3b-thinking ($0.5500/1M) llama-3.2-3b-instruct:web ($0.5625/1M) gpt-5-image ($0.5800/1M) deepseek-v4-flash-0731-fast ($0.6195/1M) mercury-2 ($0.6225/1M) gpt-6-astra ($0.6419/1M) qwen3-235b-a22b-2507:web ($0.6750/1M) gpt-5.6-luna-pro ($0.6944/1M) claude-sonnet-5 ($0.7092/1M) minimax-m3-1-flash ($0.7500/1M) qwen3-vl-235b-a22b-thinking ($0.7558/1M) hermes-3-llama-3.1-405b ($0.7992/1M) e2ee-qwen3-6-35b-a3b-uncensored-p ($0.8000/1M) qwen-3-7-plus ($0.8242/1M) venice-uncensored ($0.8250/1M) trinity-large-thinking ($0.8295/1M) gpt-5.5 ($0.8749/1M) qwen3-coder-turbo ($0.9250/1M) gpt-5.2 ($0.9434/1M) venice-uncensored-role-play ($0.9740/1M) qwen-3-8-max ($1.0187/1M) claude-opus-5 ($1.0500/1M) trinity-large-thinking:web ($1.0781/1M) minimax-m3-preview ($1.1250/1M) minimax-m2.5:web ($1.1475/1M) seed-2-1-turbo ($1.1857/1M) claude-sonnet-5.5 ($1.2406/1M) grok-4.6 ($1.3491/1M) glm-5.3-flashx ($1.3770/1M) gemini-3-5-flash-lite ($1.3857/1M) minimax-m2.7:web ($1.4062/1M) gemini-3.1-pro ($1.5369/1M) qwen3.5-plus ($1.5470/1M) aion-labs-aion-3-0-mini ($1.5750/1M) qwen3-next-80b-a3b-instruct:web ($1.6875/1M) qwen3.6-plus-uncensored ($1.7063/1M) glm-4.7-thinking ($1.8375/1M) glm-4.7-thinking:web ($1.8375/1M) glm-5v-turbo ($1.8801/1M) grok-build-0-1 ($1.9481/1M) kimi-k2 ($2.0090/1M) aion-labs.aion-2-0 ($2.0400/1M) e2ee-glm-5.1 ($2.1000/1M) claude-opus-4.5 ($2.2032/1M) claude-opus-4.8 ($2.3730/1M) gemini-3-6-flash ($2.4498/1M) claude-opus-5.5 ($2.4704/1M) minimax-m2.7-highspeed ($2.5500/1M) llama-3.3-70b-instruct:web ($2.6250/1M) gemini-2.5-pro ($2.7000/1M) e2ee-glm-5-2-p ($2.9940/1M) kimi-k2.5:web ($3.0450/1M) hermes-3-llama-3.1-405b:web ($3.0750/1M) gemini-4-argon ($3.5856/1M) gpt-5.2-codex ($3.9375/1M) glm-5:web ($3.9375/1M) glm-4.7:web ($3.9375/1M) qwen-3-7-max ($4.0000/1M) kimi-k2.6:web ($4.1288/1M) deepseek-v4-pro:web ($4.1445/1M) claude-sonnet-4.5 ($4.3667/1M) muse-spark-open ($4.4000/1M) aion-labs-aion-3-0 ($4.5000/1M) abliteration-abliterated-model-large-v2 ($4.8152/1M) glm-5.1-non-thinking:web ($4.8750/1M) glm-5.1-non-thinking ($4.8750/1M) glm-5.1:web ($5.4375/1M) gemini-3.1-pro-preview ($5.4531/1M) claude-fable-5.1 ($6.6000/1M) gpt-5.6-terra-pro ($8.6627/1M) gpt-5.6-sol-pro ($9.4800/1M) mimo-v2.6-pro-ultraspeed ($9.6570/1M) claude-fable-5 ($9.8654/1M) qwen3.8-max-prime ($13.6000/1M) kimi-k3-fast-api ($19.9773/1M) claude-opus-5-fast ($23.4050/1M) claude-opus-4-8-fast ($24.8268/1M) gpt-5.4-pro ($29.0430/1M) gpt-5.5-pro ($62.8112/1M) claude-opus-4.6-fast ($162.0000/1M) claude-opus-4-7-fast ($162.0000/1M)
model C (optional)
choose... openai-gpt-oss-20b ($0.0010/1M) deepseek-v4.1-flash ($0.0010/1M) gemma-3-4b-it ($0.0011/1M) minimax-m2.1 ($0.0018/1M) gemma-4-26b-a4b-it ($0.0019/1M) gemma-3-12b-it ($0.0020/1M) ministral-3-3b-instruct ($0.0020/1M) glm-4.7-flash ($0.0023/1M) glm-5.2 ($0.0027/1M) deepseek-v4-flash-0731 ($0.0027/1M) gemma-3-27b-it ($0.0028/1M) muse-spark-1.3-contributor ($0.0030/1M) gemini-2.5-flash-image ($0.0033/1M) openai-gpt-oss-120b ($0.0033/1M) qwen3-coder-30b-a3b-instruct ($0.0035/1M) openai-gpt-oss-safeguard-20b ($0.0035/1M) qwen3-32b ($0.0036/1M) gemma-4-31b ($0.0036/1M) gemma-4-31b-it ($0.0036/1M) ministral-3-8b-instruct ($0.0037/1M) nvidia-nemotron-3-nano-30b-a3b ($0.0037/1M) ministral-3-14b-instruct ($0.0040/1M) qwen3-235b-a22b-2507 ($0.0040/1M) glm-4.5-air ($0.0052/1M) glm-5.3-flash ($0.0053/1M) nvidia-nemotron-3-super-120b ($0.0053/1M) nvidia-nemotron-nano-9b-v2 ($0.0054/1M) gemma-4-e2b ($0.0059/1M) kimi-k2.6 ($0.0061/1M) qwen3.8-flash ($0.0061/1M) hy3 ($0.0062/1M) deepseek-v3.2 ($0.0065/1M) qwen3.8-max-0902 ($0.0069/1M) glm-5.3 ($0.0074/1M) muse-spark-1.2-contributor ($0.0075/1M) qwen3.8-omni-flash ($0.0077/1M) nvidia-nemotron-nano-12b-v2 ($0.0089/1M) qwen3.8-2.4t-a95b ($0.0089/1M) qwen3-coder-next ($0.0091/1M) qwen3-next-80b-a3b-instruct ($0.0103/1M) qwen-3-8-27b ($0.0108/1M) minimax-m2 ($0.0116/1M) deepseek-v3.1 ($0.0119/1M) minimax-m2.5 ($0.0121/1M) qwen3-coder ($0.0129/1M) openai-gpt-oss-safeguard-120b ($0.0129/1M) glm-4.7 ($0.0132/1M) mistral-small-3.2-24b-instruct ($0.0138/1M) gpt-5.6-luna ($0.0141/1M) minimax-m3 ($0.0158/1M) palmyra-vision-7b ($0.0168/1M) gemini-3.1-flash-lite ($0.0173/1M) gpt-6-luna ($0.0178/1M) deepseek-v4-pro ($0.0190/1M) qwen3-vl-235b-a22b-instruct ($0.0209/1M) glm-4.6 ($0.0216/1M) gpt-4o-mini ($0.0223/1M) glm-5 ($0.0229/1M) kimi-k2.5 ($0.0249/1M) glm-4.5 ($0.0277/1M) gemini-2.5-flash ($0.0280/1M) magistral-small-2509 ($0.0293/1M) nvidia-nemotron-3-ultra-550b-a55b ($0.0300/1M) kimi-k2-thinking ($0.0307/1M) claude-opus-4.6 ($0.0328/1M) llama-3.3-70b-instruct ($0.0349/1M) gemini-3-flash-preview ($0.0350/1M) grok-4.3 ($0.0371/1M) qwen3.7-flash ($0.0400/1M) deepseek-v4-flash ($0.0449/1M) gemini-3.7-flash ($0.0450/1M) glm-5.1 ($0.0458/1M) devstral-2-123b ($0.0494/1M) inkling ($0.0495/1M) minimax-m2.7 ($0.0503/1M) e2ee-qwen-2-5-7b-p ($0.0514/1M) glm-5-turbo ($0.0515/1M) gpt-5-nano ($0.0540/1M) muse-spark-1.3 ($0.0550/1M) claude-haiku-5.5 ($0.0600/1M) e2ee-gpt-oss-20b-p ($0.0600/1M) mimo-v2.6-flash ($0.0629/1M) deepseek-v4-pro-0813 ($0.0633/1M) gemini-3.8-flash ($0.0723/1M) grok-4.7 ($0.0730/1M) deepseek-v4.1-flash-1017 ($0.0742/1M) kimi-k3 ($0.0801/1M) mistral-large-3 ($0.0990/1M) qwen3-6-35b-a3b ($0.1035/1M) grok-4.5 ($0.1036/1M) gemini-3-5-flash ($0.1050/1M) muse-spark-1.1 ($0.1100/1M) muse-spark-1.2 ($0.1100/1M) claude-sonnet-4.6 ($0.1124/1M) qwen3-5-9b ($0.1250/1M) kimi-k2.7-code ($0.1260/1M) gpt-5.3-codex ($0.1268/1M) gpt-5-mini ($0.1349/1M) glm-5.3-prime ($0.1413/1M) gpt-5-image-mini ($0.1446/1M) gpt-5.6-terra ($0.1449/1M) qwen3.5-397b-a17b ($0.1579/1M) glm-4.7-flash-heretic ($0.1742/1M) qwen3-235b-a22b-thinking-2507 ($0.1820/1M) llama-3.2-3b-instruct ($0.1900/1M) mercury-2.5 ($0.1995/1M) nvidia-nemotron-3-5-lightning-30b-a3b ($0.2240/1M) mistral-small-4 ($0.2344/1M) claude-opus-4.7 ($0.2414/1M) e2ee-gemma-3-27b ($0.2560/1M) mimo-v2.6-pro ($0.2576/1M) mistral-small-3.2-24b-instruct:web ($0.2578/1M) xiaomi-mimo-v2-5 ($0.2620/1M) gpt-6-sol ($0.2692/1M) qwen3.6-27b ($0.2711/1M) openai-gpt-oss-120b:web ($0.2775/1M) gpt-5.4-nano ($0.2900/1M) deepseek-v4.1-flash-uncensored ($0.2968/1M) e2ee-gpt-oss-120b-p ($0.3025/1M) gemma-4-uncensored ($0.3312/1M) claude-haiku-4.5 ($0.3564/1M) qwen3-5-35b-a3b ($0.3624/1M) venice-uncensored-1.2 ($0.3626/1M) mistral-large ($0.3712/1M) gpt-4o ($0.3725/1M) gpt-5.6-sol ($0.3750/1M) deepseek-v4-flash:web ($0.3900/1M) mimo-v2.5-pro ($0.3915/1M) e2ee-gemma-4-31b ($0.4000/1M) gpt-6.1-sol ($0.4170/1M) e2ee-qwen3-6-35b-a3b ($0.4197/1M) qwen3.5-flash ($0.4250/1M) gpt-5.4 ($0.4251/1M) e2ee-gemma-4-26b-a4b-uncensored-p ($0.4276/1M) qwen3-30b-a3b ($0.4297/1M) e2ee-deepseek-v4-flash ($0.4384/1M) gpt-5.4-image-2 ($0.4701/1M) muse-wonder ($0.4800/1M) gemma-4-26b-a4b-it:web ($0.4969/1M) glm-4.7-flash:web ($0.5100/1M) gpt-5.4-mini ($0.5240/1M) grok-4.20-multi-agent-beta ($0.5250/1M) grok-4.20-beta ($0.5250/1M) qwen3-vl-30b-a3b-thinking ($0.5500/1M) llama-3.2-3b-instruct:web ($0.5625/1M) gpt-5-image ($0.5800/1M) deepseek-v4-flash-0731-fast ($0.6195/1M) mercury-2 ($0.6225/1M) gpt-6-astra ($0.6419/1M) qwen3-235b-a22b-2507:web ($0.6750/1M) gpt-5.6-luna-pro ($0.6944/1M) claude-sonnet-5 ($0.7092/1M) minimax-m3-1-flash ($0.7500/1M) qwen3-vl-235b-a22b-thinking ($0.7558/1M) hermes-3-llama-3.1-405b ($0.7992/1M) e2ee-qwen3-6-35b-a3b-uncensored-p ($0.8000/1M) qwen-3-7-plus ($0.8242/1M) venice-uncensored ($0.8250/1M) trinity-large-thinking ($0.8295/1M) gpt-5.5 ($0.8749/1M) qwen3-coder-turbo ($0.9250/1M) gpt-5.2 ($0.9434/1M) venice-uncensored-role-play ($0.9740/1M) qwen-3-8-max ($1.0187/1M) claude-opus-5 ($1.0500/1M) trinity-large-thinking:web ($1.0781/1M) minimax-m3-preview ($1.1250/1M) minimax-m2.5:web ($1.1475/1M) seed-2-1-turbo ($1.1857/1M) claude-sonnet-5.5 ($1.2406/1M) grok-4.6 ($1.3491/1M) glm-5.3-flashx ($1.3770/1M) gemini-3-5-flash-lite ($1.3857/1M) minimax-m2.7:web ($1.4062/1M) gemini-3.1-pro ($1.5369/1M) qwen3.5-plus ($1.5470/1M) aion-labs-aion-3-0-mini ($1.5750/1M) qwen3-next-80b-a3b-instruct:web ($1.6875/1M) qwen3.6-plus-uncensored ($1.7063/1M) glm-4.7-thinking ($1.8375/1M) glm-4.7-thinking:web ($1.8375/1M) glm-5v-turbo ($1.8801/1M) grok-build-0-1 ($1.9481/1M) kimi-k2 ($2.0090/1M) aion-labs.aion-2-0 ($2.0400/1M) e2ee-glm-5.1 ($2.1000/1M) claude-opus-4.5 ($2.2032/1M) claude-opus-4.8 ($2.3730/1M) gemini-3-6-flash ($2.4498/1M) claude-opus-5.5 ($2.4704/1M) minimax-m2.7-highspeed ($2.5500/1M) llama-3.3-70b-instruct:web ($2.6250/1M) gemini-2.5-pro ($2.7000/1M) e2ee-glm-5-2-p ($2.9940/1M) kimi-k2.5:web ($3.0450/1M) hermes-3-llama-3.1-405b:web ($3.0750/1M) gemini-4-argon ($3.5856/1M) gpt-5.2-codex ($3.9375/1M) glm-5:web ($3.9375/1M) glm-4.7:web ($3.9375/1M) qwen-3-7-max ($4.0000/1M) kimi-k2.6:web ($4.1288/1M) deepseek-v4-pro:web ($4.1445/1M) claude-sonnet-4.5 ($4.3667/1M) muse-spark-open ($4.4000/1M) aion-labs-aion-3-0 ($4.5000/1M) abliteration-abliterated-model-large-v2 ($4.8152/1M) glm-5.1-non-thinking:web ($4.8750/1M) glm-5.1-non-thinking ($4.8750/1M) glm-5.1:web ($5.4375/1M) gemini-3.1-pro-preview ($5.4531/1M) claude-fable-5.1 ($6.6000/1M) gpt-5.6-terra-pro ($8.6627/1M) gpt-5.6-sol-pro ($9.4800/1M) mimo-v2.6-pro-ultraspeed ($9.6570/1M) claude-fable-5 ($9.8654/1M) qwen3.8-max-prime ($13.6000/1M) kimi-k3-fast-api ($19.9773/1M) claude-opus-5-fast ($23.4050/1M) claude-opus-4-8-fast ($24.8268/1M) gpt-5.4-pro ($29.0430/1M) gpt-5.5-pro ($62.8112/1M) claude-opus-4.6-fast ($162.0000/1M) claude-opus-4-7-fast ($162.0000/1M)
▶ compare