surp/free $0.00 free │
surp/best-chat $0.012 ↓ │
surp/best-coding $0.034 ↑ │
usdc/base $1.00 │
tps 847 ↑ │
ttft 120ms ↓ │
cache hit 34% ↑ │
models live 1,204 │
srp pool 2.4M ↑ │
surp/free $0.00 free │
surp/best-chat $0.012 ↓ │
surp/best-coding $0.034 ↑ │
usdc/base $1.00 │
tps 847 ↑ │
ttft 120ms ↓ │
cache hit 34% ↑ │
models live 1,204 │
srp pool 2.4M ↑ │
surp.ivc.lol
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... gemma-3-4b-it ($0.0108/1M) glm-5.2 ($0.0128/1M) ministral-3-3b-instruct ($0.0180/1M) glm-4.7 ($0.0215/1M) openai-gpt-oss-safeguard-20b ($0.0243/1M) gemma-3-27b-it ($0.0252/1M) nvidia-nemotron-nano-9b-v2 ($0.0261/1M) ministral-3-8b-instruct ($0.0270/1M) deepseek-v4-flash-0731 ($0.0277/1M) qwen3-235b-a22b-2507 ($0.0280/1M) deepseek-v4-flash ($0.0297/1M) openai-gpt-oss-20b ($0.0333/1M) gemma-3-12b-it ($0.0342/1M) mistral-small-3.2-24b-instruct ($0.0344/1M) ministral-3-14b-instruct ($0.0360/1M) glm-4.5-air ($0.0390/1M) glm-4.7-flash ($0.0414/1M) e2ee-qwen-2-5-7b-p ($0.0432/1M) qwen3-5-9b ($0.0500/1M) gemini-2.5-flash-image ($0.0500/1M) openai-gpt-oss-120b:web ($0.0555/1M) e2ee-gpt-oss-20b-p ($0.0575/1M) glm-4.6 ($0.0654/1M) openai-gpt-oss-safeguard-120b ($0.0675/1M) palmyra-vision-7b ($0.0675/1M) qwen3-coder-30b-a3b-instruct ($0.0675/1M) nvidia-nemotron-nano-12b-v2 ($0.0720/1M) deepseek-v4-flash:web ($0.0780/1M) qwen3-235b-a22b-thinking-2507 ($0.0800/1M) gemma-4-31b-it ($0.0825/1M) glm-4.5 ($0.0840/1M) llama-3.3-70b-instruct ($0.0840/1M) gpt-5-nano ($0.0900/1M) openai-gpt-oss-120b ($0.0924/1M) nvidia-nemotron-3-nano-30b-a3b ($0.0937/1M) gpt-5.6-luna ($0.0980/1M) glm-5 ($0.1008/1M) gemma-4-31b-it:web ($0.1013/1M) qwen3-next-80b-a3b-instruct ($0.1080/1M) llama-3.2-3b-instruct ($0.1140/1M) qwen3-coder ($0.1170/1M) gemma-4-26b-a4b-it ($0.1324/1M) mistral-small-3.2-24b-instruct:web ($0.1375/1M) glm-4.7-flash-heretic ($0.1409/1M) deepseek-v4-pro ($0.1436/1M) minimax-m2.7 ($0.1500/1M) gpt-4o-mini ($0.1500/1M) deepseek-v3.2 ($0.1673/1M) glm-4.7-flash:web ($0.1700/1M) mistral-large-3 ($0.1800/1M) magistral-small-2509 ($0.1800/1M) qwen3-32b ($0.1875/1M) e2ee-gemma-3-27b ($0.1920/1M) gemma-4-uncensored ($0.1988/1M) minimax-m3 ($0.2000/1M) nvidia-nemotron-3-super-120b ($0.2000/1M) deepseek-v3.1 ($0.2034/1M) qwen3-30b-a3b ($0.2046/1M) glm-5-turbo ($0.2080/1M) gpt-5.6-luna-pro ($0.2100/1M) devstral-2-123b ($0.2160/1M) nvidia-nemotron-cascade-2-30b-a3b ($0.2256/1M) qwen3-6-35b-a3b ($0.2280/1M) e2ee-gpt-oss-120b-p ($0.2338/1M) qwen3-5-35b-a3b ($0.2344/1M) e2ee-gemma-4-31b ($0.2398/1M) minimax-m2.5 ($0.2400/1M) gemma-4-26b-a4b-it:web ($0.2650/1M) qwen3-vl-30b-a3b-thinking ($0.2750/1M) kimi-k2-thinking ($0.2790/1M) mistral-small-4 ($0.2812/1M) qwen3-vl-235b-a22b-instruct ($0.2871/1M) gpt-5.4-nano ($0.2900/1M) llama-3.2-3b-instruct:web ($0.3000/1M) qwen3.5-flash ($0.3250/1M) venice-uncensored-1.2 ($0.3297/1M) venice-uncensored ($0.3300/1M) e2ee-venice-uncensored-24b-p ($0.3360/1M) qwen3-235b-a22b-2507:web ($0.3600/1M) e2ee-gemma-4-26b-a4b-uncensored-p ($0.3621/1M) gpt-5-image-mini ($0.3739/1M) mercury-2 ($0.3746/1M) minimax-m2.1 ($0.3750/1M) minimax-m2 ($0.3750/1M) minimax-m2.5:web ($0.3825/1M) qwen3-coder-next ($0.4250/1M) grok-4.1-fast ($0.4375/1M) deepseek-v4-pro-0813 ($0.4443/1M) gpt-5-mini ($0.4500/1M) minimax-m2.7:web ($0.4688/1M) e2ee-qwen3-6-35b-a3b ($0.4795/1M) qwen3-vl-235b-a22b-thinking ($0.4825/1M) glm-5.1 ($0.5104/1M) glm-5:web ($0.5250/1M) deepseek-v4-pro:web ($0.5526/1M) qwen3-coder-turbo ($0.5550/1M) glm-4.7-thinking:web ($0.6125/1M) qwen3.5-plus ($0.6370/1M) kimi-k2.6 ($0.6375/1M) glm-5.1-non-thinking:web ($0.6500/1M) gemini-3.7-flash ($0.6750/1M) gpt-5.4-mini ($0.6825/1M) trinity-large-thinking ($0.6900/1M) nvidia-nemotron-3-ultra-550b-a55b ($0.7200/1M) hy3 ($0.7200/1M) glm-5.1:web ($0.7250/1M) venice-uncensored-role-play ($0.7492/1M) qwen-3-7-plus ($0.7492/1M) glm-5.2:web ($0.7950/1M) e2ee-qwen3-6-35b-a3b-uncensored-p ($0.7992/1M) mistral-large ($0.8000/1M) kimi-k2.5 ($0.8516/1M) qwen3-next-80b-a3b-instruct:web ($0.9000/1M) gemini-3.1-flash-lite ($0.9625/1M) glm-5.1-non-thinking ($0.9750/1M) gemini-2.5-flash ($0.9800/1M) kimi-k2.5:web ($1.0150/1M) gemini-3-flash-preview ($1.0271/1M) kimi-k2.7-code ($1.0514/1M) qwen3.6-27b ($1.0714/1M) trinity-large-thinking:web ($1.0781/1M) kimi-k3 ($1.0800/1M) grok-4.20-multi-agent-beta ($1.1239/1M) grok-4.20-beta ($1.1239/1M) e2ee-qwen3-5-122b-a10b ($1.1250/1M) claude-haiku-4.5 ($1.2000/1M) aion-labs.aion-2-0 ($1.2000/1M) gpt-5.4-image-2 ($1.2158/1M) hermes-3-llama-3.1-405b ($1.2288/1M) e2ee-glm-5.1 ($1.2587/1M) qwen3.5-397b-a17b ($1.2587/1M) e2ee-glm-4.7 ($1.2600/1M) gpt-5.6-terra ($1.2600/1M) grok-4.3 ($1.2737/1M) qwen3.6-plus-uncensored ($1.3125/1M) glm-4.7:web ($1.3125/1M) kimi-k2.7-code:web ($1.3497/1M) llama-3.3-70b-instruct:web ($1.4000/1M) grok-code-fast-1 ($1.4455/1M) gpt-5-image ($1.5000/1M) glm-5v-turbo ($1.5584/1M) hermes-3-llama-3.1-405b:web ($1.6400/1M) glm-4.7-thinking ($1.8375/1M) grok-4.5 ($1.8400/1M) gpt-5.4 ($1.9250/1M) minimax-m2.7-highspeed ($1.9500/1M) qwen3.8-2.4t-a95b ($2.0000/1M) kimi-k2 ($2.0090/1M) gpt-5.6-terra-pro ($2.1000/1M) kimi-k2.6:web ($2.2020/1M) deepseek-r1 ($2.2400/1M) grok-4.6 ($2.3840/1M) grok-build-0-1 ($2.3976/1M) claude-sonnet-5 ($2.4000/1M) qwen-3-7-max ($2.4000/1M) gemini-3-5-flash ($2.4187/1M) gpt-5.6-sol ($2.4500/1M) gpt-4o ($2.5000/1M) claude-sonnet-4.6 ($2.7000/1M) qwen-3-8-max ($2.9400/1M) gpt-5.2 ($3.1500/1M) claude-opus-5 ($3.3000/1M) gemini-3.1-pro-preview ($3.3600/1M) gpt-5.5 ($3.5000/1M) claude-sonnet-4.5 ($3.6000/1M) claude-opus-4.6 ($3.9000/1M) claude-opus-4.7 ($3.9000/1M) gpt-5.3-codex ($3.9336/1M) gpt-5.2-codex ($5.1975/1M) gemini-2.5-pro ($5.6250/1M) gpt-5.6-sol-pro ($7.0000/1M) claude-opus-4.8 ($7.1928/1M) claude-opus-4.5 ($7.3287/1M) gemini-3.1-pro ($7.7000/1M) claude-fable-5 ($14.4000/1M) grok-4 ($15.3000/1M) claude-opus-5-fast ($17.6047/1M) claude-opus-4-8-fast ($21.6000/1M) gpt-5.4-pro ($52.4475/1M) claude-opus-4.6-fast ($54.0000/1M) gpt-5.5-pro ($65.5594/1M) claude-opus-4-7-fast ($71.2800/1M)
model B
choose... gemma-3-4b-it ($0.0108/1M) glm-5.2 ($0.0128/1M) ministral-3-3b-instruct ($0.0180/1M) glm-4.7 ($0.0215/1M) openai-gpt-oss-safeguard-20b ($0.0243/1M) gemma-3-27b-it ($0.0252/1M) nvidia-nemotron-nano-9b-v2 ($0.0261/1M) ministral-3-8b-instruct ($0.0270/1M) deepseek-v4-flash-0731 ($0.0277/1M) qwen3-235b-a22b-2507 ($0.0280/1M) deepseek-v4-flash ($0.0297/1M) openai-gpt-oss-20b ($0.0333/1M) gemma-3-12b-it ($0.0342/1M) mistral-small-3.2-24b-instruct ($0.0344/1M) ministral-3-14b-instruct ($0.0360/1M) glm-4.5-air ($0.0390/1M) glm-4.7-flash ($0.0414/1M) e2ee-qwen-2-5-7b-p ($0.0432/1M) qwen3-5-9b ($0.0500/1M) gemini-2.5-flash-image ($0.0500/1M) openai-gpt-oss-120b:web ($0.0555/1M) e2ee-gpt-oss-20b-p ($0.0575/1M) glm-4.6 ($0.0654/1M) openai-gpt-oss-safeguard-120b ($0.0675/1M) palmyra-vision-7b ($0.0675/1M) qwen3-coder-30b-a3b-instruct ($0.0675/1M) nvidia-nemotron-nano-12b-v2 ($0.0720/1M) deepseek-v4-flash:web ($0.0780/1M) qwen3-235b-a22b-thinking-2507 ($0.0800/1M) gemma-4-31b-it ($0.0825/1M) glm-4.5 ($0.0840/1M) llama-3.3-70b-instruct ($0.0840/1M) gpt-5-nano ($0.0900/1M) openai-gpt-oss-120b ($0.0924/1M) nvidia-nemotron-3-nano-30b-a3b ($0.0937/1M) gpt-5.6-luna ($0.0980/1M) glm-5 ($0.1008/1M) gemma-4-31b-it:web ($0.1013/1M) qwen3-next-80b-a3b-instruct ($0.1080/1M) llama-3.2-3b-instruct ($0.1140/1M) qwen3-coder ($0.1170/1M) gemma-4-26b-a4b-it ($0.1324/1M) mistral-small-3.2-24b-instruct:web ($0.1375/1M) glm-4.7-flash-heretic ($0.1409/1M) deepseek-v4-pro ($0.1436/1M) minimax-m2.7 ($0.1500/1M) gpt-4o-mini ($0.1500/1M) deepseek-v3.2 ($0.1673/1M) glm-4.7-flash:web ($0.1700/1M) mistral-large-3 ($0.1800/1M) magistral-small-2509 ($0.1800/1M) qwen3-32b ($0.1875/1M) e2ee-gemma-3-27b ($0.1920/1M) gemma-4-uncensored ($0.1988/1M) minimax-m3 ($0.2000/1M) nvidia-nemotron-3-super-120b ($0.2000/1M) deepseek-v3.1 ($0.2034/1M) qwen3-30b-a3b ($0.2046/1M) glm-5-turbo ($0.2080/1M) gpt-5.6-luna-pro ($0.2100/1M) devstral-2-123b ($0.2160/1M) nvidia-nemotron-cascade-2-30b-a3b ($0.2256/1M) qwen3-6-35b-a3b ($0.2280/1M) e2ee-gpt-oss-120b-p ($0.2338/1M) qwen3-5-35b-a3b ($0.2344/1M) e2ee-gemma-4-31b ($0.2398/1M) minimax-m2.5 ($0.2400/1M) gemma-4-26b-a4b-it:web ($0.2650/1M) qwen3-vl-30b-a3b-thinking ($0.2750/1M) kimi-k2-thinking ($0.2790/1M) mistral-small-4 ($0.2812/1M) qwen3-vl-235b-a22b-instruct ($0.2871/1M) gpt-5.4-nano ($0.2900/1M) llama-3.2-3b-instruct:web ($0.3000/1M) qwen3.5-flash ($0.3250/1M) venice-uncensored-1.2 ($0.3297/1M) venice-uncensored ($0.3300/1M) e2ee-venice-uncensored-24b-p ($0.3360/1M) qwen3-235b-a22b-2507:web ($0.3600/1M) e2ee-gemma-4-26b-a4b-uncensored-p ($0.3621/1M) gpt-5-image-mini ($0.3739/1M) mercury-2 ($0.3746/1M) minimax-m2.1 ($0.3750/1M) minimax-m2 ($0.3750/1M) minimax-m2.5:web ($0.3825/1M) qwen3-coder-next ($0.4250/1M) grok-4.1-fast ($0.4375/1M) deepseek-v4-pro-0813 ($0.4443/1M) gpt-5-mini ($0.4500/1M) minimax-m2.7:web ($0.4688/1M) e2ee-qwen3-6-35b-a3b ($0.4795/1M) qwen3-vl-235b-a22b-thinking ($0.4825/1M) glm-5.1 ($0.5104/1M) glm-5:web ($0.5250/1M) deepseek-v4-pro:web ($0.5526/1M) qwen3-coder-turbo ($0.5550/1M) glm-4.7-thinking:web ($0.6125/1M) qwen3.5-plus ($0.6370/1M) kimi-k2.6 ($0.6375/1M) glm-5.1-non-thinking:web ($0.6500/1M) gemini-3.7-flash ($0.6750/1M) gpt-5.4-mini ($0.6825/1M) trinity-large-thinking ($0.6900/1M) nvidia-nemotron-3-ultra-550b-a55b ($0.7200/1M) hy3 ($0.7200/1M) glm-5.1:web ($0.7250/1M) venice-uncensored-role-play ($0.7492/1M) qwen-3-7-plus ($0.7492/1M) glm-5.2:web ($0.7950/1M) e2ee-qwen3-6-35b-a3b-uncensored-p ($0.7992/1M) mistral-large ($0.8000/1M) kimi-k2.5 ($0.8516/1M) qwen3-next-80b-a3b-instruct:web ($0.9000/1M) gemini-3.1-flash-lite ($0.9625/1M) glm-5.1-non-thinking ($0.9750/1M) gemini-2.5-flash ($0.9800/1M) kimi-k2.5:web ($1.0150/1M) gemini-3-flash-preview ($1.0271/1M) kimi-k2.7-code ($1.0514/1M) qwen3.6-27b ($1.0714/1M) trinity-large-thinking:web ($1.0781/1M) kimi-k3 ($1.0800/1M) grok-4.20-multi-agent-beta ($1.1239/1M) grok-4.20-beta ($1.1239/1M) e2ee-qwen3-5-122b-a10b ($1.1250/1M) claude-haiku-4.5 ($1.2000/1M) aion-labs.aion-2-0 ($1.2000/1M) gpt-5.4-image-2 ($1.2158/1M) hermes-3-llama-3.1-405b ($1.2288/1M) e2ee-glm-5.1 ($1.2587/1M) qwen3.5-397b-a17b ($1.2587/1M) e2ee-glm-4.7 ($1.2600/1M) gpt-5.6-terra ($1.2600/1M) grok-4.3 ($1.2737/1M) qwen3.6-plus-uncensored ($1.3125/1M) glm-4.7:web ($1.3125/1M) kimi-k2.7-code:web ($1.3497/1M) llama-3.3-70b-instruct:web ($1.4000/1M) grok-code-fast-1 ($1.4455/1M) gpt-5-image ($1.5000/1M) glm-5v-turbo ($1.5584/1M) hermes-3-llama-3.1-405b:web ($1.6400/1M) glm-4.7-thinking ($1.8375/1M) grok-4.5 ($1.8400/1M) gpt-5.4 ($1.9250/1M) minimax-m2.7-highspeed ($1.9500/1M) qwen3.8-2.4t-a95b ($2.0000/1M) kimi-k2 ($2.0090/1M) gpt-5.6-terra-pro ($2.1000/1M) kimi-k2.6:web ($2.2020/1M) deepseek-r1 ($2.2400/1M) grok-4.6 ($2.3840/1M) grok-build-0-1 ($2.3976/1M) claude-sonnet-5 ($2.4000/1M) qwen-3-7-max ($2.4000/1M) gemini-3-5-flash ($2.4187/1M) gpt-5.6-sol ($2.4500/1M) gpt-4o ($2.5000/1M) claude-sonnet-4.6 ($2.7000/1M) qwen-3-8-max ($2.9400/1M) gpt-5.2 ($3.1500/1M) claude-opus-5 ($3.3000/1M) gemini-3.1-pro-preview ($3.3600/1M) gpt-5.5 ($3.5000/1M) claude-sonnet-4.5 ($3.6000/1M) claude-opus-4.6 ($3.9000/1M) claude-opus-4.7 ($3.9000/1M) gpt-5.3-codex ($3.9336/1M) gpt-5.2-codex ($5.1975/1M) gemini-2.5-pro ($5.6250/1M) gpt-5.6-sol-pro ($7.0000/1M) claude-opus-4.8 ($7.1928/1M) claude-opus-4.5 ($7.3287/1M) gemini-3.1-pro ($7.7000/1M) claude-fable-5 ($14.4000/1M) grok-4 ($15.3000/1M) claude-opus-5-fast ($17.6047/1M) claude-opus-4-8-fast ($21.6000/1M) gpt-5.4-pro ($52.4475/1M) claude-opus-4.6-fast ($54.0000/1M) gpt-5.5-pro ($65.5594/1M) claude-opus-4-7-fast ($71.2800/1M)
model C (optional)
choose... gemma-3-4b-it ($0.0108/1M) glm-5.2 ($0.0128/1M) ministral-3-3b-instruct ($0.0180/1M) glm-4.7 ($0.0215/1M) openai-gpt-oss-safeguard-20b ($0.0243/1M) gemma-3-27b-it ($0.0252/1M) nvidia-nemotron-nano-9b-v2 ($0.0261/1M) ministral-3-8b-instruct ($0.0270/1M) deepseek-v4-flash-0731 ($0.0277/1M) qwen3-235b-a22b-2507 ($0.0280/1M) deepseek-v4-flash ($0.0297/1M) openai-gpt-oss-20b ($0.0333/1M) gemma-3-12b-it ($0.0342/1M) mistral-small-3.2-24b-instruct ($0.0344/1M) ministral-3-14b-instruct ($0.0360/1M) glm-4.5-air ($0.0390/1M) glm-4.7-flash ($0.0414/1M) e2ee-qwen-2-5-7b-p ($0.0432/1M) qwen3-5-9b ($0.0500/1M) gemini-2.5-flash-image ($0.0500/1M) openai-gpt-oss-120b:web ($0.0555/1M) e2ee-gpt-oss-20b-p ($0.0575/1M) glm-4.6 ($0.0654/1M) openai-gpt-oss-safeguard-120b ($0.0675/1M) palmyra-vision-7b ($0.0675/1M) qwen3-coder-30b-a3b-instruct ($0.0675/1M) nvidia-nemotron-nano-12b-v2 ($0.0720/1M) deepseek-v4-flash:web ($0.0780/1M) qwen3-235b-a22b-thinking-2507 ($0.0800/1M) gemma-4-31b-it ($0.0825/1M) glm-4.5 ($0.0840/1M) llama-3.3-70b-instruct ($0.0840/1M) gpt-5-nano ($0.0900/1M) openai-gpt-oss-120b ($0.0924/1M) nvidia-nemotron-3-nano-30b-a3b ($0.0937/1M) gpt-5.6-luna ($0.0980/1M) glm-5 ($0.1008/1M) gemma-4-31b-it:web ($0.1013/1M) qwen3-next-80b-a3b-instruct ($0.1080/1M) llama-3.2-3b-instruct ($0.1140/1M) qwen3-coder ($0.1170/1M) gemma-4-26b-a4b-it ($0.1324/1M) mistral-small-3.2-24b-instruct:web ($0.1375/1M) glm-4.7-flash-heretic ($0.1409/1M) deepseek-v4-pro ($0.1436/1M) minimax-m2.7 ($0.1500/1M) gpt-4o-mini ($0.1500/1M) deepseek-v3.2 ($0.1673/1M) glm-4.7-flash:web ($0.1700/1M) mistral-large-3 ($0.1800/1M) magistral-small-2509 ($0.1800/1M) qwen3-32b ($0.1875/1M) e2ee-gemma-3-27b ($0.1920/1M) gemma-4-uncensored ($0.1988/1M) minimax-m3 ($0.2000/1M) nvidia-nemotron-3-super-120b ($0.2000/1M) deepseek-v3.1 ($0.2034/1M) qwen3-30b-a3b ($0.2046/1M) glm-5-turbo ($0.2080/1M) gpt-5.6-luna-pro ($0.2100/1M) devstral-2-123b ($0.2160/1M) nvidia-nemotron-cascade-2-30b-a3b ($0.2256/1M) qwen3-6-35b-a3b ($0.2280/1M) e2ee-gpt-oss-120b-p ($0.2338/1M) qwen3-5-35b-a3b ($0.2344/1M) e2ee-gemma-4-31b ($0.2398/1M) minimax-m2.5 ($0.2400/1M) gemma-4-26b-a4b-it:web ($0.2650/1M) qwen3-vl-30b-a3b-thinking ($0.2750/1M) kimi-k2-thinking ($0.2790/1M) mistral-small-4 ($0.2812/1M) qwen3-vl-235b-a22b-instruct ($0.2871/1M) gpt-5.4-nano ($0.2900/1M) llama-3.2-3b-instruct:web ($0.3000/1M) qwen3.5-flash ($0.3250/1M) venice-uncensored-1.2 ($0.3297/1M) venice-uncensored ($0.3300/1M) e2ee-venice-uncensored-24b-p ($0.3360/1M) qwen3-235b-a22b-2507:web ($0.3600/1M) e2ee-gemma-4-26b-a4b-uncensored-p ($0.3621/1M) gpt-5-image-mini ($0.3739/1M) mercury-2 ($0.3746/1M) minimax-m2.1 ($0.3750/1M) minimax-m2 ($0.3750/1M) minimax-m2.5:web ($0.3825/1M) qwen3-coder-next ($0.4250/1M) grok-4.1-fast ($0.4375/1M) deepseek-v4-pro-0813 ($0.4443/1M) gpt-5-mini ($0.4500/1M) minimax-m2.7:web ($0.4688/1M) e2ee-qwen3-6-35b-a3b ($0.4795/1M) qwen3-vl-235b-a22b-thinking ($0.4825/1M) glm-5.1 ($0.5104/1M) glm-5:web ($0.5250/1M) deepseek-v4-pro:web ($0.5526/1M) qwen3-coder-turbo ($0.5550/1M) glm-4.7-thinking:web ($0.6125/1M) qwen3.5-plus ($0.6370/1M) kimi-k2.6 ($0.6375/1M) glm-5.1-non-thinking:web ($0.6500/1M) gemini-3.7-flash ($0.6750/1M) gpt-5.4-mini ($0.6825/1M) trinity-large-thinking ($0.6900/1M) nvidia-nemotron-3-ultra-550b-a55b ($0.7200/1M) hy3 ($0.7200/1M) glm-5.1:web ($0.7250/1M) venice-uncensored-role-play ($0.7492/1M) qwen-3-7-plus ($0.7492/1M) glm-5.2:web ($0.7950/1M) e2ee-qwen3-6-35b-a3b-uncensored-p ($0.7992/1M) mistral-large ($0.8000/1M) kimi-k2.5 ($0.8516/1M) qwen3-next-80b-a3b-instruct:web ($0.9000/1M) gemini-3.1-flash-lite ($0.9625/1M) glm-5.1-non-thinking ($0.9750/1M) gemini-2.5-flash ($0.9800/1M) kimi-k2.5:web ($1.0150/1M) gemini-3-flash-preview ($1.0271/1M) kimi-k2.7-code ($1.0514/1M) qwen3.6-27b ($1.0714/1M) trinity-large-thinking:web ($1.0781/1M) kimi-k3 ($1.0800/1M) grok-4.20-multi-agent-beta ($1.1239/1M) grok-4.20-beta ($1.1239/1M) e2ee-qwen3-5-122b-a10b ($1.1250/1M) claude-haiku-4.5 ($1.2000/1M) aion-labs.aion-2-0 ($1.2000/1M) gpt-5.4-image-2 ($1.2158/1M) hermes-3-llama-3.1-405b ($1.2288/1M) e2ee-glm-5.1 ($1.2587/1M) qwen3.5-397b-a17b ($1.2587/1M) e2ee-glm-4.7 ($1.2600/1M) gpt-5.6-terra ($1.2600/1M) grok-4.3 ($1.2737/1M) qwen3.6-plus-uncensored ($1.3125/1M) glm-4.7:web ($1.3125/1M) kimi-k2.7-code:web ($1.3497/1M) llama-3.3-70b-instruct:web ($1.4000/1M) grok-code-fast-1 ($1.4455/1M) gpt-5-image ($1.5000/1M) glm-5v-turbo ($1.5584/1M) hermes-3-llama-3.1-405b:web ($1.6400/1M) glm-4.7-thinking ($1.8375/1M) grok-4.5 ($1.8400/1M) gpt-5.4 ($1.9250/1M) minimax-m2.7-highspeed ($1.9500/1M) qwen3.8-2.4t-a95b ($2.0000/1M) kimi-k2 ($2.0090/1M) gpt-5.6-terra-pro ($2.1000/1M) kimi-k2.6:web ($2.2020/1M) deepseek-r1 ($2.2400/1M) grok-4.6 ($2.3840/1M) grok-build-0-1 ($2.3976/1M) claude-sonnet-5 ($2.4000/1M) qwen-3-7-max ($2.4000/1M) gemini-3-5-flash ($2.4187/1M) gpt-5.6-sol ($2.4500/1M) gpt-4o ($2.5000/1M) claude-sonnet-4.6 ($2.7000/1M) qwen-3-8-max ($2.9400/1M) gpt-5.2 ($3.1500/1M) claude-opus-5 ($3.3000/1M) gemini-3.1-pro-preview ($3.3600/1M) gpt-5.5 ($3.5000/1M) claude-sonnet-4.5 ($3.6000/1M) claude-opus-4.6 ($3.9000/1M) claude-opus-4.7 ($3.9000/1M) gpt-5.3-codex ($3.9336/1M) gpt-5.2-codex ($5.1975/1M) gemini-2.5-pro ($5.6250/1M) gpt-5.6-sol-pro ($7.0000/1M) claude-opus-4.8 ($7.1928/1M) claude-opus-4.5 ($7.3287/1M) gemini-3.1-pro ($7.7000/1M) claude-fable-5 ($14.4000/1M) grok-4 ($15.3000/1M) claude-opus-5-fast ($17.6047/1M) claude-opus-4-8-fast ($21.6000/1M) gpt-5.4-pro ($52.4475/1M) claude-opus-4.6-fast ($54.0000/1M) gpt-5.5-pro ($65.5594/1M) claude-opus-4-7-fast ($71.2800/1M)
▶ compare