surp/free $0.00 free │
surp/best-chat $0.012 ↓ │
surp/best-coding $0.034 ↑ │
usdc/base $1.00 │
tps 847 ↑ │
ttft 120ms ↓ │
cache 23.08% hist / 0 live │
models live 227 │
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 23.08% hist / 0 live │
models live 227 │
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... jev-1.13 ($0.0004/1M) openai-gpt-oss-20b ($0.0011/1M) gemma-3-4b-it ($0.0015/1M) gemma-4-26b-a4b-it ($0.0020/1M) gemma-3-12b-it ($0.0020/1M) deepseek-v4.1-flash ($0.0021/1M) ministral-3-3b-instruct ($0.0022/1M) gemma-3-27b-it ($0.0028/1M) gemini-2.5-flash-image ($0.0033/1M) qwen3-coder-30b-a3b-instruct ($0.0035/1M) qwen3-32b ($0.0036/1M) openai-gpt-oss-120b ($0.0037/1M) nvidia-nemotron-3-nano-30b-a3b ($0.0037/1M) gemma-4-31b ($0.0043/1M) gemma-4-31b-it ($0.0043/1M) ministral-3-14b-instruct ($0.0045/1M) glm-4.7-flash ($0.0046/1M) ministral-3-8b-instruct ($0.0046/1M) glm-4.5-air ($0.0052/1M) nvidia-nemotron-nano-9b-v2 ($0.0057/1M) gpt-6-luna ($0.0058/1M) qwen3.8-flash ($0.0062/1M) qwen3-235b-a22b-2507 ($0.0064/1M) glm-5.3-flash ($0.0065/1M) deepseek-v3.2 ($0.0066/1M) gemma-4-e2b ($0.0072/1M) openai-gpt-oss-safeguard-20b ($0.0074/1M) nvidia-nemotron-3-super-120b ($0.0080/1M) nvidia-nemotron-nano-12b-v2 ($0.0090/1M) qwen3-coder-next ($0.0091/1M) deepseek-v4-flash ($0.0091/1M) qwen3-next-80b-a3b-instruct ($0.0107/1M) gemini-3.8-flash ($0.0109/1M) minimax-m2.5 ($0.0121/1M) qwen3-coder ($0.0129/1M) openai-gpt-oss-safeguard-120b ($0.0148/1M) minimax-m2.1 ($0.0150/1M) minimax-m2 ($0.0150/1M) minimax-m3 ($0.0151/1M) glm-4.7 ($0.0152/1M) palmyra-vision-7b ($0.0170/1M) glm-5.2 ($0.0171/1M) mistral-small-3.2-24b-instruct ($0.0171/1M) qwen3.8-omni-flash ($0.0173/1M) gemini-3.1-flash-lite ($0.0175/1M) gpt-5.6-luna ($0.0184/1M) deepseek-v3.1 ($0.0205/1M) deepseek-v4-pro ($0.0211/1M) qwen3-vl-235b-a22b-instruct ($0.0211/1M) glm-4.6 ($0.0216/1M) gemini-3.7-flash ($0.0238/1M) glm-5 ($0.0249/1M) kimi-k2.5 ($0.0267/1M) minimax-m2.7 ($0.0273/1M) glm-4.5 ($0.0277/1M) gemini-2.5-flash ($0.0280/1M) nvidia-nemotron-3-ultra-550b-a55b ($0.0300/1M) kimi-k2-thinking ($0.0310/1M) gemini-3-flash-preview ($0.0350/1M) deepseek-v4-flash-0731 ($0.0360/1M) gpt-4o-mini ($0.0375/1M) magistral-small-2509 ($0.0396/1M) e2ee-qwen-2-5-7b-p ($0.0424/1M) glm-5.3 ($0.0431/1M) muse-spark-1.2-contributor ($0.0450/1M) muse-spark-1.3-contributor ($0.0450/1M) glm-5-turbo ($0.0515/1M) devstral-2-123b ($0.0547/1M) glm-5.1 ($0.0572/1M) llama-3.3-70b-instruct ($0.0588/1M) e2ee-gpt-oss-20b-p ($0.0600/1M) kimi-k2.7-code ($0.0603/1M) qwen3-5-9b ($0.0618/1M) grok-4.7 ($0.0897/1M) qwen3-235b-a22b-thinking-2507 ($0.1000/1M) gemini-3-5-flash ($0.1050/1M) xiaomi-mimo-v2-5 ($0.1050/1M) gpt-5-mini ($0.1063/1M) gpt-6-sol ($0.1064/1M) claude-haiku-5.5 ($0.1080/1M) gpt-5-nano ($0.1125/1M) glm-4.7-flash-heretic ($0.1151/1M) gpt-6.1-sol ($0.1178/1M) mistral-large-3 ($0.1188/1M) deepseek-v4-pro-0813 ($0.1287/1M) mimo-v2.6-flash ($0.1371/1M) gpt-5-image-mini ($0.1495/1M) llama-3.2-3b-instruct ($0.1520/1M) gpt-5.6-terra ($0.1608/1M) hy3 ($0.1650/1M) qwen3-6-35b-a3b ($0.1693/1M) gpt-5.4 ($0.1745/1M) kimi-k2.6 ($0.1809/1M) e2ee-gpt-oss-120b-p ($0.1844/1M) nvidia-nemotron-3-5-lightning-30b-a3b ($0.2240/1M) grok-4.3 ($0.2250/1M) mistral-small-3.2-24b-instruct:web ($0.2303/1M) mistral-small-4 ($0.2344/1M) gpt-6-luna-pro ($0.2400/1M) openai-gpt-oss-120b:web ($0.2479/1M) e2ee-gemma-3-27b ($0.2560/1M) mimo-v2.6-pro ($0.2607/1M) gpt-5.6-sol ($0.2623/1M) claude-sonnet-5 ($0.2673/1M) venice-uncensored-1.2 ($0.2747/1M) e2ee-deepseek-v4-flash ($0.2775/1M) e2ee-gemma-4-26b-a4b-uncensored-p ($0.3099/1M) gpt-5.5 ($0.3156/1M) gpt-5.3-codex ($0.3256/1M) mimo-v2.5-pro ($0.3262/1M) qwen3-5-35b-a3b ($0.3303/1M) gemma-4-uncensored ($0.3312/1M) claude-opus-4.7 ($0.3373/1M) deepseek-v4-flash:web ($0.3484/1M) qwen3.5-flash ($0.3500/1M) claude-opus-4.6 ($0.3557/1M) e2ee-qwen3-6-35b-a3b ($0.3669/1M) mistral-large ($0.3712/1M) mercury-2.5 ($0.3800/1M) qwen3.8-2.4t-a95b ($0.4000/1M) e2ee-gemma-4-31b ($0.4000/1M) kimi-k3 ($0.4050/1M) qwen3-30b-a3b ($0.4340/1M) grok-4.1-fast ($0.4375/1M) qwen3-vl-30b-a3b-thinking ($0.4400/1M) gemma-4-26b-a4b-it:web ($0.4439/1M) gemini-2.5-pro ($0.4489/1M) gemma-4-31b-it:web ($0.4522/1M) gpt-6-astra ($0.4652/1M) claude-haiku-4.5 ($0.4764/1M) gpt-5.4-image-2 ($0.4863/1M) llama-3.2-3b-instruct:web ($0.5025/1M) glm-4.7-flash:web ($0.5100/1M) grok-4.20-multi-agent-beta ($0.5250/1M) deepseek-v4-flash-0731-fast ($0.5250/1M) grok-4.20-beta ($0.5250/1M) qwen3-vl-235b-a22b-thinking ($0.5264/1M) mercury-2 ($0.5500/1M) gemini-3.1-pro-preview ($0.5600/1M) gpt-5.6-luna-pro ($0.5600/1M) muse-glimmer-30b ($0.6000/1M) gpt-5-image ($0.6000/1M) qwen3-235b-a22b-2507:web ($0.6030/1M) venice-uncensored-role-play ($0.6213/1M) qwen-3-7-plus ($0.6213/1M) gpt-4o ($0.6250/1M) hermes-3-llama-3.1-405b ($0.6822/1M) command-a-plus ($0.7200/1M) gpt-5.4-nano ($0.7250/1M) venice-uncensored ($0.7370/1M) minimax-m3-preview ($0.7500/1M) gpt-5.2 ($0.7875/1M) e2ee-qwen3-6-35b-a3b-uncensored-p ($0.8000/1M) trinity-large-thinking ($0.8295/1M) qwen3.6-27b ($0.8375/1M) aion-labs-aion-3-0-mini ($0.8400/1M) grok-4.6 ($0.8536/1M) qwen3-coder-turbo ($0.9250/1M) gpt-5.4-mini ($0.9980/1M) seed-2-1-turbo ($1.0116/1M) minimax-m2.5:web ($1.0251/1M) trinity-large-thinking:web ($1.0781/1M) gemini-3-5-flash-lite ($1.0976/1M) muse-spark-1.2 ($1.1000/1M) qwen-3-8-27b ($1.1900/1M) qwen3.5-plus ($1.2740/1M) deepseek-r1 ($1.2800/1M) grok-4.5 ($1.3586/1M) inkling ($1.3655/1M) seed-2.0-code ($1.4000/1M) minimax-m2.7:web ($1.4062/1M) grok-build-0-1 ($1.5000/1M) qwen3-next-80b-a3b-instruct:web ($1.5075/1M) gemini-3.1-pro ($1.5369/1M) glm-5v-turbo ($1.6008/1M) qwen3.5-397b-a17b ($1.6168/1M) gemini-3-6-flash ($1.7820/1M) claude-sonnet-5.5 ($1.8000/1M) glm-4.7-thinking ($1.8375/1M) glm-4.7-thinking:web ($1.8375/1M) qwen-3-8-max ($1.9682/1M) aion-labs.aion-2-0 ($2.0400/1M) e2ee-glm-5.1 ($2.1000/1M) qwen3.6-plus-uncensored ($2.1437/1M) llama-3.3-70b-instruct:web ($2.3450/1M) claude-opus-4.8 ($2.4243/1M) kimi-k2 ($2.4395/1M) e2ee-glm-5-2-p ($2.5751/1M) minimax-m2.7-highspeed ($2.7000/1M) kimi-k2.5:web ($2.7202/1M) kimi-k2.7-code:web ($2.7403/1M) hermes-3-llama-3.1-405b:web ($2.7470/1M) fugu-max ($3.2000/1M) claude-sonnet-4.6 ($3.4688/1M) glm-5:web ($3.5175/1M) glm-5.2:web ($3.5510/1M) aion-labs-aion-3-0 ($3.5640/1M) claude-opus-5.5 ($3.5964/1M) kimi-k2.6:web ($3.6883/1M) deepseek-v4-pro:web ($3.7024/1M) gpt-5.2-codex ($3.9375/1M) glm-4.7:web ($3.9375/1M) qwen-3-7-max ($4.0000/1M) claude-sonnet-4.5 ($4.1976/1M) claude-opus-5 ($4.2210/1M) glm-5.1-non-thinking:web ($4.3550/1M) glm-5.1-non-thinking ($4.3550/1M) glm-5.3-prime ($4.6400/1M) gpt-6-sol-pro ($4.8000/1M) gpt-5.6-sol-pro ($4.8000/1M) gpt-6.1-sol-pro ($4.8000/1M) glm-5.1:web ($4.8575/1M) mimo-v2.6-pro-ultraspeed ($5.2200/1M) gpt-5.6-terra-pro ($5.6000/1M) claude-opus-4.5 ($6.7200/1M) claude-fable-5.1 ($9.1167/1M) claude-fable-5 ($10.7999/1M) muse-spark-1.1 ($11.0000/1M) kimi-k3-fast-api ($11.4750/1M) fugu-ultra-v2 ($14.0000/1M) claude-opus-5-fast ($14.9550/1M) claude-opus-4-8-fast ($24.8268/1M) ember-1 ($36.0000/1M) gpt-5.5-pro ($65.6250/1M) gpt-5.4-pro ($84.0000/1M) claude-opus-4.6-fast ($86.4000/1M) claude-opus-4-7-fast ($108.0000/1M)
model B
choose... jev-1.13 ($0.0004/1M) openai-gpt-oss-20b ($0.0011/1M) gemma-3-4b-it ($0.0015/1M) gemma-4-26b-a4b-it ($0.0020/1M) gemma-3-12b-it ($0.0020/1M) deepseek-v4.1-flash ($0.0021/1M) ministral-3-3b-instruct ($0.0022/1M) gemma-3-27b-it ($0.0028/1M) gemini-2.5-flash-image ($0.0033/1M) qwen3-coder-30b-a3b-instruct ($0.0035/1M) qwen3-32b ($0.0036/1M) openai-gpt-oss-120b ($0.0037/1M) nvidia-nemotron-3-nano-30b-a3b ($0.0037/1M) gemma-4-31b ($0.0043/1M) gemma-4-31b-it ($0.0043/1M) ministral-3-14b-instruct ($0.0045/1M) glm-4.7-flash ($0.0046/1M) ministral-3-8b-instruct ($0.0046/1M) glm-4.5-air ($0.0052/1M) nvidia-nemotron-nano-9b-v2 ($0.0057/1M) gpt-6-luna ($0.0058/1M) qwen3.8-flash ($0.0062/1M) qwen3-235b-a22b-2507 ($0.0064/1M) glm-5.3-flash ($0.0065/1M) deepseek-v3.2 ($0.0066/1M) gemma-4-e2b ($0.0072/1M) openai-gpt-oss-safeguard-20b ($0.0074/1M) nvidia-nemotron-3-super-120b ($0.0080/1M) nvidia-nemotron-nano-12b-v2 ($0.0090/1M) qwen3-coder-next ($0.0091/1M) deepseek-v4-flash ($0.0091/1M) qwen3-next-80b-a3b-instruct ($0.0107/1M) gemini-3.8-flash ($0.0109/1M) minimax-m2.5 ($0.0121/1M) qwen3-coder ($0.0129/1M) openai-gpt-oss-safeguard-120b ($0.0148/1M) minimax-m2.1 ($0.0150/1M) minimax-m2 ($0.0150/1M) minimax-m3 ($0.0151/1M) glm-4.7 ($0.0152/1M) palmyra-vision-7b ($0.0170/1M) glm-5.2 ($0.0171/1M) mistral-small-3.2-24b-instruct ($0.0171/1M) qwen3.8-omni-flash ($0.0173/1M) gemini-3.1-flash-lite ($0.0175/1M) gpt-5.6-luna ($0.0184/1M) deepseek-v3.1 ($0.0205/1M) deepseek-v4-pro ($0.0211/1M) qwen3-vl-235b-a22b-instruct ($0.0211/1M) glm-4.6 ($0.0216/1M) gemini-3.7-flash ($0.0238/1M) glm-5 ($0.0249/1M) kimi-k2.5 ($0.0267/1M) minimax-m2.7 ($0.0273/1M) glm-4.5 ($0.0277/1M) gemini-2.5-flash ($0.0280/1M) nvidia-nemotron-3-ultra-550b-a55b ($0.0300/1M) kimi-k2-thinking ($0.0310/1M) gemini-3-flash-preview ($0.0350/1M) deepseek-v4-flash-0731 ($0.0360/1M) gpt-4o-mini ($0.0375/1M) magistral-small-2509 ($0.0396/1M) e2ee-qwen-2-5-7b-p ($0.0424/1M) glm-5.3 ($0.0431/1M) muse-spark-1.2-contributor ($0.0450/1M) muse-spark-1.3-contributor ($0.0450/1M) glm-5-turbo ($0.0515/1M) devstral-2-123b ($0.0547/1M) glm-5.1 ($0.0572/1M) llama-3.3-70b-instruct ($0.0588/1M) e2ee-gpt-oss-20b-p ($0.0600/1M) kimi-k2.7-code ($0.0603/1M) qwen3-5-9b ($0.0618/1M) grok-4.7 ($0.0897/1M) qwen3-235b-a22b-thinking-2507 ($0.1000/1M) gemini-3-5-flash ($0.1050/1M) xiaomi-mimo-v2-5 ($0.1050/1M) gpt-5-mini ($0.1063/1M) gpt-6-sol ($0.1064/1M) claude-haiku-5.5 ($0.1080/1M) gpt-5-nano ($0.1125/1M) glm-4.7-flash-heretic ($0.1151/1M) gpt-6.1-sol ($0.1178/1M) mistral-large-3 ($0.1188/1M) deepseek-v4-pro-0813 ($0.1287/1M) mimo-v2.6-flash ($0.1371/1M) gpt-5-image-mini ($0.1495/1M) llama-3.2-3b-instruct ($0.1520/1M) gpt-5.6-terra ($0.1608/1M) hy3 ($0.1650/1M) qwen3-6-35b-a3b ($0.1693/1M) gpt-5.4 ($0.1745/1M) kimi-k2.6 ($0.1809/1M) e2ee-gpt-oss-120b-p ($0.1844/1M) nvidia-nemotron-3-5-lightning-30b-a3b ($0.2240/1M) grok-4.3 ($0.2250/1M) mistral-small-3.2-24b-instruct:web ($0.2303/1M) mistral-small-4 ($0.2344/1M) gpt-6-luna-pro ($0.2400/1M) openai-gpt-oss-120b:web ($0.2479/1M) e2ee-gemma-3-27b ($0.2560/1M) mimo-v2.6-pro ($0.2607/1M) gpt-5.6-sol ($0.2623/1M) claude-sonnet-5 ($0.2673/1M) venice-uncensored-1.2 ($0.2747/1M) e2ee-deepseek-v4-flash ($0.2775/1M) e2ee-gemma-4-26b-a4b-uncensored-p ($0.3099/1M) gpt-5.5 ($0.3156/1M) gpt-5.3-codex ($0.3256/1M) mimo-v2.5-pro ($0.3262/1M) qwen3-5-35b-a3b ($0.3303/1M) gemma-4-uncensored ($0.3312/1M) claude-opus-4.7 ($0.3373/1M) deepseek-v4-flash:web ($0.3484/1M) qwen3.5-flash ($0.3500/1M) claude-opus-4.6 ($0.3557/1M) e2ee-qwen3-6-35b-a3b ($0.3669/1M) mistral-large ($0.3712/1M) mercury-2.5 ($0.3800/1M) qwen3.8-2.4t-a95b ($0.4000/1M) e2ee-gemma-4-31b ($0.4000/1M) kimi-k3 ($0.4050/1M) qwen3-30b-a3b ($0.4340/1M) grok-4.1-fast ($0.4375/1M) qwen3-vl-30b-a3b-thinking ($0.4400/1M) gemma-4-26b-a4b-it:web ($0.4439/1M) gemini-2.5-pro ($0.4489/1M) gemma-4-31b-it:web ($0.4522/1M) gpt-6-astra ($0.4652/1M) claude-haiku-4.5 ($0.4764/1M) gpt-5.4-image-2 ($0.4863/1M) llama-3.2-3b-instruct:web ($0.5025/1M) glm-4.7-flash:web ($0.5100/1M) grok-4.20-multi-agent-beta ($0.5250/1M) deepseek-v4-flash-0731-fast ($0.5250/1M) grok-4.20-beta ($0.5250/1M) qwen3-vl-235b-a22b-thinking ($0.5264/1M) mercury-2 ($0.5500/1M) gemini-3.1-pro-preview ($0.5600/1M) gpt-5.6-luna-pro ($0.5600/1M) muse-glimmer-30b ($0.6000/1M) gpt-5-image ($0.6000/1M) qwen3-235b-a22b-2507:web ($0.6030/1M) venice-uncensored-role-play ($0.6213/1M) qwen-3-7-plus ($0.6213/1M) gpt-4o ($0.6250/1M) hermes-3-llama-3.1-405b ($0.6822/1M) command-a-plus ($0.7200/1M) gpt-5.4-nano ($0.7250/1M) venice-uncensored ($0.7370/1M) minimax-m3-preview ($0.7500/1M) gpt-5.2 ($0.7875/1M) e2ee-qwen3-6-35b-a3b-uncensored-p ($0.8000/1M) trinity-large-thinking ($0.8295/1M) qwen3.6-27b ($0.8375/1M) aion-labs-aion-3-0-mini ($0.8400/1M) grok-4.6 ($0.8536/1M) qwen3-coder-turbo ($0.9250/1M) gpt-5.4-mini ($0.9980/1M) seed-2-1-turbo ($1.0116/1M) minimax-m2.5:web ($1.0251/1M) trinity-large-thinking:web ($1.0781/1M) gemini-3-5-flash-lite ($1.0976/1M) muse-spark-1.2 ($1.1000/1M) qwen-3-8-27b ($1.1900/1M) qwen3.5-plus ($1.2740/1M) deepseek-r1 ($1.2800/1M) grok-4.5 ($1.3586/1M) inkling ($1.3655/1M) seed-2.0-code ($1.4000/1M) minimax-m2.7:web ($1.4062/1M) grok-build-0-1 ($1.5000/1M) qwen3-next-80b-a3b-instruct:web ($1.5075/1M) gemini-3.1-pro ($1.5369/1M) glm-5v-turbo ($1.6008/1M) qwen3.5-397b-a17b ($1.6168/1M) gemini-3-6-flash ($1.7820/1M) claude-sonnet-5.5 ($1.8000/1M) glm-4.7-thinking ($1.8375/1M) glm-4.7-thinking:web ($1.8375/1M) qwen-3-8-max ($1.9682/1M) aion-labs.aion-2-0 ($2.0400/1M) e2ee-glm-5.1 ($2.1000/1M) qwen3.6-plus-uncensored ($2.1437/1M) llama-3.3-70b-instruct:web ($2.3450/1M) claude-opus-4.8 ($2.4243/1M) kimi-k2 ($2.4395/1M) e2ee-glm-5-2-p ($2.5751/1M) minimax-m2.7-highspeed ($2.7000/1M) kimi-k2.5:web ($2.7202/1M) kimi-k2.7-code:web ($2.7403/1M) hermes-3-llama-3.1-405b:web ($2.7470/1M) fugu-max ($3.2000/1M) claude-sonnet-4.6 ($3.4688/1M) glm-5:web ($3.5175/1M) glm-5.2:web ($3.5510/1M) aion-labs-aion-3-0 ($3.5640/1M) claude-opus-5.5 ($3.5964/1M) kimi-k2.6:web ($3.6883/1M) deepseek-v4-pro:web ($3.7024/1M) gpt-5.2-codex ($3.9375/1M) glm-4.7:web ($3.9375/1M) qwen-3-7-max ($4.0000/1M) claude-sonnet-4.5 ($4.1976/1M) claude-opus-5 ($4.2210/1M) glm-5.1-non-thinking:web ($4.3550/1M) glm-5.1-non-thinking ($4.3550/1M) glm-5.3-prime ($4.6400/1M) gpt-6-sol-pro ($4.8000/1M) gpt-5.6-sol-pro ($4.8000/1M) gpt-6.1-sol-pro ($4.8000/1M) glm-5.1:web ($4.8575/1M) mimo-v2.6-pro-ultraspeed ($5.2200/1M) gpt-5.6-terra-pro ($5.6000/1M) claude-opus-4.5 ($6.7200/1M) claude-fable-5.1 ($9.1167/1M) claude-fable-5 ($10.7999/1M) muse-spark-1.1 ($11.0000/1M) kimi-k3-fast-api ($11.4750/1M) fugu-ultra-v2 ($14.0000/1M) claude-opus-5-fast ($14.9550/1M) claude-opus-4-8-fast ($24.8268/1M) ember-1 ($36.0000/1M) gpt-5.5-pro ($65.6250/1M) gpt-5.4-pro ($84.0000/1M) claude-opus-4.6-fast ($86.4000/1M) claude-opus-4-7-fast ($108.0000/1M)
model C (optional)
choose... jev-1.13 ($0.0004/1M) openai-gpt-oss-20b ($0.0011/1M) gemma-3-4b-it ($0.0015/1M) gemma-4-26b-a4b-it ($0.0020/1M) gemma-3-12b-it ($0.0020/1M) deepseek-v4.1-flash ($0.0021/1M) ministral-3-3b-instruct ($0.0022/1M) gemma-3-27b-it ($0.0028/1M) gemini-2.5-flash-image ($0.0033/1M) qwen3-coder-30b-a3b-instruct ($0.0035/1M) qwen3-32b ($0.0036/1M) openai-gpt-oss-120b ($0.0037/1M) nvidia-nemotron-3-nano-30b-a3b ($0.0037/1M) gemma-4-31b ($0.0043/1M) gemma-4-31b-it ($0.0043/1M) ministral-3-14b-instruct ($0.0045/1M) glm-4.7-flash ($0.0046/1M) ministral-3-8b-instruct ($0.0046/1M) glm-4.5-air ($0.0052/1M) nvidia-nemotron-nano-9b-v2 ($0.0057/1M) gpt-6-luna ($0.0058/1M) qwen3.8-flash ($0.0062/1M) qwen3-235b-a22b-2507 ($0.0064/1M) glm-5.3-flash ($0.0065/1M) deepseek-v3.2 ($0.0066/1M) gemma-4-e2b ($0.0072/1M) openai-gpt-oss-safeguard-20b ($0.0074/1M) nvidia-nemotron-3-super-120b ($0.0080/1M) nvidia-nemotron-nano-12b-v2 ($0.0090/1M) qwen3-coder-next ($0.0091/1M) deepseek-v4-flash ($0.0091/1M) qwen3-next-80b-a3b-instruct ($0.0107/1M) gemini-3.8-flash ($0.0109/1M) minimax-m2.5 ($0.0121/1M) qwen3-coder ($0.0129/1M) openai-gpt-oss-safeguard-120b ($0.0148/1M) minimax-m2.1 ($0.0150/1M) minimax-m2 ($0.0150/1M) minimax-m3 ($0.0151/1M) glm-4.7 ($0.0152/1M) palmyra-vision-7b ($0.0170/1M) glm-5.2 ($0.0171/1M) mistral-small-3.2-24b-instruct ($0.0171/1M) qwen3.8-omni-flash ($0.0173/1M) gemini-3.1-flash-lite ($0.0175/1M) gpt-5.6-luna ($0.0184/1M) deepseek-v3.1 ($0.0205/1M) deepseek-v4-pro ($0.0211/1M) qwen3-vl-235b-a22b-instruct ($0.0211/1M) glm-4.6 ($0.0216/1M) gemini-3.7-flash ($0.0238/1M) glm-5 ($0.0249/1M) kimi-k2.5 ($0.0267/1M) minimax-m2.7 ($0.0273/1M) glm-4.5 ($0.0277/1M) gemini-2.5-flash ($0.0280/1M) nvidia-nemotron-3-ultra-550b-a55b ($0.0300/1M) kimi-k2-thinking ($0.0310/1M) gemini-3-flash-preview ($0.0350/1M) deepseek-v4-flash-0731 ($0.0360/1M) gpt-4o-mini ($0.0375/1M) magistral-small-2509 ($0.0396/1M) e2ee-qwen-2-5-7b-p ($0.0424/1M) glm-5.3 ($0.0431/1M) muse-spark-1.2-contributor ($0.0450/1M) muse-spark-1.3-contributor ($0.0450/1M) glm-5-turbo ($0.0515/1M) devstral-2-123b ($0.0547/1M) glm-5.1 ($0.0572/1M) llama-3.3-70b-instruct ($0.0588/1M) e2ee-gpt-oss-20b-p ($0.0600/1M) kimi-k2.7-code ($0.0603/1M) qwen3-5-9b ($0.0618/1M) grok-4.7 ($0.0897/1M) qwen3-235b-a22b-thinking-2507 ($0.1000/1M) gemini-3-5-flash ($0.1050/1M) xiaomi-mimo-v2-5 ($0.1050/1M) gpt-5-mini ($0.1063/1M) gpt-6-sol ($0.1064/1M) claude-haiku-5.5 ($0.1080/1M) gpt-5-nano ($0.1125/1M) glm-4.7-flash-heretic ($0.1151/1M) gpt-6.1-sol ($0.1178/1M) mistral-large-3 ($0.1188/1M) deepseek-v4-pro-0813 ($0.1287/1M) mimo-v2.6-flash ($0.1371/1M) gpt-5-image-mini ($0.1495/1M) llama-3.2-3b-instruct ($0.1520/1M) gpt-5.6-terra ($0.1608/1M) hy3 ($0.1650/1M) qwen3-6-35b-a3b ($0.1693/1M) gpt-5.4 ($0.1745/1M) kimi-k2.6 ($0.1809/1M) e2ee-gpt-oss-120b-p ($0.1844/1M) nvidia-nemotron-3-5-lightning-30b-a3b ($0.2240/1M) grok-4.3 ($0.2250/1M) mistral-small-3.2-24b-instruct:web ($0.2303/1M) mistral-small-4 ($0.2344/1M) gpt-6-luna-pro ($0.2400/1M) openai-gpt-oss-120b:web ($0.2479/1M) e2ee-gemma-3-27b ($0.2560/1M) mimo-v2.6-pro ($0.2607/1M) gpt-5.6-sol ($0.2623/1M) claude-sonnet-5 ($0.2673/1M) venice-uncensored-1.2 ($0.2747/1M) e2ee-deepseek-v4-flash ($0.2775/1M) e2ee-gemma-4-26b-a4b-uncensored-p ($0.3099/1M) gpt-5.5 ($0.3156/1M) gpt-5.3-codex ($0.3256/1M) mimo-v2.5-pro ($0.3262/1M) qwen3-5-35b-a3b ($0.3303/1M) gemma-4-uncensored ($0.3312/1M) claude-opus-4.7 ($0.3373/1M) deepseek-v4-flash:web ($0.3484/1M) qwen3.5-flash ($0.3500/1M) claude-opus-4.6 ($0.3557/1M) e2ee-qwen3-6-35b-a3b ($0.3669/1M) mistral-large ($0.3712/1M) mercury-2.5 ($0.3800/1M) qwen3.8-2.4t-a95b ($0.4000/1M) e2ee-gemma-4-31b ($0.4000/1M) kimi-k3 ($0.4050/1M) qwen3-30b-a3b ($0.4340/1M) grok-4.1-fast ($0.4375/1M) qwen3-vl-30b-a3b-thinking ($0.4400/1M) gemma-4-26b-a4b-it:web ($0.4439/1M) gemini-2.5-pro ($0.4489/1M) gemma-4-31b-it:web ($0.4522/1M) gpt-6-astra ($0.4652/1M) claude-haiku-4.5 ($0.4764/1M) gpt-5.4-image-2 ($0.4863/1M) llama-3.2-3b-instruct:web ($0.5025/1M) glm-4.7-flash:web ($0.5100/1M) grok-4.20-multi-agent-beta ($0.5250/1M) deepseek-v4-flash-0731-fast ($0.5250/1M) grok-4.20-beta ($0.5250/1M) qwen3-vl-235b-a22b-thinking ($0.5264/1M) mercury-2 ($0.5500/1M) gemini-3.1-pro-preview ($0.5600/1M) gpt-5.6-luna-pro ($0.5600/1M) muse-glimmer-30b ($0.6000/1M) gpt-5-image ($0.6000/1M) qwen3-235b-a22b-2507:web ($0.6030/1M) venice-uncensored-role-play ($0.6213/1M) qwen-3-7-plus ($0.6213/1M) gpt-4o ($0.6250/1M) hermes-3-llama-3.1-405b ($0.6822/1M) command-a-plus ($0.7200/1M) gpt-5.4-nano ($0.7250/1M) venice-uncensored ($0.7370/1M) minimax-m3-preview ($0.7500/1M) gpt-5.2 ($0.7875/1M) e2ee-qwen3-6-35b-a3b-uncensored-p ($0.8000/1M) trinity-large-thinking ($0.8295/1M) qwen3.6-27b ($0.8375/1M) aion-labs-aion-3-0-mini ($0.8400/1M) grok-4.6 ($0.8536/1M) qwen3-coder-turbo ($0.9250/1M) gpt-5.4-mini ($0.9980/1M) seed-2-1-turbo ($1.0116/1M) minimax-m2.5:web ($1.0251/1M) trinity-large-thinking:web ($1.0781/1M) gemini-3-5-flash-lite ($1.0976/1M) muse-spark-1.2 ($1.1000/1M) qwen-3-8-27b ($1.1900/1M) qwen3.5-plus ($1.2740/1M) deepseek-r1 ($1.2800/1M) grok-4.5 ($1.3586/1M) inkling ($1.3655/1M) seed-2.0-code ($1.4000/1M) minimax-m2.7:web ($1.4062/1M) grok-build-0-1 ($1.5000/1M) qwen3-next-80b-a3b-instruct:web ($1.5075/1M) gemini-3.1-pro ($1.5369/1M) glm-5v-turbo ($1.6008/1M) qwen3.5-397b-a17b ($1.6168/1M) gemini-3-6-flash ($1.7820/1M) claude-sonnet-5.5 ($1.8000/1M) glm-4.7-thinking ($1.8375/1M) glm-4.7-thinking:web ($1.8375/1M) qwen-3-8-max ($1.9682/1M) aion-labs.aion-2-0 ($2.0400/1M) e2ee-glm-5.1 ($2.1000/1M) qwen3.6-plus-uncensored ($2.1437/1M) llama-3.3-70b-instruct:web ($2.3450/1M) claude-opus-4.8 ($2.4243/1M) kimi-k2 ($2.4395/1M) e2ee-glm-5-2-p ($2.5751/1M) minimax-m2.7-highspeed ($2.7000/1M) kimi-k2.5:web ($2.7202/1M) kimi-k2.7-code:web ($2.7403/1M) hermes-3-llama-3.1-405b:web ($2.7470/1M) fugu-max ($3.2000/1M) claude-sonnet-4.6 ($3.4688/1M) glm-5:web ($3.5175/1M) glm-5.2:web ($3.5510/1M) aion-labs-aion-3-0 ($3.5640/1M) claude-opus-5.5 ($3.5964/1M) kimi-k2.6:web ($3.6883/1M) deepseek-v4-pro:web ($3.7024/1M) gpt-5.2-codex ($3.9375/1M) glm-4.7:web ($3.9375/1M) qwen-3-7-max ($4.0000/1M) claude-sonnet-4.5 ($4.1976/1M) claude-opus-5 ($4.2210/1M) glm-5.1-non-thinking:web ($4.3550/1M) glm-5.1-non-thinking ($4.3550/1M) glm-5.3-prime ($4.6400/1M) gpt-6-sol-pro ($4.8000/1M) gpt-5.6-sol-pro ($4.8000/1M) gpt-6.1-sol-pro ($4.8000/1M) glm-5.1:web ($4.8575/1M) mimo-v2.6-pro-ultraspeed ($5.2200/1M) gpt-5.6-terra-pro ($5.6000/1M) claude-opus-4.5 ($6.7200/1M) claude-fable-5.1 ($9.1167/1M) claude-fable-5 ($10.7999/1M) muse-spark-1.1 ($11.0000/1M) kimi-k3-fast-api ($11.4750/1M) fugu-ultra-v2 ($14.0000/1M) claude-opus-5-fast ($14.9550/1M) claude-opus-4-8-fast ($24.8268/1M) ember-1 ($36.0000/1M) gpt-5.5-pro ($65.6250/1M) gpt-5.4-pro ($84.0000/1M) claude-opus-4.6-fast ($86.4000/1M) claude-opus-4-7-fast ($108.0000/1M)
▶ compare