surp --list-models | sort by price
182 AI models available on the Surplus Intelligence marketplace right now. Sorted cheapest first. Click any model for detailed specs, pros & cons, and live pricing. Every model is OpenAI-compatible and accessible via our x402 LLM gateway with pay-per-request pricing in USDC on Base.
Compare: side by side comparison · top 5 leaderboards · find the right model · connect your app
| model | maker | tier | class | USD / 1M tok | sellers |
|---|---|---|---|---|---|
| gemma-3-4b-it | standard | fast | $0.0108 | 3 | |
| glm-5.2 | Zhipu AI / Z.AI | standard | chat | $0.0128 | 87 |
| ministral-3-3b-instruct | Independent | standard | fast | $0.0180 | 3 |
| glm-4.7 | Zhipu AI / Z.AI | standard | chat | $0.0215 | 94 |
| deepseek-v4-flash | DeepSeek | standard | chat | $0.0243 | 80 |
| openai-gpt-oss-safeguard-20b | OpenAI | standard | chat | $0.0243 | 3 |
| gemma-3-27b-it | standard | chat | $0.0252 | 75 | |
| deepseek-v4-flash-0731 | DeepSeek | standard | chat | $0.0254 | 34 |
| nvidia-nemotron-nano-9b-v2 | NVIDIA | standard | fast | $0.0261 | 3 |
| ministral-3-8b-instruct | Independent | standard | fast | $0.0270 | 3 |
| openai-gpt-oss-20b | OpenAI | standard | chat | $0.0333 | 3 |
| mistral-small-3.2-24b-instruct | Mistral AI | standard | fast | $0.0340 | 80 |
| gemma-3-12b-it | standard | fast | $0.0342 | 3 | |
| e2ee-qwen-2-5-7b-p | Venice AI | standard | chat | $0.0360 | 66 |
| ministral-3-14b-instruct | Independent | standard | fast | $0.0360 | 3 |
| glm-4.5-air | Zhipu AI / Z.AI | standard | fast | $0.0390 | 13 |
| qwen3-235b-a22b-2507 | Alibaba | standard | chat | $0.0475 | 79 |
| e2ee-gpt-oss-20b-p | OpenAI | standard | chat | $0.0480 | 63 |
| openai-gpt-oss-120b:web | OpenAI | standard | chat | $0.0555 | 5 |
| qwen3-5-9b | Alibaba | standard | fast | $0.0624 | 59 |
| glm-4.6 | Zhipu AI / Z.AI | standard | chat | $0.0654 | 106 |
| openai-gpt-oss-safeguard-120b | OpenAI | standard | chat | $0.0675 | 3 |
| palmyra-vision-7b | Independent | frontier | vision | $0.0675 | 3 |
| qwen3-coder-30b-a3b-instruct | Alibaba | frontier | coding | $0.0675 | 3 |
| nvidia-nemotron-nano-12b-v2 | NVIDIA | standard | fast | $0.0720 | 3 |
| deepseek-v4-flash:web | DeepSeek | standard | chat | $0.0780 | 7 |
| qwen3-235b-a22b-thinking-2507 | Alibaba | standard | reasoning | $0.0800 | 67 |
| gemma-4-31b-it | standard | chat | $0.0825 | 73 | |
| glm-4.5 | Zhipu AI / Z.AI | standard | chat | $0.0840 | 11 |
| glm-4.7-flash | Zhipu AI / Z.AI | standard | chat | $0.0876 | 68 |
| gpt-5-nano | OpenAI | frontier | fast | $0.0900 | 26 |
| openai-gpt-oss-120b | OpenAI | standard | chat | $0.0924 | 75 |
| nvidia-nemotron-3-nano-30b-a3b | NVIDIA | standard | fast | $0.0937 | 69 |
| gpt-5.6-luna | OpenAI | frontier | chat | $0.0980 | 68 |
| glm-5 | Zhipu AI / Z.AI | standard | chat | $0.0995 | 108 |
| gemma-4-31b-it:web | standard | chat | $0.1013 | 7 | |
| gemma-4-26b-a4b-it | standard | fast | $0.1059 | 89 | |
| llama-3.2-3b-instruct | Meta | standard | fast | $0.1140 | 61 |
| qwen3-coder | Alibaba | frontier | coding | $0.1170 | 25 |
| glm-4.7-flash-heretic | Zhipu AI / Z.AI | standard | chat | $0.1174 | 68 |
| deepseek-v4-pro | DeepSeek | standard | chat | $0.1174 | 99 |
| llama-3.3-70b-instruct | Meta | standard | chat | $0.1260 | 74 |
| mistral-small-3.2-24b-instruct:web | Mistral AI | standard | fast | $0.1375 | 1 |
| minimax-m2.7 | MiniMax | standard | fast | $0.1500 | 67 |
| gpt-4o-mini | OpenAI | frontier | fast | $0.1500 | 93 |
| deepseek-v3.2 | DeepSeek | standard | chat | $0.1673 | 17 |
| glm-4.7-flash:web | Zhipu AI / Z.AI | standard | chat | $0.1700 | 2 |
| mistral-large-3 | Mistral AI | standard | chat | $0.1800 | 3 |
| magistral-small-2509 | Mistral AI | standard | fast | $0.1800 | 4 |
| qwen3-32b | Alibaba | standard | chat | $0.1875 | 2 |
| glm-5.1 | Zhipu AI / Z.AI | standard | chat | $0.1914 | 96 |
| e2ee-gemma-3-27b | standard | chat | $0.1920 | 52 | |
| e2ee-gpt-oss-120b-p | OpenAI | standard | chat | $0.1948 | 62 |
| gemma-4-uncensored | standard | chat | $0.1988 | 56 | |
| e2ee-gemma-4-31b | standard | chat | $0.1998 | 61 | |
| minimax-m3 | MiniMax | standard | fast | $0.2000 | 14 |
| nvidia-nemotron-3-super-120b | NVIDIA | standard | chat | $0.2000 | 2 |
| deepseek-v3.1 | DeepSeek | standard | chat | $0.2034 | 3 |
| qwen3-30b-a3b | Alibaba | standard | chat | $0.2046 | 10 |
| glm-5-turbo | Zhipu AI / Z.AI | standard | chat | $0.2054 | 117 |
| gpt-5.6-luna-pro | OpenAI | frontier | chat | $0.2100 | 49 |
| devstral-2-123b | Independent | standard | chat | $0.2160 | 3 |
| nvidia-nemotron-cascade-2-30b-a3b | NVIDIA | standard | chat | $0.2256 | 5 |
| qwen3-6-35b-a3b | Alibaba | standard | chat | $0.2280 | 31 |
| minimax-m2.5 | MiniMax | standard | fast | $0.2398 | 78 |
| gemma-4-26b-a4b-it:web | standard | fast | $0.2650 | 3 | |
| venice-uncensored-1.2 | Venice AI | standard | chat | $0.2747 | 59 |
| qwen3-vl-30b-a3b-thinking | Alibaba | frontier | vision | $0.2750 | 48 |
| mistral-small-4 | Mistral AI | standard | fast | $0.2812 | 55 |
| qwen3-vl-235b-a22b-instruct | Alibaba | frontier | vision | $0.2871 | 3 |
| e2ee-gemma-4-26b-a4b-uncensored-p | standard | chat | $0.2897 | 61 | |
| gpt-5.4-nano | OpenAI | frontier | fast | $0.2900 | 24 |
| qwen3-5-35b-a3b | Alibaba | standard | chat | $0.2969 | 74 |
| qwen3-next-80b-a3b-instruct | Alibaba | standard | fast | $0.3000 | 80 |
| llama-3.2-3b-instruct:web | Meta | standard | fast | $0.3000 | 3 |
| mercury-2 | Inception Labs | standard | chat | $0.3122 | 63 |
| deepseek-v4-pro-0813 | DeepSeek | standard | chat | $0.3134 | 18 |
| venice-uncensored | Venice AI | standard | chat | $0.3300 | 3 |
| e2ee-venice-uncensored-24b-p | Venice AI | standard | chat | $0.3360 | 7 |
| qwen3.5-flash | Alibaba | standard | chat | $0.3500 | 13 |
| qwen3-235b-a22b-2507:web | Alibaba | standard | chat | $0.3600 | 3 |
| minimax-m2.1 | MiniMax | standard | fast | $0.3750 | 9 |
| minimax-m2 | MiniMax | standard | fast | $0.3750 | 2 |
| minimax-m2.5:web | MiniMax | standard | fast | $0.3825 | 6 |
| e2ee-qwen3-6-35b-a3b | Alibaba | standard | chat | $0.3996 | 64 |
| qwen3-vl-235b-a22b-thinking | Alibaba | frontier | vision | $0.4120 | 73 |
| qwen3-coder-next | Alibaba | frontier | coding | $0.4250 | 2 |
| grok-4.1-fast | xAI | frontier | chat | $0.4375 | 6 |
| gpt-5-mini | OpenAI | frontier | fast | $0.4500 | 24 |
| glm-5.3 | Zhipu AI / Z.AI | standard | chat | $0.4594 | 13 |
| minimax-m2.7:web | MiniMax | standard | fast | $0.4688 | 2 |
| gpt-5-image-mini | OpenAI | frontier | fast | $0.4935 | 11 |
| glm-5:web | Zhipu AI / Z.AI | standard | chat | $0.5250 | 13 |
| gemini-3.7-flash | Independent | standard | fast | $0.5402 | 20 |
| deepseek-v4-pro:web | DeepSeek | standard | chat | $0.5526 | 9 |
| qwen3-coder-turbo | Alibaba | frontier | coding | $0.5550 | 48 |
| kimi-k2.6 | Moonshot AI | frontier | chat | $0.5950 | 88 |
| glm-4.7-thinking:web | Zhipu AI / Z.AI | standard | reasoning | $0.6125 | 2 |
| venice-uncensored-role-play | Venice AI | standard | chat | $0.6244 | 62 |
| qwen-3-7-plus | Alibaba | standard | chat | $0.6244 | 64 |
| qwen3.5-plus | Alibaba | standard | chat | $0.6370 | 16 |
| glm-5.1-non-thinking:web | Zhipu AI / Z.AI | standard | reasoning | $0.6500 | 10 |
| kimi-k2.5 | Moonshot AI | frontier | chat | $0.6750 | 76 |
| gpt-5.4-mini | OpenAI | frontier | fast | $0.6825 | 106 |
| trinity-large-thinking | Arcee AI | standard | reasoning | $0.6900 | 3 |
| hy3 | Independent | standard | chat | $0.7200 | 2 |
| glm-5.1:web | Zhipu AI / Z.AI | standard | chat | $0.7250 | 10 |
| nvidia-nemotron-3-ultra-550b-a55b | NVIDIA | standard | chat | $0.7492 | 64 |
| kimi-k2-thinking | Moonshot AI | frontier | reasoning | $0.7750 | 9 |
| mistral-large | Mistral AI | standard | chat | $0.7920 | 15 |
| glm-5.2:web | Zhipu AI / Z.AI | standard | chat | $0.7950 | 7 |
| gemini-3-flash-preview | standard | fast | $0.7991 | 84 | |
| e2ee-qwen3-6-35b-a3b-uncensored-p | Alibaba | standard | chat | $0.7992 | 55 |
| qwen3.6-27b | Alibaba | standard | chat | $0.8929 | 65 |
| qwen3-next-80b-a3b-instruct:web | Alibaba | standard | fast | $0.9000 | 3 |
| grok-4.20-multi-agent-beta | xAI | frontier | chat | $0.9366 | 65 |
| grok-4.20-beta | xAI | frontier | chat | $0.9366 | 75 |
| gemini-3.1-flash-lite | Independent | standard | fast | $0.9625 | 13 |
| glm-5.1-non-thinking | Zhipu AI / Z.AI | standard | reasoning | $0.9750 | 7 |
| gpt-5.6-terra | OpenAI | frontier | chat | $0.9800 | 74 |
| kimi-k2.5:web | Moonshot AI | frontier | chat | $1.0150 | 8 |
| hermes-3-llama-3.1-405b | Meta | standard | chat | $1.0240 | 67 |
| e2ee-glm-5.1 | Zhipu AI / Z.AI | standard | chat | $1.0490 | 64 |
| qwen3.5-397b-a17b | Alibaba | frontier | chat | $1.0490 | 69 |
| kimi-k2.7-code | Moonshot AI | frontier | coding | $1.0514 | 66 |
| grok-4.3 | xAI | frontier | chat | $1.0614 | 72 |
| trinity-large-thinking:web | Arcee AI | standard | reasoning | $1.0781 | 1 |
| kimi-k3 | Moonshot AI | frontier | chat | $1.0800 | 68 |
| e2ee-qwen3-5-122b-a10b | Alibaba | standard | chat | $1.1250 | 7 |
| claude-haiku-4.5 | Anthropic | standard | chat | $1.2000 | 23 |
| aion-labs.aion-2-0 | Aion Labs | standard | chat | $1.2000 | 28 |
| e2ee-glm-4.7 | Zhipu AI / Z.AI | standard | chat | $1.2600 | 6 |
| gemini-3-5-flash | standard | fast | $1.2831 | 75 | |
| qwen3.6-plus-uncensored | Alibaba | standard | chat | $1.3125 | 56 |
| glm-4.7:web | Zhipu AI / Z.AI | standard | chat | $1.3125 | 2 |
| kimi-k2.7-code:web | Moonshot AI | frontier | coding | $1.3497 | 4 |
| llama-3.3-70b-instruct:web | Meta | standard | chat | $1.4000 | 3 |
| gemini-2.5-flash | standard | fast | $1.4000 | 16 | |
| grok-code-fast-1 | xAI | frontier | chat | $1.4455 | 3 |
| glm-5v-turbo | Zhipu AI / Z.AI | frontier | vision | $1.5584 | 66 |
| qwen3.8-2.4t-a95b | Alibaba | standard | chat | $1.6000 | 15 |
| grok-4.5 | xAI | frontier | chat | $1.6000 | 54 |
| gpt-5.4-image-2 | OpenAI | frontier | chat | $1.6048 | 11 |
| hermes-3-llama-3.1-405b:web | Meta | standard | chat | $1.6400 | 3 |
| glm-4.7-thinking | Zhipu AI / Z.AI | standard | reasoning | $1.8375 | 1 |
| grok-4.6 | xAI | frontier | chat | $1.8624 | 23 |
| gpt-5.4 | OpenAI | frontier | chat | $1.9250 | 106 |
| gpt-5-image | OpenAI | frontier | chat | $1.9800 | 11 |
| grok-build-0-1 | xAI | frontier | chat | $1.9980 | 65 |
| kimi-k2 | Moonshot AI | frontier | chat | $2.0090 | 5 |
| claude-opus-5 | Anthropic | frontier | chat | $2.0970 | 68 |
| gpt-5.6-terra-pro | OpenAI | frontier | chat | $2.1000 | 50 |
| kimi-k2.6:web | Moonshot AI | frontier | chat | $2.2020 | 6 |
| deepseek-r1 | DeepSeek | frontier | reasoning | $2.2400 | 6 |
| gpt-5.6-sol | OpenAI | frontier | chat | $2.2750 | 84 |
| claude-sonnet-5 | Anthropic | frontier | chat | $2.4000 | 67 |
| qwen-3-7-max | Alibaba | standard | chat | $2.4000 | 58 |
| gpt-4o | OpenAI | frontier | chat | $2.5000 | 97 |
| minimax-m2.7-highspeed | MiniMax | standard | fast | $2.7000 | 5 |
| claude-sonnet-4.6 | Anthropic | frontier | chat | $2.7000 | 94 |
| claude-opus-4.6 | Anthropic | frontier | chat | $2.9970 | 100 |
| claude-opus-4.7 | Anthropic | frontier | chat | $2.9970 | 104 |
| qwen-3-8-max | Alibaba | standard | chat | $3.0000 | 28 |
| gpt-5.5 | OpenAI | frontier | chat | $3.0625 | 107 |
| gpt-5.2 | OpenAI | frontier | chat | $3.1500 | 96 |
| gemini-3.1-pro-preview | frontier | fast | $3.3264 | 77 | |
| gpt-5.6-sol-pro | OpenAI | frontier | chat | $3.5000 | 57 |
| claude-sonnet-4.5 | Anthropic | frontier | chat | $3.6000 | 83 |
| gpt-5.3-codex | OpenAI | frontier | coding | $3.9336 | 81 |
| gemini-2.5-pro | frontier | fast | $5.5136 | 17 | |
| gpt-5.2-codex | OpenAI | frontier | coding | $6.3000 | 43 |
| claude-opus-4.8 | Anthropic | frontier | chat | $7.0957 | 104 |
| claude-opus-4.5 | Anthropic | frontier | chat | $7.4925 | 84 |
| gemini-3.1-pro | frontier | fast | $7.7000 | 6 | |
| claude-fable-5 | Anthropic | frontier | chat | $12.1176 | 81 |
| claude-opus-5-fast | Anthropic | frontier | chat | $14.6913 | 43 |
| grok-4 | xAI | frontier | chat | $15.3000 | 3 |
| claude-opus-4-8-fast | Anthropic | frontier | chat | $21.6000 | 60 |
| gpt-5.4-pro | OpenAI | frontier | chat | $52.4475 | 89 |
| claude-opus-4.6-fast | Anthropic | frontier | chat | $54.0000 | 26 |
| gpt-5.5-pro | OpenAI | frontier | chat | $56.9318 | 69 |
| claude-opus-4-7-fast | Anthropic | frontier | chat | $71.2800 | 19 |
Prices update live from the marketplace. See top 5 per category » · Find the right model for you »