Market intel — Surplus Intelligence sell-side catalog (2026-07-24)
Source: api.surplusintelligence.ai/v1/models (371 unique models, 100% mirrored into our catalog).
Servable via OpenRouter today: 105 (live-priced endpoints seeded).
Listed without a route (sell-side inventory): 266 — mostly Venice-exclusive chat, e2ee variants, and video/image/TTS (kling, wan, seedance, veo3, ltx, pixverse).
Surplus lists a LOWER input price than OpenRouter on 21/105 comparable models — their discount posture; our seller order book (multiplier offers) is the mechanism to match or beat it.
| model | surplus in $/MTok | surplus out | openrouter in | openrouter out | surplus vs OR in |
|---|---|---|---|---|---|
| aion-labs/aion-2.0 | 1.0000 | 2.0000 | 0.8000 | 1.6000 | +25.0% |
| anthropic/claude-fable-5 | 12.0000 | 60.0000 | 10.0000 | 50.0000 | +20.0% |
| anthropic/claude-haiku-4.5 | 1.0000 | 5.0000 | 1.0000 | 5.0000 | +0.0% |
| anthropic/claude-opus-4.5 | 5.0000 | 25.0000 | 5.0000 | 25.0000 | +0.0% |
| anthropic/claude-opus-4.6 | 5.0000 | 25.0000 | 5.0000 | 25.0000 | +0.0% |
| anthropic/claude-opus-4.7 | 5.0000 | 25.0000 | 5.0000 | 25.0000 | +0.0% |
| anthropic/claude-opus-4.7-fast | 36.0000 | 180.0000 | 30.0000 | 150.0000 | +20.0% |
| anthropic/claude-opus-4.8 | 6.0000 | 30.0000 | 5.0000 | 25.0000 | +20.0% |
| anthropic/claude-opus-4.8-fast | 12.0000 | 60.0000 | 10.0000 | 50.0000 | +20.0% |
| anthropic/claude-sonnet-4.5 | 3.0000 | 15.0000 | 3.0000 | 15.0000 | +0.0% |
| anthropic/claude-sonnet-4.6 | 3.0000 | 15.0000 | 3.0000 | 15.0000 | +0.0% |
| anthropic/claude-sonnet-5 | 2.0000 | 10.0000 | 2.0000 | 10.0000 | +0.0% |
| arcee-ai/trinity-large-thinking | 0.3125 | 1.1250 | 0.2500 | 0.8000 | +25.0% |
| deepseek/deepseek-r1 | 0.5500 | 2.1900 | 0.7000 | 2.5000 | -21.4% |
| deepseek/deepseek-v3.2 | 0.2288 | 0.3432 | 0.2690 | 0.4000 | -14.9% |
| deepseek/deepseek-v4-flash | 0.0900 | 0.1800 | 0.0980 | 0.1960 | -8.2% |
| deepseek/deepseek-v4-pro | 0.4350 | 0.8700 | 0.4350 | 0.8700 | +0.0% |
| google/gemini-2.5-flash | 0.3000 | 2.5000 | 0.3000 | 2.5000 | +0.0% |
| google/gemini-2.5-flash-image | 0.3000 | 2.5000 | 0.3000 | 2.5000 | +0.0% |
| google/gemini-2.5-pro | 1.2500 | 10.0000 | 1.2500 | 10.0000 | +0.0% |
| google/gemini-3-flash-preview | 0.5000 | 3.0000 | 0.5000 | 3.0000 | +0.0% |
| google/gemini-3.1-flash-lite | 0.2500 | 1.5000 | 0.2500 | 1.5000 | +0.0% |
| google/gemini-3.1-pro-preview | 2.0000 | 12.0000 | 2.0000 | 12.0000 | +0.0% |
| google/gemini-3.5-flash | 1.5000 | 9.0000 | 1.5000 | 9.0000 | +0.0% |
| google/gemma-3-12b-it | 0.0900 | 0.2900 | 0.0500 | 0.1500 | +80.0% |
| google/gemma-3-27b-it | 0.0800 | 0.1600 | 0.0800 | 0.4500 | +0.0% |
| google/gemma-3-4b-it | 0.0400 | 0.0800 | 0.0500 | 0.1000 | -20.0% |
| google/gemma-4-26b-a4b-it | 0.1500 | 0.4000 | 0.1200 | 0.3500 | +25.0% |
| google/gemma-4-31b-it | 0.1500 | 0.4000 | 0.1000 | 0.3500 | +50.0% |
| inception/mercury-2 | 0.3125 | 0.9375 | 0.2500 | 0.7500 | +25.0% |
| meta-llama/llama-3.2-3b-instruct | 0.0509 | 0.3350 | 0.0500 | 0.3300 | +1.8% |
| meta-llama/llama-3.3-70b-instruct | 0.1000 | 0.3200 | 0.1300 | 0.4000 | -23.1% |
| minimax/minimax-m2 | 0.3000 | 1.2000 | 0.2550 | 1.0200 | +17.6% |
| minimax/minimax-m2.1 | 0.2900 | 0.9500 | 0.3000 | 1.2000 | -3.3% |
| minimax/minimax-m2.5 | 0.1200 | 0.4800 | 0.1500 | 0.9000 | -20.0% |
| minimax/minimax-m2.7 | 0.1800 | 0.7200 | 0.2500 | 1.0000 | -28.0% |
| minimax/minimax-m3 | 0.4000 | 1.6000 | 0.3000 | 1.2000 | +33.3% |
| mistralai/mistral-large | 0.5000 | 2.0000 | 2.0000 | 6.0000 | -75.0% |
| mistralai/mistral-small-3.2-24b-instruct | 0.0750 | 0.2000 | 0.1000 | 0.3000 | -25.0% |
| mistralai/voxtral-small-24b-2507 | 0.1000 | 0.3000 | 0.1000 | 0.3000 | +0.0% |
| moonshotai/kimi-k2 | 0.5600 | 2.3000 | 0.5700 | 2.3000 | -1.8% |
| moonshotai/kimi-k2-thinking | 0.6000 | 2.5000 | 0.6000 | 2.5000 | +0.0% |
| moonshotai/kimi-k2.5 | 0.3750 | 2.0250 | 0.5700 | 2.8500 | -34.2% |
| moonshotai/kimi-k2.6 | 0.6600 | 3.4100 | 0.6840 | 3.4200 | -3.5% |
| moonshotai/kimi-k2.7-code | 0.7400 | 3.5000 | 0.7100 | 3.4900 | +4.2% |
| moonshotai/kimi-k3 | 3.0000 | 15.0000 | 3.0000 | 15.0000 | +0.0% |
| nousresearch/hermes-3-llama-3.1-405b | 1.1000 | 3.0000 | 1.0000 | 1.0000 | +10.0% |
| nvidia/nemotron-3-nano-30b-a3b | 0.0750 | 0.3000 | 0.0500 | 0.2000 | +50.0% |
| nvidia/nemotron-3-ultra-550b-a55b | 0.5000 | 2.5000 | 0.5000 | 2.2000 | +0.0% |
| openai/gpt-4o | 2.5000 | 10.0000 | 2.5000 | 10.0000 | +0.0% |
| openai/gpt-4o-mini | 0.1500 | 0.6000 | 0.1500 | 0.6000 | +0.0% |
| openai/gpt-5-image | 10.0000 | 10.0000 | 10.0000 | 10.0000 | +0.0% |
| openai/gpt-5-image-mini | 2.5000 | 2.0000 | 2.5000 | 2.0000 | +0.0% |
| openai/gpt-5-mini | 0.2500 | 2.0000 | 0.2500 | 2.0000 | +0.0% |
| openai/gpt-5-nano | 0.0500 | 0.4000 | 0.0500 | 0.4000 | +0.0% |
| openai/gpt-5.2 | 1.7500 | 14.0000 | 1.7500 | 14.0000 | +0.0% |
| openai/gpt-5.2-codex | 1.7500 | 14.0000 | 1.7500 | 14.0000 | +0.0% |
| openai/gpt-5.3-codex | 1.7500 | 14.0000 | 1.7500 | 14.0000 | +0.0% |
| openai/gpt-5.4 | 2.5000 | 15.0000 | 2.5000 | 15.0000 | +0.0% |
| openai/gpt-5.4-image-2 | 8.0000 | 15.0000 | 8.0000 | 15.0000 | +0.0% |
| openai/gpt-5.4-mini | 0.7500 | 4.5000 | 0.7500 | 4.5000 | +0.0% |
| openai/gpt-5.4-nano | 0.2000 | 1.2500 | 0.2000 | 1.2500 | +0.0% |
| openai/gpt-5.4-pro | 30.0000 | 180.0000 | 30.0000 | 180.0000 | +0.0% |
| openai/gpt-5.5 | 5.0000 | 30.0000 | 5.0000 | 30.0000 | +0.0% |
| openai/gpt-5.5-pro | 37.5000 | 225.0000 | 30.0000 | 180.0000 | +25.0% |
| openai/gpt-5.6-luna | 1.0000 | 6.0000 | 1.0000 | 6.0000 | +0.0% |
| openai/gpt-5.6-luna-pro | 1.0000 | 6.0000 | 1.0000 | 6.0000 | +0.0% |
| openai/gpt-5.6-sol | 5.0000 | 30.0000 | 5.0000 | 30.0000 | +0.0% |
| openai/gpt-5.6-sol-pro | 5.0000 | 30.0000 | 5.0000 | 30.0000 | +0.0% |
| openai/gpt-5.6-terra | 2.5000 | 15.0000 | 2.5000 | 15.0000 | +0.0% |
| openai/gpt-5.6-terra-pro | 2.5000 | 15.0000 | 2.5000 | 15.0000 | +0.0% |
| openai/gpt-oss-120b | 0.0700 | 0.2800 | 0.0370 | 0.1700 | +89.2% |
| openai/gpt-oss-20b | 0.0700 | 0.3000 | 0.0290 | 0.1400 | +141.4% |
| openai/gpt-oss-safeguard-20b | 0.0700 | 0.2000 | 0.0750 | 0.3000 | -6.7% |
| qwen/qwen3-235b-a22b-2507 | 0.0900 | 0.1000 | 0.0900 | 0.5500 | +0.0% |
| qwen/qwen3-235b-a22b-thinking-2507 | 0.1000 | 0.1000 | 0.3000 | 3.0000 | -66.7% |
| qwen/qwen3-30b-a3b | 0.1200 | 0.5000 | 0.1300 | 0.5200 | -7.7% |
| qwen/qwen3-32b | 0.1500 | 0.6000 | 0.0800 | 0.2800 | +87.5% |
| qwen/qwen3-coder | 0.2200 | 1.8000 | 0.3800 | 1.5500 | -42.1% |
| qwen/qwen3-coder-30b-a3b-instruct | 0.1500 | 0.6000 | 0.0700 | 0.2700 | +114.3% |
| qwen/qwen3-coder-next | 0.5000 | 1.2000 | 0.1100 | 0.8000 | +354.5% |
| qwen/qwen3-next-80b-a3b-instruct | 0.0900 | 1.1000 | 0.1500 | 1.2000 | -40.0% |
| qwen/qwen3-vl-235b-a22b-instruct | 0.5300 | 2.6600 | 0.2100 | 1.9000 | +152.4% |
| qwen/qwen3-vl-235b-a22b-thinking | 0.2600 | 2.6000 | 0.2600 | 2.6000 | +0.0% |
| qwen/qwen3-vl-30b-a3b-thinking | 0.1300 | 1.5600 | 0.1300 | 1.5600 | +0.0% |
| qwen/qwen3.5-35b-a3b | 0.3125 | 1.2500 | 0.1400 | 1.0000 | +123.2% |
| qwen/qwen3.5-397b-a17b | 0.7500 | 4.5000 | 0.3900 | 2.3400 | +92.3% |
| qwen/qwen3.5-9b | 0.0500 | 0.1500 | 0.1000 | 0.1500 | -50.0% |
| qwen/qwen3.6-27b | 0.3250 | 3.2500 | 0.2880 | 2.4000 | +12.8% |
| qwen/qwen3.7-max | 2.0000 | 6.0000 | 1.4750 | 4.4250 | +35.6% |
| qwen/qwen3.7-plus | 0.5000 | 2.0000 | 0.3200 | 1.2800 | +56.2% |
| tencent/hy3 | 0.2000 | 0.8000 | 0.1320 | 0.5280 | +51.5% |
| x-ai/grok-4.3 | 1.4200 | 2.8300 | 1.2500 | 2.5000 | +13.6% |
| x-ai/grok-4.5 | 2.0000 | 6.0000 | 2.0000 | 6.0000 | +0.0% |
| x-ai/grok-build-0.1 | 2.5000 | 7.5000 | 1.0000 | 2.0000 | +150.0% |
| z-ai/glm-4.5 | 0.6000 | 2.2000 | 0.6000 | 2.2000 | +0.0% |
| z-ai/glm-4.5-air | 0.2000 | 1.1000 | 0.1300 | 0.8500 | +53.8% |
| z-ai/glm-4.6 | 0.4300 | 1.7400 | 0.5000 | 2.0000 | -14.0% |
| z-ai/glm-4.7 | 0.4000 | 1.7500 | 0.4000 | 1.7500 | +0.0% |
| z-ai/glm-4.7-flash | 0.0600 | 0.4000 | 0.0600 | 0.4000 | +0.0% |
| z-ai/glm-5 | 0.6000 | 1.9200 | 0.9500 | 2.5500 | -36.8% |
| z-ai/glm-5-turbo | 1.2000 | 4.0000 | 1.2000 | 4.0000 | +0.0% |
| z-ai/glm-5.1 | 1.4000 | 4.4000 | 0.9660 | 3.0360 | +44.9% |
| z-ai/glm-5.2 | 0.9500 | 3.0000 | 0.8190 | 2.5740 | +16.0% |
| z-ai/glm-5v-turbo | 1.5000 | 5.0000 | 1.2000 | 4.0000 | +25.0% |