surp/best-chat --interactive
Pick a combo, send a message. The first request will return 402 with payment requirements — you'll sign with your wallet, and the completion will stream back. (Real USDC on Base mainnet — sign with your wallet.)
| combo | routes to | USD / 1M tok | vs $9/1M list | pool |
|---|---|---|---|---|
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | openai-gpt-oss-20b ◀ routed now | chat | $0.0001 | 46 |
| 2 | openai-gpt-oss-120b | chat | $0.0004 | 69 |
| 3 | openai-gpt-oss-safeguard-20b | chat | $0.0004 | 37 |
| 4 | qwen3.8-omni-flash | chat | $0.0007 | 20 |
| 5 | glm-4.5-air | fast | $0.0010 | 19 |
| 6 | gemma-3-4b-it | fast | $0.0010 | 18 |
| 7 | deepseek-v4.1-flash | chat | $0.0016 | 36 |
| 8 | gemini-2.5-flash-image | fast | $0.0017 | 81 |
| 9 | minimax-m2.1 | fast | $0.0018 | 27 |
| 10 | gemma-4-26b-a4b-it | fast | $0.0019 | 96 |
| … and 152 more model(s) not shown | ||||
highest Artificial Analysis Intelligence Index, then Surplus discount — compares 162 model(s), routes to the cheapest. click any row to see the full list.
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | openai-gpt-oss-20b ◀ routed now | chat | $0.0001 | 46 |
| 2 | openai-gpt-oss-120b | chat | $0.0004 | 69 |
| 3 | openai-gpt-oss-safeguard-20b | chat | $0.0004 | 37 |
| 4 | qwen3.8-omni-flash | chat | $0.0007 | 20 |
| 5 | glm-4.5-air | fast | $0.0010 | 19 |
| 6 | gemma-3-4b-it | fast | $0.0010 | 18 |
| 7 | deepseek-v4.1-flash | chat | $0.0016 | 36 |
| 8 | gemini-2.5-flash-image | fast | $0.0017 | 81 |
| 9 | minimax-m2.1 | fast | $0.0018 | 27 |
| 10 | gemma-4-26b-a4b-it | fast | $0.0019 | 96 |
| … and 152 more model(s) not shown | ||||
highest AA median tokens/sec inside the 20% quality band — compares 162 model(s), routes to the cheapest. click any row to see the full list.
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | openai-gpt-oss-20b ◀ routed now | chat | $0.0001 | 46 |
| 2 | openai-gpt-oss-120b | chat | $0.0004 | 69 |
| 3 | openai-gpt-oss-safeguard-20b | chat | $0.0004 | 37 |
| 4 | qwen3.8-omni-flash | chat | $0.0007 | 20 |
| 5 | glm-4.5-air | fast | $0.0010 | 19 |
| 6 | gemma-3-4b-it | fast | $0.0010 | 18 |
| 7 | deepseek-v4.1-flash | chat | $0.0016 | 36 |
| 8 | gemini-2.5-flash-image | fast | $0.0017 | 81 |
| 9 | minimax-m2.1 | fast | $0.0018 | 27 |
| 10 | gemma-4-26b-a4b-it | fast | $0.0019 | 96 |
| … and 152 more model(s) not shown | ||||
multimodal / vision pool, then the value rule — compares 4 model(s), routes to the cheapest. click any row to see the full list.
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | palmyra-vision-7b ◀ routed now | vision | $0.0168 | 21 |
| 2 | qwen3-vl-235b-a22b-instruct | vision | $0.0209 | 12 |
| 3 | qwen3-vl-30b-a3b-thinking | vision | $0.7700 | 15 |
| 4 | glm-5v-turbo | vision | $3.2240 | 12 |
your intelligence / speed / discount mix (surp_weights=cost:intel:speed) — compares 162 model(s), routes to the cheapest. click any row to see the full list.
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | openai-gpt-oss-20b ◀ routed now | chat | $0.0001 | 46 |
| 2 | openai-gpt-oss-120b | chat | $0.0004 | 69 |
| 3 | openai-gpt-oss-safeguard-20b | chat | $0.0004 | 37 |
| 4 | qwen3.8-omni-flash | chat | $0.0007 | 20 |
| 5 | glm-4.5-air | fast | $0.0010 | 19 |
| 6 | gemma-3-4b-it | fast | $0.0010 | 18 |
| 7 | deepseek-v4.1-flash | chat | $0.0016 | 36 |
| 8 | gemini-2.5-flash-image | fast | $0.0017 | 81 |
| 9 | minimax-m2.1 | fast | $0.0018 | 27 |
| 10 | gemma-4-26b-a4b-it | fast | $0.0019 | 96 |
| … and 152 more model(s) not shown | ||||
Jev decision-model routing — TypeSafe Jev picks from the value pool per request (bounded, metadata-only, fail-open) — compares 162 model(s), routes to the cheapest. click any row to see the full list.
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | openai-gpt-oss-20b ◀ routed now | chat | $0.0001 | 46 |
| 2 | openai-gpt-oss-120b | chat | $0.0004 | 69 |
| 3 | openai-gpt-oss-safeguard-20b | chat | $0.0004 | 37 |
| 4 | qwen3.8-omni-flash | chat | $0.0007 | 20 |
| 5 | glm-4.5-air | fast | $0.0010 | 19 |
| 6 | gemma-3-4b-it | fast | $0.0010 | 18 |
| 7 | deepseek-v4.1-flash | chat | $0.0016 | 36 |
| 8 | gemini-2.5-flash-image | fast | $0.0017 | 81 |
| 9 | minimax-m2.1 | fast | $0.0018 | 27 |
| 10 | gemma-4-26b-a4b-it | fast | $0.0019 | 96 |
| … and 152 more model(s) not shown | ||||
cheapest coding-class model (coder / codex / qwen3-coder) — compares 6 model(s), routes to the cheapest. click any row to see the full list.
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | qwen3-coder-30b-a3b-instruct ◀ routed now | coding | $0.0035 | 24 |
| 2 | qwen3-coder-next | coding | $0.0091 | 13 |
| 3 | qwen3-coder | coding | $0.0129 | 28 |
| 4 | kimi-k2.7-code | coding | $0.0920 | 40 |
| 5 | gpt-5.3-codex | coding | $2.2960 | 57 |
| 6 | gpt-5.2-codex | coding | $3.9375 | 16 |
cheapest reasoning model (thinking / r1) — compares 3 model(s), routes to the cheapest. click any row to see the full list.
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | kimi-k2-thinking ◀ routed now | reasoning | $0.0307 | 28 |
| 2 | qwen3-235b-a22b-thinking-2507 | reasoning | $0.1820 | 17 |
| 3 | trinity-large-thinking | reasoning | $0.8295 | 1 |
cheapest small/fast model (mini / nano / lite / small) — compares 43 model(s), routes to the cheapest. click any row to see the full list.
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | glm-4.5-air ◀ routed now | fast | $0.0010 | 19 |
| 2 | gemma-3-4b-it | fast | $0.0010 | 18 |
| 3 | gemini-2.5-flash-image | fast | $0.0017 | 81 |
| 4 | minimax-m2.1 | fast | $0.0018 | 27 |
| 5 | gemma-4-26b-a4b-it | fast | $0.0019 | 96 |
| 6 | gemma-3-12b-it | fast | $0.0020 | 18 |
| 7 | ministral-3-3b-instruct | fast | $0.0020 | 20 |
| 8 | ministral-3-8b-instruct | fast | $0.0034 | 19 |
| 9 | qwen3-coder-30b-a3b-instruct | coding | $0.0035 | 24 |
| 10 | nvidia-nemotron-3-nano-30b-a3b | fast | $0.0037 | 58 |
| … and 33 more model(s) not shown | ||||
cheapest multimodal vision model (-vl / vision / 5v) — compares 4 model(s), routes to the cheapest. click any row to see the full list.
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | palmyra-vision-7b ◀ routed now | vision | $0.0168 | 21 |
| 2 | qwen3-vl-235b-a22b-instruct | vision | $0.0209 | 12 |
| 3 | qwen3-vl-30b-a3b-thinking | vision | $0.7700 | 15 |
| 4 | glm-5v-turbo | vision | $3.2240 | 12 |
cheapest general text LLM (no specialization) — compares 149 model(s), routes to the cheapest. click any row to see the full list.
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | openai-gpt-oss-20b ◀ routed now | chat | $0.0001 | 46 |
| 2 | openai-gpt-oss-120b | chat | $0.0004 | 69 |
| 3 | openai-gpt-oss-safeguard-20b | chat | $0.0004 | 37 |
| 4 | qwen3.8-omni-flash | chat | $0.0007 | 20 |
| 5 | glm-4.5-air | fast | $0.0010 | 19 |
| 6 | gemma-3-4b-it | fast | $0.0010 | 18 |
| 7 | deepseek-v4.1-flash | chat | $0.0016 | 36 |
| 8 | gemini-2.5-flash-image | fast | $0.0017 | 81 |
| 9 | minimax-m2.1 | fast | $0.0018 | 27 |
| 10 | gemma-4-26b-a4b-it | fast | $0.0019 | 96 |
| … and 139 more model(s) not shown | ||||
cheapest coding model, biased to small/fast variants — compares 1 model(s), routes to the cheapest. click any row to see the full list.
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | qwen3-coder-30b-a3b-instruct ◀ routed now | coding | $0.0035 | 24 |
cheapest FRONTIER-tier coding model — compares 5 model(s), routes to the cheapest. click any row to see the full list.
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | qwen3-coder-30b-a3b-instruct ◀ routed now | coding | $0.0035 | 24 |
| 2 | qwen3-coder-next | coding | $0.0091 | 13 |
| 3 | qwen3-coder | coding | $0.0129 | 28 |
| 4 | gpt-5.3-codex | coding | $2.2960 | 57 |
| 5 | gpt-5.2-codex | coding | $3.9375 | 16 |
cheapest FRONTIER-tier vision model — compares 4 model(s), routes to the cheapest. click any row to see the full list.
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | palmyra-vision-7b ◀ routed now | vision | $0.0168 | 21 |
| 2 | qwen3-vl-235b-a22b-instruct | vision | $0.0209 | 12 |
| 3 | qwen3-vl-30b-a3b-thinking | vision | $0.7700 | 15 |
| 4 | glm-5v-turbo | vision | $3.2240 | 12 |
cheapest FRONTIER-tier chat model — compares 33 model(s), routes to the cheapest. click any row to see the full list.
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | gpt-5.6-luna ◀ routed now | chat | $0.0359 | 42 |
| 2 | grok-4.3 | chat | $0.0371 | 25 |
| 3 | kimi-k3 | chat | $0.0798 | 40 |
| 4 | qwen3.5-397b-a17b | chat | $0.1224 | 25 |
| 5 | gpt-5.6-terra | chat | $0.1376 | 61 |
| 6 | claude-opus-4.7 | chat | $0.2100 | 70 |
| 7 | claude-sonnet-5.5 | chat | $0.3318 | 41 |
| 8 | grok-4.7 | chat | $0.3523 | 30 |
| 9 | grok-4.5 | chat | $0.3556 | 31 |
| 10 | claude-sonnet-4.6 | chat | $0.3919 | 61 |
| … and 23 more model(s) not shown | ||||
cheapest FRONTIER-tier fast model — compares 4 model(s), routes to the cheapest. click any row to see the full list.
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | qwen3-coder-30b-a3b-instruct ◀ routed now | coding | $0.0035 | 24 |
| 2 | gemini-3.1-pro-preview | fast | $0.7700 | 39 |
| 3 | gemini-3.1-pro | fast | $1.5369 | 10 |
| 4 | gemini-2.5-pro | fast | $2.1544 | 13 |
alias of best-coding — compares 6 model(s), routes to the cheapest. click any row to see the full list.
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | qwen3-coder-30b-a3b-instruct ◀ routed now | coding | $0.0035 | 24 |
| 2 | qwen3-coder-next | coding | $0.0091 | 13 |
| 3 | qwen3-coder | coding | $0.0129 | 28 |
| 4 | kimi-k2.7-code | coding | $0.0920 | 40 |
| 5 | gpt-5.3-codex | coding | $2.2960 | 57 |
| 6 | gpt-5.2-codex | coding | $3.9375 | 16 |
alias of best-chat — compares 149 model(s), routes to the cheapest. click any row to see the full list.
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | openai-gpt-oss-20b ◀ routed now | chat | $0.0001 | 46 |
| 2 | openai-gpt-oss-120b | chat | $0.0004 | 69 |
| 3 | openai-gpt-oss-safeguard-20b | chat | $0.0004 | 37 |
| 4 | qwen3.8-omni-flash | chat | $0.0007 | 20 |
| 5 | glm-4.5-air | fast | $0.0010 | 19 |
| 6 | gemma-3-4b-it | fast | $0.0010 | 18 |
| 7 | deepseek-v4.1-flash | chat | $0.0016 | 36 |
| 8 | gemini-2.5-flash-image | fast | $0.0017 | 81 |
| 9 | minimax-m2.1 | fast | $0.0018 | 27 |
| 10 | gemma-4-26b-a4b-it | fast | $0.0019 | 96 |
| … and 139 more model(s) not shown | ||||