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 | jev-1.13 ◀ routed now | chat | $0.0004 | 4 |
| 2 | openai-gpt-oss-20b | chat | $0.0011 | 26 |
| 3 | gemma-3-4b-it | fast | $0.0015 | 19 |
| 4 | gemma-3-12b-it | fast | $0.0020 | 19 |
| 5 | ministral-3-3b-instruct | fast | $0.0020 | 20 |
| 6 | glm-4.7-flash | chat | $0.0024 | 44 |
| 7 | gemma-3-27b-it | chat | $0.0028 | 56 |
| 8 | gemma-4-26b-a4b-it | fast | $0.0028 | 91 |
| 9 | deepseek-v4.1-flash | chat | $0.0029 | 49 |
| 10 | gemini-2.5-flash-image | fast | $0.0033 | 65 |
| … and 171 more model(s) not shown | ||||
highest Artificial Analysis Intelligence Index, then Surplus discount — compares 181 model(s), routes to the cheapest. click any row to see the full list.
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | jev-1.13 ◀ routed now | chat | $0.0004 | 4 |
| 2 | openai-gpt-oss-20b | chat | $0.0011 | 26 |
| 3 | gemma-3-4b-it | fast | $0.0015 | 19 |
| 4 | gemma-3-12b-it | fast | $0.0020 | 19 |
| 5 | ministral-3-3b-instruct | fast | $0.0020 | 20 |
| 6 | glm-4.7-flash | chat | $0.0024 | 44 |
| 7 | gemma-3-27b-it | chat | $0.0028 | 56 |
| 8 | gemma-4-26b-a4b-it | fast | $0.0028 | 91 |
| 9 | deepseek-v4.1-flash | chat | $0.0029 | 49 |
| 10 | gemini-2.5-flash-image | fast | $0.0033 | 65 |
| … and 171 more model(s) not shown | ||||
highest AA median tokens/sec inside the 20% quality band — compares 181 model(s), routes to the cheapest. click any row to see the full list.
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | jev-1.13 ◀ routed now | chat | $0.0004 | 4 |
| 2 | openai-gpt-oss-20b | chat | $0.0011 | 26 |
| 3 | gemma-3-4b-it | fast | $0.0015 | 19 |
| 4 | gemma-3-12b-it | fast | $0.0020 | 19 |
| 5 | ministral-3-3b-instruct | fast | $0.0020 | 20 |
| 6 | glm-4.7-flash | chat | $0.0024 | 44 |
| 7 | gemma-3-27b-it | chat | $0.0028 | 56 |
| 8 | gemma-4-26b-a4b-it | fast | $0.0028 | 91 |
| 9 | deepseek-v4.1-flash | chat | $0.0029 | 49 |
| 10 | gemini-2.5-flash-image | fast | $0.0033 | 65 |
| … and 171 more model(s) not shown | ||||
multimodal / vision pool, then the value rule — compares 5 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 | 19 |
| 2 | qwen3-vl-235b-a22b-instruct | vision | $0.0209 | 26 |
| 3 | qwen3-vl-30b-a3b-thinking | vision | $0.4600 | 25 |
| 4 | qwen3-vl-235b-a22b-thinking | vision | $0.5264 | 31 |
| 5 | glm-5v-turbo | vision | $1.4513 | 27 |
your intelligence / speed / discount mix (surp_weights=cost:intel:speed) — compares 181 model(s), routes to the cheapest. click any row to see the full list.
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | jev-1.13 ◀ routed now | chat | $0.0004 | 4 |
| 2 | openai-gpt-oss-20b | chat | $0.0011 | 26 |
| 3 | gemma-3-4b-it | fast | $0.0015 | 19 |
| 4 | gemma-3-12b-it | fast | $0.0020 | 19 |
| 5 | ministral-3-3b-instruct | fast | $0.0020 | 20 |
| 6 | glm-4.7-flash | chat | $0.0024 | 44 |
| 7 | gemma-3-27b-it | chat | $0.0028 | 56 |
| 8 | gemma-4-26b-a4b-it | fast | $0.0028 | 91 |
| 9 | deepseek-v4.1-flash | chat | $0.0029 | 49 |
| 10 | gemini-2.5-flash-image | fast | $0.0033 | 65 |
| … and 171 more model(s) not shown | ||||
Jev decision-model routing — TypeSafe Jev picks from the value pool per request (bounded, metadata-only, fail-open) — compares 181 model(s), routes to the cheapest. click any row to see the full list.
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | jev-1.13 ◀ routed now | chat | $0.0004 | 4 |
| 2 | openai-gpt-oss-20b | chat | $0.0011 | 26 |
| 3 | gemma-3-4b-it | fast | $0.0015 | 19 |
| 4 | gemma-3-12b-it | fast | $0.0020 | 19 |
| 5 | ministral-3-3b-instruct | fast | $0.0020 | 20 |
| 6 | glm-4.7-flash | chat | $0.0024 | 44 |
| 7 | gemma-3-27b-it | chat | $0.0028 | 56 |
| 8 | gemma-4-26b-a4b-it | fast | $0.0028 | 91 |
| 9 | deepseek-v4.1-flash | chat | $0.0029 | 49 |
| 10 | gemini-2.5-flash-image | fast | $0.0033 | 65 |
| … and 171 more model(s) not shown | ||||
cheapest coding-class model (coder / codex / qwen3-coder) — compares 7 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 | 25 |
| 2 | kimi-k2.7-code | coding | $0.0066 | 50 |
| 3 | qwen3-coder-next | coding | $0.0091 | 22 |
| 4 | qwen3-coder | coding | $0.0129 | 34 |
| 5 | gpt-5.3-codex | coding | $0.2751 | 38 |
| 6 | qwen3-coder-turbo | coding | $0.7400 | 25 |
| 7 | gpt-5.2-codex | coding | $3.9375 | 17 |
cheapest reasoning model (thinking / r1) — compares 5 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 | 30 |
| 2 | qwen3-235b-a22b-thinking-2507 | reasoning | $0.1000 | 32 |
| 3 | trinity-large-thinking | reasoning | $0.8295 | 3 |
| 4 | deepseek-r1 | reasoning | $1.6000 | 5 |
| 5 | glm-4.7-thinking | reasoning | $1.8375 | 2 |
cheapest small/fast model (mini / nano / lite / small) — compares 44 model(s), routes to the cheapest. click any row to see the full list.
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | gemma-3-4b-it ◀ routed now | fast | $0.0015 | 19 |
| 2 | gemma-3-12b-it | fast | $0.0020 | 19 |
| 3 | ministral-3-3b-instruct | fast | $0.0020 | 20 |
| 4 | gemma-4-26b-a4b-it | fast | $0.0028 | 91 |
| 5 | gemini-2.5-flash-image | fast | $0.0033 | 65 |
| 6 | qwen3-coder-30b-a3b-instruct | coding | $0.0035 | 25 |
| 7 | nvidia-nemotron-3-nano-30b-a3b | fast | $0.0037 | 62 |
| 8 | ministral-3-14b-instruct | fast | $0.0042 | 22 |
| 9 | ministral-3-8b-instruct | fast | $0.0042 | 20 |
| 10 | glm-4.5-air | fast | $0.0052 | 20 |
| … and 34 more model(s) not shown | ||||
cheapest multimodal vision model (-vl / vision / 5v) — compares 5 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 | 19 |
| 2 | qwen3-vl-235b-a22b-instruct | vision | $0.0209 | 26 |
| 3 | qwen3-vl-30b-a3b-thinking | vision | $0.4600 | 25 |
| 4 | qwen3-vl-235b-a22b-thinking | vision | $0.5264 | 31 |
| 5 | glm-5v-turbo | vision | $1.4513 | 27 |
cheapest general text LLM (no specialization) — compares 164 model(s), routes to the cheapest. click any row to see the full list.
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | jev-1.13 ◀ routed now | chat | $0.0004 | 4 |
| 2 | openai-gpt-oss-20b | chat | $0.0011 | 26 |
| 3 | gemma-3-4b-it | fast | $0.0015 | 19 |
| 4 | gemma-3-12b-it | fast | $0.0020 | 19 |
| 5 | ministral-3-3b-instruct | fast | $0.0020 | 20 |
| 6 | glm-4.7-flash | chat | $0.0024 | 44 |
| 7 | gemma-3-27b-it | chat | $0.0028 | 56 |
| 8 | gemma-4-26b-a4b-it | fast | $0.0028 | 91 |
| 9 | deepseek-v4.1-flash | chat | $0.0029 | 49 |
| 10 | gemini-2.5-flash-image | fast | $0.0033 | 65 |
| … and 154 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 | 25 |
cheapest FRONTIER-tier coding model — 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 | 25 |
| 2 | qwen3-coder-next | coding | $0.0091 | 22 |
| 3 | qwen3-coder | coding | $0.0129 | 34 |
| 4 | gpt-5.3-codex | coding | $0.2751 | 38 |
| 5 | qwen3-coder-turbo | coding | $0.7400 | 25 |
| 6 | gpt-5.2-codex | coding | $3.9375 | 17 |
cheapest FRONTIER-tier reasoning model — compares 1 model(s), routes to the cheapest. click any row to see the full list.
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | deepseek-r1 ◀ routed now | reasoning | $1.6000 | 5 |
cheapest FRONTIER-tier vision model — compares 5 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 | 19 |
| 2 | qwen3-vl-235b-a22b-instruct | vision | $0.0209 | 26 |
| 3 | qwen3-vl-30b-a3b-thinking | vision | $0.4600 | 25 |
| 4 | qwen3-vl-235b-a22b-thinking | vision | $0.5264 | 31 |
| 5 | glm-5v-turbo | vision | $1.4513 | 27 |
cheapest FRONTIER-tier chat model — compares 38 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 | $0.0143 | 38 |
| 2 | grok-4.3 | chat | $0.0371 | 61 |
| 3 | claude-sonnet-4.6 | chat | $0.0674 | 59 |
| 4 | grok-4.7 | chat | $0.0816 | 21 |
| 5 | kimi-k3 | chat | $0.1224 | 59 |
| 6 | gpt-5.6-terra | chat | $0.1312 | 36 |
| 7 | gemini-3.1-pro-preview | fast | $0.1400 | 59 |
| 8 | qwen3.5-397b-a17b | chat | $0.2050 | 34 |
| 9 | grok-4.5 | chat | $0.2371 | 46 |
| 10 | claude-opus-4.6 | chat | $0.2586 | 66 |
| … and 28 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 | 25 |
| 2 | gemini-3.1-pro-preview | fast | $0.1400 | 59 |
| 3 | gemini-2.5-pro | fast | $0.3375 | 14 |
| 4 | gemini-3.1-pro | fast | $1.5369 | 3 |
alias of best-coding — compares 7 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 | 25 |
| 2 | kimi-k2.7-code | coding | $0.0066 | 50 |
| 3 | qwen3-coder-next | coding | $0.0091 | 22 |
| 4 | qwen3-coder | coding | $0.0129 | 34 |
| 5 | gpt-5.3-codex | coding | $0.2751 | 38 |
| 6 | qwen3-coder-turbo | coding | $0.7400 | 25 |
| 7 | gpt-5.2-codex | coding | $3.9375 | 17 |
alias of best-chat — compares 164 model(s), routes to the cheapest. click any row to see the full list.
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | jev-1.13 ◀ routed now | chat | $0.0004 | 4 |
| 2 | openai-gpt-oss-20b | chat | $0.0011 | 26 |
| 3 | gemma-3-4b-it | fast | $0.0015 | 19 |
| 4 | gemma-3-12b-it | fast | $0.0020 | 19 |
| 5 | ministral-3-3b-instruct | fast | $0.0020 | 20 |
| 6 | glm-4.7-flash | chat | $0.0024 | 44 |
| 7 | gemma-3-27b-it | chat | $0.0028 | 56 |
| 8 | gemma-4-26b-a4b-it | fast | $0.0028 | 91 |
| 9 | deepseek-v4.1-flash | chat | $0.0029 | 49 |
| 10 | gemini-2.5-flash-image | fast | $0.0033 | 65 |
| … and 154 more model(s) not shown | ||||
treasury-sponsored free inference with live fallback and daily limits — compares 181 model(s), routes to the cheapest. click any row to see the full list.
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | jev-1.13 ◀ routed now | chat | $0.0004 | 4 |
| 2 | openai-gpt-oss-20b | chat | $0.0011 | 26 |
| 3 | gemma-3-4b-it | fast | $0.0015 | 19 |
| 4 | gemma-3-12b-it | fast | $0.0020 | 19 |
| 5 | ministral-3-3b-instruct | fast | $0.0020 | 20 |
| 6 | glm-4.7-flash | chat | $0.0024 | 44 |
| 7 | gemma-3-27b-it | chat | $0.0028 | 56 |
| 8 | gemma-4-26b-a4b-it | fast | $0.0028 | 91 |
| 9 | deepseek-v4.1-flash | chat | $0.0029 | 49 |
| 10 | gemini-2.5-flash-image | fast | $0.0033 | 65 |
| … and 171 more model(s) not shown | ||||
legacy alias of surp/free (treasury-sponsored) — compares 181 model(s), routes to the cheapest. click any row to see the full list.
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | jev-1.13 ◀ routed now | chat | $0.0004 | 4 |
| 2 | openai-gpt-oss-20b | chat | $0.0011 | 26 |
| 3 | gemma-3-4b-it | fast | $0.0015 | 19 |
| 4 | gemma-3-12b-it | fast | $0.0020 | 19 |
| 5 | ministral-3-3b-instruct | fast | $0.0020 | 20 |
| 6 | glm-4.7-flash | chat | $0.0024 | 44 |
| 7 | gemma-3-27b-it | chat | $0.0028 | 56 |
| 8 | gemma-4-26b-a4b-it | fast | $0.0028 | 91 |
| 9 | deepseek-v4.1-flash | chat | $0.0029 | 49 |
| 10 | gemini-2.5-flash-image | fast | $0.0033 | 65 |
| … and 171 more model(s) not shown | ||||