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 | deepseek-v4.1-flash ◀ routed now | chat | $0.0012 | 39 |
| 2 | gemma-3-4b-it | fast | $0.0015 | 14 |
| 3 | gemma-3-12b-it | fast | $0.0020 | 12 |
| 4 | gemma-4-e2b | fast | $0.0024 | 5 |
| 5 | gemma-3-27b-it | chat | $0.0028 | 60 |
| 6 | qwen3-coder-30b-a3b-instruct | coding | $0.0035 | 14 |
| 7 | qwen3-32b | chat | $0.0036 | 10 |
| 8 | openai-gpt-oss-120b | chat | $0.0037 | 59 |
| 9 | openai-gpt-oss-20b | chat | $0.0037 | 16 |
| 10 | nvidia-nemotron-3-nano-30b-a3b | fast | $0.0037 | 56 |
| … and 158 more model(s) not shown | ||||
highest Artificial Analysis Intelligence Index, then Surplus discount — compares 168 model(s), routes to the cheapest. click any row to see the full list.
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | deepseek-v4.1-flash ◀ routed now | chat | $0.0012 | 39 |
| 2 | gemma-3-4b-it | fast | $0.0015 | 14 |
| 3 | gemma-3-12b-it | fast | $0.0020 | 12 |
| 4 | gemma-4-e2b | fast | $0.0024 | 5 |
| 5 | gemma-3-27b-it | chat | $0.0028 | 60 |
| 6 | qwen3-coder-30b-a3b-instruct | coding | $0.0035 | 14 |
| 7 | qwen3-32b | chat | $0.0036 | 10 |
| 8 | openai-gpt-oss-120b | chat | $0.0037 | 59 |
| 9 | openai-gpt-oss-20b | chat | $0.0037 | 16 |
| 10 | nvidia-nemotron-3-nano-30b-a3b | fast | $0.0037 | 56 |
| … and 158 more model(s) not shown | ||||
highest AA median tokens/sec inside the 20% quality band — compares 168 model(s), routes to the cheapest. click any row to see the full list.
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | deepseek-v4.1-flash ◀ routed now | chat | $0.0012 | 39 |
| 2 | gemma-3-4b-it | fast | $0.0015 | 14 |
| 3 | gemma-3-12b-it | fast | $0.0020 | 12 |
| 4 | gemma-4-e2b | fast | $0.0024 | 5 |
| 5 | gemma-3-27b-it | chat | $0.0028 | 60 |
| 6 | qwen3-coder-30b-a3b-instruct | coding | $0.0035 | 14 |
| 7 | qwen3-32b | chat | $0.0036 | 10 |
| 8 | openai-gpt-oss-120b | chat | $0.0037 | 59 |
| 9 | openai-gpt-oss-20b | chat | $0.0037 | 16 |
| 10 | nvidia-nemotron-3-nano-30b-a3b | fast | $0.0037 | 56 |
| … and 158 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 | $0.0150 | 9 |
| 2 | qwen3-vl-235b-a22b-instruct | vision | $0.0211 | 15 |
| 3 | qwen3-vl-30b-a3b-thinking | vision | $0.2090 | 36 |
| 4 | qwen3-vl-235b-a22b-thinking | vision | $0.4009 | 48 |
| 5 | glm-5v-turbo | vision | $1.9058 | 26 |
your intelligence / speed / discount mix (surp_weights=cost:intel:speed) — compares 168 model(s), routes to the cheapest. click any row to see the full list.
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | deepseek-v4.1-flash ◀ routed now | chat | $0.0012 | 39 |
| 2 | gemma-3-4b-it | fast | $0.0015 | 14 |
| 3 | gemma-3-12b-it | fast | $0.0020 | 12 |
| 4 | gemma-4-e2b | fast | $0.0024 | 5 |
| 5 | gemma-3-27b-it | chat | $0.0028 | 60 |
| 6 | qwen3-coder-30b-a3b-instruct | coding | $0.0035 | 14 |
| 7 | qwen3-32b | chat | $0.0036 | 10 |
| 8 | openai-gpt-oss-120b | chat | $0.0037 | 59 |
| 9 | openai-gpt-oss-20b | chat | $0.0037 | 16 |
| 10 | nvidia-nemotron-3-nano-30b-a3b | fast | $0.0037 | 56 |
| … and 158 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 | 14 |
| 2 | kimi-k2.7-code | coding | $0.0059 | 66 |
| 3 | qwen3-coder-next | coding | $0.0092 | 12 |
| 4 | qwen3-coder | coding | $0.0130 | 36 |
| 5 | qwen3-coder-turbo | coding | $0.4625 | 28 |
| 6 | gpt-5.3-codex | coding | $0.7830 | 57 |
| 7 | gpt-5.2-codex | coding | $3.9375 | 26 |
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 | $0.0310 | 20 |
| 2 | qwen3-235b-a22b-thinking-2507 | reasoning | $0.0960 | 45 |
| 3 | deepseek-r1 | reasoning | $2.2400 | 5 |
cheapest small/fast model (mini / nano / lite / small) — compares 42 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 | 14 |
| 2 | gemma-3-12b-it | fast | $0.0020 | 12 |
| 3 | gemma-4-e2b | fast | $0.0024 | 5 |
| 4 | qwen3-coder-30b-a3b-instruct | coding | $0.0035 | 14 |
| 5 | nvidia-nemotron-3-nano-30b-a3b | fast | $0.0037 | 56 |
| 6 | ministral-3-3b-instruct | fast | $0.0040 | 10 |
| 7 | gemma-4-26b-a4b-it | fast | $0.0053 | 66 |
| 8 | nvidia-nemotron-nano-9b-v2 | fast | $0.0058 | 10 |
| 9 | ministral-3-8b-instruct | fast | $0.0060 | 10 |
| 10 | ministral-3-14b-instruct | fast | $0.0080 | 10 |
| … and 32 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 | $0.0150 | 9 |
| 2 | qwen3-vl-235b-a22b-instruct | vision | $0.0211 | 15 |
| 3 | qwen3-vl-30b-a3b-thinking | vision | $0.2090 | 36 |
| 4 | qwen3-vl-235b-a22b-thinking | vision | $0.4009 | 48 |
| 5 | glm-5v-turbo | vision | $1.9058 | 26 |
cheapest general text LLM (no specialization) — compares 153 model(s), routes to the cheapest. click any row to see the full list.
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | deepseek-v4.1-flash ◀ routed now | chat | $0.0012 | 39 |
| 2 | gemma-3-4b-it | fast | $0.0015 | 14 |
| 3 | gemma-3-12b-it | fast | $0.0020 | 12 |
| 4 | gemma-4-e2b | fast | $0.0024 | 5 |
| 5 | gemma-3-27b-it | chat | $0.0028 | 60 |
| 6 | qwen3-32b | chat | $0.0036 | 10 |
| 7 | openai-gpt-oss-120b | chat | $0.0037 | 59 |
| 8 | openai-gpt-oss-20b | chat | $0.0037 | 16 |
| 9 | nvidia-nemotron-3-nano-30b-a3b | fast | $0.0037 | 56 |
| 10 | ministral-3-3b-instruct | fast | $0.0040 | 10 |
| … and 143 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 | 14 |
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 | 14 |
| 2 | qwen3-coder-next | coding | $0.0092 | 12 |
| 3 | qwen3-coder | coding | $0.0130 | 36 |
| 4 | qwen3-coder-turbo | coding | $0.4625 | 28 |
| 5 | gpt-5.3-codex | coding | $0.7830 | 57 |
| 6 | gpt-5.2-codex | coding | $3.9375 | 26 |
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 | $2.2400 | 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 | $0.0150 | 9 |
| 2 | qwen3-vl-235b-a22b-instruct | vision | $0.0211 | 15 |
| 3 | qwen3-vl-30b-a3b-thinking | vision | $0.2090 | 36 |
| 4 | qwen3-vl-235b-a22b-thinking | vision | $0.4009 | 48 |
| 5 | glm-5v-turbo | vision | $1.9058 | 26 |
cheapest FRONTIER-tier chat model — compares 37 model(s), routes to the cheapest. click any row to see the full list.
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | grok-4.3 ◀ routed now | chat | $0.0375 | 54 |
| 2 | gpt-5.6-luna | chat | $0.0480 | 40 |
| 3 | gpt-5.6-luna-pro | chat | $0.3500 | 27 |
| 4 | grok-4.20-beta | chat | $0.3750 | 50 |
| 5 | gpt-5.5 | chat | $0.3857 | 78 |
| 6 | gpt-5.6-terra | chat | $0.3997 | 62 |
| 7 | claude-sonnet-4.6 | chat | $0.4225 | 62 |
| 8 | grok-4.1-fast | chat | $0.4375 | 5 |
| 9 | kimi-k3 | chat | $0.4760 | 64 |
| 10 | grok-4.20-multi-agent-beta | chat | $0.5250 | 41 |
| … and 27 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 | 14 |
| 2 | gemini-2.5-pro | fast | $0.6669 | 15 |
| 3 | gemini-3.1-pro-preview | fast | $0.7345 | 51 |
| 4 | gemini-3.1-pro | fast | $2.8000 | 4 |
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 | 14 |
| 2 | kimi-k2.7-code | coding | $0.0059 | 66 |
| 3 | qwen3-coder-next | coding | $0.0092 | 12 |
| 4 | qwen3-coder | coding | $0.0130 | 36 |
| 5 | qwen3-coder-turbo | coding | $0.4625 | 28 |
| 6 | gpt-5.3-codex | coding | $0.7830 | 57 |
| 7 | gpt-5.2-codex | coding | $3.9375 | 26 |
alias of best-chat — compares 153 model(s), routes to the cheapest. click any row to see the full list.
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | deepseek-v4.1-flash ◀ routed now | chat | $0.0012 | 39 |
| 2 | gemma-3-4b-it | fast | $0.0015 | 14 |
| 3 | gemma-3-12b-it | fast | $0.0020 | 12 |
| 4 | gemma-4-e2b | fast | $0.0024 | 5 |
| 5 | gemma-3-27b-it | chat | $0.0028 | 60 |
| 6 | qwen3-32b | chat | $0.0036 | 10 |
| 7 | openai-gpt-oss-120b | chat | $0.0037 | 59 |
| 8 | openai-gpt-oss-20b | chat | $0.0037 | 16 |
| 9 | nvidia-nemotron-3-nano-30b-a3b | fast | $0.0037 | 56 |
| 10 | ministral-3-3b-instruct | fast | $0.0040 | 10 |
| … and 143 more model(s) not shown | ||||
treasury-sponsored free inference with live fallback and daily limits — compares 168 model(s), routes to the cheapest. click any row to see the full list.
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | deepseek-v4.1-flash ◀ routed now | chat | $0.0012 | 39 |
| 2 | gemma-3-4b-it | fast | $0.0015 | 14 |
| 3 | gemma-3-12b-it | fast | $0.0020 | 12 |
| 4 | gemma-4-e2b | fast | $0.0024 | 5 |
| 5 | gemma-3-27b-it | chat | $0.0028 | 60 |
| 6 | qwen3-coder-30b-a3b-instruct | coding | $0.0035 | 14 |
| 7 | qwen3-32b | chat | $0.0036 | 10 |
| 8 | openai-gpt-oss-120b | chat | $0.0037 | 59 |
| 9 | openai-gpt-oss-20b | chat | $0.0037 | 16 |
| 10 | nvidia-nemotron-3-nano-30b-a3b | fast | $0.0037 | 56 |
| … and 158 more model(s) not shown | ||||
legacy alias of surp/free (treasury-sponsored) — compares 168 model(s), routes to the cheapest. click any row to see the full list.
| # | model | class | USD / 1M tok | sellers |
|---|---|---|---|---|
| 1 | deepseek-v4.1-flash ◀ routed now | chat | $0.0012 | 39 |
| 2 | gemma-3-4b-it | fast | $0.0015 | 14 |
| 3 | gemma-3-12b-it | fast | $0.0020 | 12 |
| 4 | gemma-4-e2b | fast | $0.0024 | 5 |
| 5 | gemma-3-27b-it | chat | $0.0028 | 60 |
| 6 | qwen3-coder-30b-a3b-instruct | coding | $0.0035 | 14 |
| 7 | qwen3-32b | chat | $0.0036 | 10 |
| 8 | openai-gpt-oss-120b | chat | $0.0037 | 59 |
| 9 | openai-gpt-oss-20b | chat | $0.0037 | 16 |
| 10 | nvidia-nemotron-3-nano-30b-a3b | fast | $0.0037 | 56 |
| … and 158 more model(s) not shown | ||||