Dobby is freeeeeee — no key, no signup, no card. We don't read docs, we call the endpoint and publish what came back, including the 402s.
openrouter
OpenRouter — docs
Call it
- Base URL
https://openrouter.ai/api/v1- API key
- your own from OpenRouter
curl https://openrouter.ai/api/v1/chat/completions \
-H 'Authorization: Bearer YOUR_OPENROUTER_API_KEY' \
-H 'Content-Type: application/json' \
-d '{"model":"cohere/north-mini-code:free","messages":[{"role":"user","content":"hello"}]}'OPENAI_BASE_URL=https://openrouter.ai/api/v1
OPENAI_API_KEY=your-openrouter-api-key
OPENAI_MODEL=cohere/north-mini-code:freeUsing cohere/north-mini-code:free, answered all 5 checks we made in the last week, last answered our key 14 h ago from this server's address. Every model this endpoint offers is in the table below.
This provider requires an API key. Every row below was measured with stillworks' own free-tier key, from this server's address, at the time shown. That says the endpoint answered our account — it says nothing about what a new signup's free tier includes, and we have no way to measure that for you. Our key is never shown here, returned by the API, or stored in the database.
Free tier, key required. Account opened 2026-08-04 with Google sign-in and a terms checkbox: no card, no phone number. This row reads the zero-price slice of the catalogue: 16 of 338 models cost nothing on that date, 14 of them carrying the :free suffix. Two facts measured here that the marketing does not lead with -- meta-llama/llama-3.3-70b-instruct:free, which every free-LLM list still names, returns 404 and exists only as a paid slug; and the free models are shared upstream pools that answer 429 under load rather than queueing.
Models
| Model | Tier | Answers our key | Chat | Tools | Schema | JSON | Vision | Draws | Worked | Last checked | Last listed |
|---|---|---|---|---|---|---|---|---|---|---|---|
cohere/north-mini-code:free | — | yes, on our key | yes | yes | no | no | — | — | 5/5 | 14 h ago | 21 min ago |
deepseek/deepseek-v4-flash-0731:free | — | yes, on our key | yes | yes | yes | yes | — | — | 2/2 | 6 h ago | 21 min ago |
dots-studio/dots-3-note-preview:free | — | yes, on our key | yes | yes | yes | yes | yes | — | 5/5 | 26 h ago | 21 min ago |
google/gemma-4-26b-a4b-it:free | — | yes, on our key | yes | yes | yes | no, claimed | yes | — | 2/5 | 8 h ago | 21 min ago |
google/gemma-4-31b-it:free | — | yes, on our key | yes | — | — | yes | — | — | 1/5 | 34 h ago | 21 min ago |
inclusionai/ling-3.0-flash-fin:free | — | yes, on our key | yes | yes | no | no | — | — | 5/5 | 15 h ago | 21 min ago |
inclusionai/ling-3.0-flash-sante:free | — | yes, on our key | yes | yes | no | no | — | — | 5/5 | 12 h ago | 21 min ago |
inclusionai/ling-3.0-flash-vl:free | — | yes, on our key | yes | yes | no | — | yes | — | 4/5 | 21 h ago | 21 min ago |
inclusionai/ling-3.0-flash:free | — | yes, on our key | yes | yes | no | no | — | — | 0/5 | 18 h ago | 44 days ago |
inclusionai/ling-3.0-tiny:free | — | yes, on our key | yes | yes | no | no | — | — | 0/5 | 23 h ago | 37 days ago |
liquid/lfm-2.5-2.6b:free | — | yes, on our key | yes | yes | yes | yes | — | — | 5/5 | 19 h ago | 21 min ago |
minimax/minimax-m2.7:free | — | yes, on our key | yes | yes | yes | no, claimed | — | — | 0/5 | 25 h ago | 12 days ago |
minimax/minimax-m3:free | — | yes, on our key | yes | yes | no | no, claimed | no | — | 0/5 | 24 h ago | 12 days ago |
nex-agi/nex-n2.5-mini:free | — | yes, on our key | yes | — | — | yes | — | — | 3/5 | 1 h ago | 21 min ago |
nex-agi/nex-n2.5-pro:free | — | yes, on our key | yes | yes | yes | yes | yes | — | 5/6 | 21 min ago | 21 min ago |
nvidia/nemotron-3-nano-30b-a3b:free | — | yes, on our key | yes | yes | yes | yes | — | — | 0/5 | 20 h ago | 26 days ago |
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free | — | yes, on our key | yes | yes | yes | yes | yes | — | 3/5 | 3 h ago | 21 min ago |
nvidia/nemotron-3-super-120b-a12b:free | — | yes, on our key | yes | yes | yes | yes | — | — | 4/5 | 28 h ago | 21 min ago |
nvidia/nemotron-3-ultra-550b-a55b:free | — | yes, on our key | yes | yes | yes | yes | — | — | 3/5 | 7 h ago | 21 min ago |
nvidia/nemotron-3.5-content-safety:free | — | yes, on our key | yes | — | no | no | — | — | 5/5 | 9 h ago | 21 min ago |
nvidia/nemotron-3.5-lightning:free | — | yes, on our key | yes | yes | yes | yes | — | — | 3/5 | 2 h ago | 21 min ago |
nvidia/nemotron-nano-12b-v2-vl:free | — | yes, on our key | yes | yes | yes | yes | yes | — | 0/5 | 27 h ago | 26 days ago |
nvidia/nemotron-nano-9b-v2:free | — | yes, on our key | yes | yes | yes | yes | — | — | 0/5 | 33 h ago | 26 days ago |
openai/gpt-oss-20b:free | — | yes, on our key | yes | yes | yes | yes | — | — | 0/5 | 22 h ago | 28 days ago |
poolside/laguna-s-2.1:free | — | yes, on our key | yes | yes | yes | no | — | — | 3/5 | 17 h ago | 21 min ago |
poolside/laguna-xs-2.1:free | — | yes, on our key | yes | yes | yes | — | — | — | 2/5 | 10 h ago | 21 min ago |
stealth/ox-alpha | — | yes, on our key | yes | no, claimed | no | yes | yes | — | 0/5 | 30 h ago | 24 days ago |
z-ai/glm-5.2:free | — | yes, on our key | yes | — | — | yes | — | — | 0/5 | 16 h ago | 21 min ago |
~z-ai/glm-latest | — | yes, on our key | yes | yes | yes | yes | — | — | 5/5 | 11 h ago | 19 days ago |
google/lyria-3-clip-preview | — | not yet checked | yes | — | — | — | — | — | 0/5 | 4 h ago | 21 min ago |
google/lyria-3-pro-preview | — | not yet checked | yes | — | — | — | — | — | 0/5 | 29 h ago | 21 min ago |
qwen/qwen3.8-27b:free | — | not yet checked | yes | — | — | — | — | — | 0/2 | 13 h ago | 21 min ago |
stealth/union-alpha | — | not yet checked | yes | — | — | — | — | — | 0/3 | 5 h ago | 44 h ago |
thinkingmachines/inkling-small:free | — | not yet checked | yes | — | — | — | — | — | 0/5 | 32 h ago | 21 min ago |
thinkingmachines/inkling:free | — | not yet checked | yes | — | — | — | — | — | 0/5 | 31 h ago | 21 min ago |
Scroll the table sideways for the rest of each row. Chat, Worked and Last listed are folded away at this width.
Feature columns are measurements. Where the provider's own listing claims a feature we could not get out of it, the cell says so — that disagreement is the reason this shelf exists.
What Tools, Schema, JSON and Vision mean, and what each cell state means
The columns
Each name links to the call this endpoint's verdict was read from.
- Tools
- We sent a
toolsarray and the model came back with a well-formedtool_callsentry an agent could dispatch. A 200 with no tool call in it is not tool support, and is recorded as a no. - Schema
- The strict structured-output mode:
response_format: {"type": "json_schema", …}. The reply parsed and matched the schema we sent. - JSON
- The weaker mode:
response_format: {"type": "json_object"}. Valid JSON, with no shape enforced. The two come apart in both directions — OVH'sMistral-7B-Instruct-v0.3does the strict form and emits invalid JSON for the weak one; llm7'smeta-Llama-3.1-8B-Instruct-Turbodoesjson_objectwhilejson_schemaanswers 405. - Vision
- A real image went in inline and a correct answer about it came back. We ask about something only a model that looked could know.
- Draws
- On an endpoint's own page: bytes came back with an image content type, and they really are an image. Not a 200 taken on trust.
The cell states
- yes
- A real call proved it, at the time the endpoint page prints beside that call. The dot's tooltip says the same thing where there is a pointer to hover with.
- no
- A clean negative: the parameter was refused, or the answer did not conform.
- no, claimed
- The negative contradicts the provider's own published claim — their listing advertises the feature and our call could not get it out of the model. This is the most interesting cell on the site and the reason the shelf exists.
- never probed
- No verdict. Either nobody has asked yet, or the check ran and got no usable answer back — Pollinations sits here because its anonymous pool answered 402 to every feature probe. It is a question, never a no.
The same columns, in the API
curl 'https://stillworks.supercapybara.com/api/llm/up?feature=tools,json_schema'The names are the API's spelling of the columns: tools, json_schema, json_object, vision, image_out. Several are and, never or — a row comes back only if a real call proved every feature named. Models we never probed for one of them are left out rather than optimistically included, so a filtered shelf is shorter than a hopeful one.
The call behind each verdict
One row per feature: the most recent call that decided that column, whatever it answered. A refusal is the evidence behind a no exactly as a success is the evidence behind a yes, so both are here.
| Feature | When | Outcome | HTTP | Latency | Model | Detail |
|---|---|---|---|---|---|---|
| Tools | 1 h ago | ok | 200 | 808 ms | inclusionai/ling-3.0-flash-sante:free | |
| Schema | 1 h ago | client_error | 400 | 165 ms | inclusionai/ling-3.0-flash-sante:free | Provider returned error |
| JSON | 1 h ago | client_error | 400 | 182 ms | inclusionai/ling-3.0-flash-sante:free | Provider returned error |
| Vision | 1 h ago | client_error | 404 | 22 ms | inclusionai/ling-3.0-flash-sante:free | No endpoints found that support image input |
Raw probe log
Our working, so you can check it rather than trust it. Wider than the page at any width — scroll it sideways for the Detail column, which quotes the provider's own refusal back.
| When | Kind | Outcome | HTTP | Latency | Model | Detail |
|---|---|---|---|---|---|---|
| 21 min ago | chat | ok | 200 | 1158 ms | nex-agi/nex-n2.5-pro:free | |
| 21 min ago | models | ok | 200 | 21 ms | — | |
| 1 h ago | chat | ok | 200 | 1838 ms | nex-agi/nex-n2.5-mini:free | |
| 1 h ago | models | ok | 200 | 107 ms | — | |
| 1 h ago | vision | client_error | 404 | 22 ms | inclusionai/ling-3.0-flash-sante:free | No endpoints found that support image input |
| 1 h ago | json_object | client_error | 400 | 182 ms | inclusionai/ling-3.0-flash-sante:free | Provider returned error |
| 1 h ago | json_schema | client_error | 400 | 165 ms | inclusionai/ling-3.0-flash-sante:free | Provider returned error |
| 1 h ago | tools | ok | 200 | 808 ms | inclusionai/ling-3.0-flash-sante:free | |
| 1 h ago | vision | ok | 200 | 1339 ms | nvidia/nemotron-3.5-content-safety:free | no colour named in: User Safety: safe |
| 1 h ago | json_object | ok | 200 | 1385 ms | nvidia/nemotron-3.5-content-safety:free | content is not a JSON object: User Safety: safe |
| 1 h ago | json_schema | ok | 200 | 1462 ms | nvidia/nemotron-3.5-content-safety:free | content is not a JSON object: User Safety: safe |
| 1 h ago | tools | client_error | 404 | 212 ms | nvidia/nemotron-3.5-content-safety:free | No endpoints found that support tool use. Try disabling "get_weather". To learn more about… |
| 2 h ago | chat | timeout | — | 25001 ms | nvidia/nemotron-3.5-lightning:free | Post "https://openrouter.ai/api/v1/chat/completions": context deadline exceeded (Client.Ti… |
| 2 h ago | models | ok | 200 | 106 ms | — | |
| 3 h ago | chat | bad_body | 200 | 499 ms | nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free | 200 with no completion in the body |
| 3 h ago | models | ok | 200 | 181 ms | — | |
| 4 h ago | chat | server_error | 502 | 1734 ms | google/lyria-3-clip-preview | Provider returned error |
| 4 h ago | models | ok | 200 | 121 ms | — | |
| 5 h ago | chat | client_error | 404 | 231 ms | stealth/union-alpha | Thank you for participating in the Stealth Union Alpha testing period. This model was Unbi… |
| 5 h ago | models | ok | 200 | 160 ms | — | |
| 6 h ago | chat | ok | 200 | 2094 ms | deepseek/deepseek-v4-flash-0731:free | |
| 6 h ago | models | ok | 200 | 121 ms | — | |
| 7 h ago | chat | bad_body | 200 | 486 ms | nvidia/nemotron-3-ultra-550b-a55b:free | 200 with no completion in the body |
| 7 h ago | models | ok | 200 | 443 ms | — | |
| 8 h ago | chat | ok | 200 | 1316 ms | google/gemma-4-26b-a4b-it:free | |
| 8 h ago | models | ok | 200 | 260 ms | — | |
| 9 h ago | chat | ok | 200 | 1210 ms | nvidia/nemotron-3.5-content-safety:free | |
| 9 h ago | models | ok | 200 | 154 ms | — | |
| 10 h ago | chat | rate_limited | 429 | 601 ms | poolside/laguna-xs-2.1:free | Provider returned error |
| 10 h ago | models | ok | 200 | 495 ms | — | |
| 11 h ago | chat | ok | 200 | 1038 ms | ~z-ai/glm-latest | |
| 11 h ago | models | ok | 200 | 527 ms | — | |
| 12 h ago | chat | ok | 200 | 2664 ms | inclusionai/ling-3.0-flash-sante:free | |
| 12 h ago | models | ok | 200 | 573 ms | — | |
| 13 h ago | chat | rate_limited | 429 | 686 ms | qwen/qwen3.8-27b:free | Provider returned error |
| 13 h ago | models | ok | 200 | 576 ms | — | |
| 14 h ago | chat | ok | 200 | 748 ms | cohere/north-mini-code:free | |
| 14 h ago | models | ok | 200 | 105 ms | — | |
| 15 h ago | chat | ok | 200 | 811 ms | inclusionai/ling-3.0-flash-fin:free | |
| 15 h ago | models | ok | 200 | 146 ms | — |