Make room for Muse.
In your own app.
OpenAI-compatible requests. Your API key. An available model route. Start here.
01
QUICKSTART
- BUY
Add a prepaid token block.
- ISSUE
Create a scoped API key.
- ROUTE
Send a standard chat completion.
bash
curl https://openmuse.fun/api/v1/chat/completions \
-H "Authorization: Bearer tlm_live_..." \
-H "Content-Type: application/json" \
-d '{
"model": "jevcontrol/gpt-6-astra",
"messages": [{"role":"user","content":"Review this diff."}]
}'02
AVAILABLE ROUTES
Use the exact model ID returned by GET /v1/models. Legacy jevcontrol/ route IDs remain supported; the workspace name does not change an existing route.
The live route catalog is temporarily unavailable. Your API can list routes using the authenticated models endpoint when the service is connected.
03
NORMALIZED USAGE
Every response returns the underlying token count and its route coefficient. The ledger stays readable across providers.
json
{
"choices": [{"message": {"role": "assistant", "content": "..."}}],
"usage": {"input_tokens": 1840, "output_tokens": 620,
"route_multiplier": 3, "charged_tokens": 7380}
}