Integrations

GPT (OpenAI-compatible)

Call GPT models through the Chat Completions API with the OpenAI SDK or curl.

GPT models are served through an OpenAI-compatible Chat Completions endpoint, so any OpenAI client works unchanged.

  • Base URL: https://api.roteo.ai/v1
  • Auth: Authorization: Bearer sk_your_key
  • Endpoint: POST /v1/chat/completions

Models

Model IDContextBest for
gpt-6-astra1MThe flagship, for the most demanding agentic work.
gpt-6.1-sol1MThe newest Sol, fast and economical for everyday agentic work.
gpt-6-luna1MThe lightest and most economical option.
gpt-5.6-sol1MThe previous Sol, a pinned agentic model.
gpt-5.6-terra1MA balanced mid-tier option.

Model IDs are served verbatim, so copy them exactly.

Make a request

curl https://api.roteo.ai/v1/chat/completions \
-H "Authorization: Bearer sk_your_key" \
-H "content-type: application/json" \
-d '{
  "model": "gpt-5.6-sol",
  "messages": [{ "role": "user", "content": "Hello, Roteo!" }],
  "stream": true
}'
bash · 8 lines

Set "stream": true for server-sent events as the model generates. Tools work as with the OpenAI API: pass tools and read tool_calls back. See Streaming, Tool use and Reasoning.

Bill a specific chain

Add x-roteo-billing-chain (base, arbitrum, solana or robinhood) to bill a call on a specific chain. Omit it to use your dashboard default; every response echoes the chain it billed on. See Billing chains.

See also

GPT (OpenAI-compatible) | Roteo