OpenAI

Responses go through /v1/chat/completions with max_completion_tokens; LLM_OPENAI_REASONING_EFFORT=low|medium|high|none sets the reasoning field (omit drops it). Temperature is omitted by default for the reasoning models.

bash

LLM_CHAIN=openai,anthropic   # failover to a second endpoint is one more name
LLM_OPENAI_API_KEY=sk-…
LLM_OPENAI_MODEL=gpt-5.6-luna

Every endpoint takes the same knobs: LLM_<NAME>_TEMPERATURE (none omits it), LLM_<NAME>_BODY (JSON merged into every request), LLM_<NAME>_PRICE (input,cached,output per million, for the cost ledger), LLM_<NAME>_NOTES (a per-model notes file). Two models of one provider: LLM_FAST_PRESET=openai under another name. Environment has the full list.

Check it: npm run gateway, then curl localhost:8787/api/health — the llm.chain entry shows the endpoint, whether its key is set, and its state.

Provider docs: https://platform.openai.com/docs

Source: docs/providers/openai.md — edit it there; the site mirrors the repository.

OpenAI ​

OpenAI