OpenAI

{ "publicModel": "gpt-5.5", "adapterKey": "openai", "upstreamModel": "gpt-5.5", "credentials": { "apiKey": "sk-..." } }

• Credentials: apiKey only.
• Text transports: both Responses and Chat Completions are supported. Without an operator override, each public endpoint prefers its matching native transport. transportOverrides can pin text.generate when a deployment intentionally needs one transport for every public text contract.
• Reasoning: openai_effort (reasoning_effort) on reasoning-family models. -chat suffixed variants (e.g. gpt-5.2-chat) are non-reasoning — the real API rejects reasoning_effort on them, and the catalog declares them without a reasoning spec accordingly. On GPT-5.6, xhigh and max are separate tiers and are forwarded unchanged.
• Encrypted reasoning round-trips through the client. On reasoning-capable models the upstream call sets store: false and requests include: ["reasoning.encrypted_content"]; the encrypted state is returned to the client (native reasoning items on /v1/responses, message-level provider_specific_fields on /v1/chat/completions) and replayed upstream when echoed back. Responses are therefore never stored in your OpenAI account. See Provider-specific fields.
• Responses WebSocket: public WebSocket sessions terminate at the gateway. The OpenAI adapter opens a separate upstream /responses WebSocket, maps public response ids to private upstream ids, and uses incremental continuation while the same deployment remains selected. Routing to another deployment reconstructs the full canonical context instead of leaking or forwarding provider events directly.
• Images: gpt-image-* models; always returns b64_json regardless of requested response_format (see Images).
• Videos: Sora profiles are included for OpenAI-shaped compatibility, but OpenAI's current docs mark the Sora 2 Videos API deprecated with shutdown scheduled for September 24, 2026.
• Catalog: src/adapters/openai/catalog.json.

What to read next

• Creating deployments — the full request shape.
• Reasoning — the openai_effort kind in detail.
• Videos — the async video lifecycle.