Get started
Compatibility
What each of the three formats accepts, at a glance, and the few requests that are refused.
On this page
One key, three formats
One key, the same models, three reply formats: Chat completions, Responses and Messages. Use the one your code or SDK already uses. The differences are in the request, not in what a model can do. A model built for decisions is the exception: it answers its own endpoint only.
This page shows what each format accepts, so you can tell quickly whether a request works as it is. The fields, the reply and the refusals in full are on that format’s own page.
What each format accepts
| Request | Chat completions | Responses | Messages |
|---|---|---|---|
| A streamed reply | Yes | Yes | Yes |
Function tools, with tools | Yes | Yes | Yes |
Choosing a tool with tool_choice | Yes | Yes | Yes |
| Text from an image | image_url parts | input_image with a URL | image blocks, URL or base64 |
| Reasoning | reasoning_effort | reasoning | thinking |
| Structured output | response_format | text.format | No |
| Temperature, top_p and stop | Yes | Yes | Yes |
| More than one choice in a reply | No | — | — |
| State kept between requests | No | No | No |
Decision questions, at /v1/systemone | — | — | — |
A refusal is never quiet: the request answers 400, naming the field in param. A client that sends something this API doesn’t do hears about it on the first call, not in the reply.
Where the habits differ
Before you point an existing client at this API, there are three habits to know.
- Nothing is stored. There is no
previous_response_id, noconversationand no stored reply: send the earlier turns ininputormessageson every call.storeis accepted and ignored. - A model may be called in all three formats, but a field that only one format has stays there. Structured output lives on Chat completions and Responses; Messages refuses it, and its own approach is a tool the model has to call.
- Model IDs are this API’s, not another API’s. List models gives the IDs this key can call, which is also the list an SDK asking for models will see.
What isn’t there
| What | What happens |
|---|---|
| Files, batches, assistants, threads, embeddings, audio and image generation | Not served. Only the three reply formats, their model lists and count tokens exist. |
| Long-running or background requests | Refused with a 400. A streamed reply is the way to wait for a long one. |
| Multiple choices in one request | Refused with a 400 on Chat completions. Send separate requests. |
Every format’s page lists what it accepts and what each refusal looks like: Chat completions, Responses, Messages.
Requests are standard HTTPS with your key in a header, so an SDK needs only the base URL and the key: see OpenAI and Anthropic SDKs. Error codes are on Errors.