Skip to main content
POST
Requires version 2.0.1 or later of the Archetype platform.

Overview

This endpoint takes an OpenAI Responses request and sends it to a model that the Archetype Platform hosts. model names one of the available models that serves Responses: newton-c-2.6 or newton-fusion-1.0. The platform forwards the body to a running copy of that model and returns its response object unchanged. You can call it with an OpenAI SDK by setting the base URL to https://platform.u1.archetypeai.app/api/inference and the API key to your Archetype API key.

Request

string
required
Name of the model to query: newton-c-2.6 or newton-fusion-1.0. A model that doesn’t serve Responses, such as omega-embedding, returns 400. An unknown name returns 404.
string | object[]
required
The conversation: a string, or a list of messages. A message’s content is a string or a list of parts: input_text, input_image, input_video, and input_audio. To continue a conversation, append the previous response’s output to input. Send images and video inline as data: URIs, in a request body under 2 MiB; every image and video frame is resized to 224 × 224 pixels. See Current Limitations.
string
A system message for the model.
boolean
default:"false"
Must be false or omitted. Streaming isn’t supported yet, and true returns 400.
integer
Maximum number of tokens to generate.
number
Sampling temperature, from 0 to 2.
number
Nucleus sampling cutoff, from 0 to 1.
boolean
Accepted with any value, and ignored: the platform doesn’t store responses.
Options that need stored state or features the model doesn’t have return 400: previous_response_id, conversation, reasoning, a text format other than plain text, non-empty tools, a tool_choice other than none or auto, non-empty include, a truncation other than disabled, a non-zero top_logprobs, background: true, prompt, max_tool_calls, non-empty context_management, moderation, and non-empty metadata. Their OpenAI defaults are accepted, so an SDK that sends every field still works.

Notes for OpenAI SDK Users

  • Newton Fusion 1.0’s reasoning arrives in the answer. The text starts with a <think>...</think> block, empty when the model answered directly; remove it before showing the answer. reasoning is refused. To answer without reasoning, end the user text with /no_think: it works when the request includes an image or video, and on a text-only request the model reasons anyway. See Reasoning.
  • repetition_penalty is ignored here. It isn’t an OpenAI field; sent through the SDK (for example in extra_body), it’s accepted and has no effect. If the model repeats itself in long lists, send the request to /inference/query, which applies it.
  • Media go inline. Send images and video as data: URIs; uploaded files can’t be referenced.
  • A query stops after about 60 seconds and returns 504. Keep answers short with the token limit and the prompt; see Choosing an Endpoint.

Response

The model’s response object. The OpenAI SDKs expose the answer text as output_text.

Important Notes

  • Every error is listed in Errors on the Inference API overview.
  • Errors use the Archetype error envelope, not OpenAI’s. An OpenAI SDK raises them as API errors with the HTTP status.
  • 400 with model '<model>' refused this request means the model rejected the body, for example because it sets one of the unsupported options above.