POST /chat/completions

Live
Create a synchronous or streaming text completion.
Open in ChatGPT
(opens in new tab)Last verified: 2026-08-11

Endpoint

POST /chat/completions
Create a synchronous or streaming text completion. The base URL is https://api.modelrush.ai/v1.

Request

model, messages; optional stream, temperature, max_tokens, reasoning_effort, tools, tool_choice, parallel_tool_calls, response_format, stream_options, store=false, region. Send Authorization: Bearer $MODELRUSH_API_KEY for authenticated routes and Content-Type: application/json for JSON bodies.

Response

JSON completion or text/event-stream chunks with id, model, choices, usage, and optional tool_calls. Preserve returned request or generation identifiers. Generated outputs and their Provider file references are removed from the ModelRush database 24 hours after request completion; download anything you need to keep.

Errors

Invalid inputs return a 4xx response with a structured error. A 403 with adult_attestation_required, portrait_rights_attestation_required, or person_rights_confirmation_required must be resolved by the account user and must never be retried automatically. Retry 429 according to Retry-After; retry 5xx failures only with a bounded backoff policy.
PreviousAgent skills
NextPOST /images/generations