Create a chat completion (OpenAI compatible)

post

https://api.ainft.com/v1/chat/completions

Accepts a list of messages and returns a model-generated response. Supports both single-turn and multi-turn conversations. Authenticate via Bearer token. Responses can be streamed (SSE) or returned as a single JSON object.

Recent Requests

Time	Status	User Agent
Retrieving recent requests…

Loading…

Body Params

model

string

required

ID of the model to use (e.g. gpt-5.2).

messages

array of objects

required

List of messages in the conversation.

messages*

stream

boolean

If true, partial message deltas will be sent as server-sent events. Default false.

max_tokens

integer

Maximum number of tokens that can be generated in the completion.

temperature

number

Sampling temperature between 0 and 2. Higher = more random. Default 1.

top_p

number

Nucleus sampling: consider tokens with top_p probability mass. Default 1.

stop

Up to 4 sequences where the API will stop generating. String or array of strings.

integer

How many chat completion choices to generate. Default 1.

frequency_penalty

number

-2.0 to 2.0. Penalize repeated tokens. Default 0.

presence_penalty

number

-2.0 to 2.0. Penalize tokens that appear in the text so far. Default 0.

seed

integer

Random seed for deterministic sampling (if supported by model).

response_format

object

Specify output format: { "type": "text" } or { "type": "json_object" } or json_schema.

tools

array of objects

List of tools the model may call. Each has type "function" and function { name, description?, parameters? }.

tools

tool_choice

enum

user

string

Optional end-user identifier for abuse monitoring.

web_search_options

object

Optional. Enables web search for models that support it (OpenAI Chat Completions). When present, this gateway treats the request as web-search-enabled; model allowlists may apply. Field names align with OpenAI web_search_options.

Headers

string

enum

Defaults to application/json

Generated from available response content types

Allowed:

Responses

200Success. Schema differs by stream mode.

400Bad Request - invalid parameters, malformed body, or invalid request

401Unauthorized - invalid or missing authentication

403Forbidden - access denied, insufficient quota, or model access restricted

429Too Many Requests - rate limit exceeded

500Internal Server Error

502Bad Gateway - upstream service error

503Service Unavailable - overloaded or no available channel