Skip to main content
POST
Python

Authorizations

Authorization
string
header
required

API key provided as a Bearer token: Authorization: Bearer <api_key>. Get an API key at https://platform.inceptionlabs.ai.

Body

application/json
messages
Message · object[]
required
model
string
required

The model to use for the chat completion.

max_tokens
integer
default:16384

Maximum number of tokens to generate.

Required range: 1 <= x <= 50000
temperature
number
default:0.75

What sampling temperature to use, between 0.5 and 1. Higher values make the output more random; lower values make it more focused and deterministic. Values outside this range are reset to 0.75 and a warning is returned in the response.

Required range: 0.5 <= x <= 1
stop
string[]

A list of sequences where the API will stop generating further tokens. The returned text will not contain the stop sequences.

tools
ChatCompletionTool · object[]

A list of tools the model may call. Use this to provide functions the model can generate JSON arguments for.

tool_choice
enum<string>

Controls tool selection: 'auto' (model decides, default when tools present), 'required' (model must call one), or 'none' (model must not call one).

Available options:
auto,
required,
none
stream
boolean
default:false

Whether to stream the response.

stream_options
StreamOptions · object

Options that control streaming behavior.

diffusing
boolean
default:false

Whether to show the diffusion effect in the streamed response.

extra_body
Extra Body · object

Extra parameters passed to the model (OpenAI-compat passthrough).

realtime
boolean
default:false

Enable flag for more realtime workloads that require lower TTFT/TTFAT.

response_format
ResponseFormatText · object

An object specifying the format that the model must output.

reasoning_summary
boolean
default:false

Request a summary of the model's reasoning process.

reasoning_summary_wait
boolean
default:false

Wait for all reasoning summaries to complete before finishing the response.

reasoning_effort
enum<string>
default:medium

Constrains the effort spent on reasoning before the model responds.

Available options:
instant,
low,
medium,
high

Response

Successful response. Returns a JSON object when stream=false, or a server-sent events stream of ChatCompletionChunk objects (terminated by data: [DONE]) when stream=true.

id
string
required
object
string
default:chat.completion
required
Allowed value: "chat.completion"
created
integer
required
model
string
required
choices
Choice · object[]
required
usage
Usage · object
required
warning
string | null
reasoning_summary
ReasoningSummary · object | null

Summary of reasoning process if requested and available.