API Reference

Create a chat completion

post
https://integrate.api.nvidia.com/v1/chat/completions

Supports text, up to eight images, function tools, and streaming. Video and audio inputs are unsupported. With stream=true, consume data-only SSE events until data: [DONE]; reasoning, content, and tool calls arrive as deltas.

Recent Requests
Log in to see full request history
TimeStatusUser Agent
Retrieving recent requests…
LoadingLoading…
Body Params
string
enum
required
Defaults to stepfun-ai/step-5-preview
Allowed:
messages
array of objects
required
length ≥ 1

Conversation history. Use content-part arrays for images. After an assistant tool call, include a tool message with its tool_call_id. Preserve assistant reasoning_content when continuing a conversation.

Messages*
string
enum
required
Allowed:
string | null | array
string | null

Assistant reasoning, separate from the final answer.

tool_calls
array of objects
Tool Calls
string

Required on tool-result messages; matches an assistant tool call ID.

string
integer
1 to 1048576
Defaults to 4096

Maximum generated tokens, including reasoning and the final answer. Small budgets may end during reasoning with null content and finish_reason=length. Prompt plus output must fit the context window.

boolean
Defaults to false
number
0 to 2
Defaults to 0.5
number
≤ 1
Defaults to 1
number
-2 to 2
Defaults to 0
number
-2 to 2
Defaults to 0
integer
0 to 9007199254740991

Optional sampling seed, limited to JavaScript-safe integers for the interactive examples. Deterministic output is not guaranteed.

string | array | null

Stop string or list of stop strings; omitted from the output.

tools
array of objects

Functions the model may request; the caller executes them.

Tools
string | object

Choose auto, none, required, or force a named function.

chat_template_kwargs
object

Reasoning remains enabled on this checkpoint. Do not set enable_thinking=false: it does not stop reasoning generation.

Headers
string
enum
Defaults to application/json

Generated from available response content types

Allowed:
Responses

400

Invalid request or unsupported input.

401

Missing or invalid NVIDIA API key.

402

Insufficient API credits.

422

Request validation failed.

429

Request rate limit exceeded.

Updated about 1 hour ago

Did this page help you?
Language
Credentials
Bearer
LoadingLoading…
Response
Click Try It! to start a request and see the response here! Or choose an example:
application/json
text/event-stream

Updated about 1 hour ago

Did this page help you?
country_code