Endpoint Details
Review how to make this request and handle its possible responses.
https://integrate.api.nvidia.com/v1/chat/completionsGiven a list of messages comprising a conversation, the model will return a response. Compatible with OpenAI. See https://platform.openai.com/docs/api-reference/chat/create
Request Body
Edit the request fields below.
Request details
Parameters15 Parameters
modeloptionalThe Build playground adds its staging prefix automatically. Standalone gateway requests use stg/nvidia/nemotron-3.5-bolt-e4b.
nvidia/nemotron-3.5-bolt-e4bmessagesrequiredConversation messages. System and developer instructions, user messages, assistant responses, and tool results are supported. Include tool_call_id on tool results.
[{"content":"I am going to Paris, what should I see?","role":"user"}]Minimum items: 1messages[].rolerequiredThe role of the message author.
developer · system · user · assistant · tool · functionmessages[].contentoptionalText or text content parts, or null for an assistant tool call.
messages[].nameoptionalmessages[].tool_call_idoptionalmessages[].tool_callsoptionalmessages[].reasoning_contentoptionalReasoning text returned separately from the final answer.
messages[].function_calloptionalLegacy assistant function call. Prefer tool_calls for new integrations.
temperatureoptionalThe sampling temperature to use for text generation. The higher the temperature value is, the less deterministic the output text will be. It is not recommended to modify both temperature and top_p in the same call.
1Minimum: 0Maximum: 2top_poptionalThe top-p sampling mass used for text generation. The top-p value determines the probability mass that is sampled at sampling time. For example, if top_p = 0.2, only the most likely tokens (summing to 0.2 cumulative probability) will be sampled. It is not recommended to modify both temperature and top_p in the same call.
0.95Maximum: 1Exclusive minimum: 0max_tokensoptionalThe maximum number of tokens to generate in any given call. Note that the model is not aware of this value, and generation will simply stop at the number of tokens specified. The hosted function caps completion budgets at 65536 tokens.
1024Minimum: 1Maximum: 65536seedoptionalIf specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.
42Example: 42streamoptionalIf set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events (SSE) as they become available (JSON responses are prefixed by `data: `), with the stream terminated by a `data: [DONE]` message.
truestopoptionalA string or a list of strings where the API will stop generating further tokens. The returned text will not contain the stop sequence.
toolsoptionalFunction definitions available for tool calling.
tool_choiceoptionalAutomatically select a tool, disable tools, require a tool, or select a named function.
parallel_tool_callsoptionalWhether multiple tool calls may be generated in one response.
trueresponse_formatoptionalUse json_schema with a JSON schema to constrain structured output.
stream_optionsoptionalInclude token usage in streamed chunks or emit continuous usage updates.
chat_template_kwargsoptionalOptional chat-template arguments. Set enable_thinking to true or false to control Bolt reasoning.
{"enable_thinking":true}skip_special_tokensoptionalSet to false for reasoning and tool parsing so the serving parser retains special-token boundaries.
Headers3 Headers
AuthorizationrequiredFormat: Bearer $NVIDIA_API_KEY
Content-TyperequiredAcceptoptional