---
updatedAt: 2026-08-10T16:54:28.000Z
---
# Creates a model response for the given chat conversation.
Given 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
# OpenAPI definition
```json
{
"openapi": "3.1.0",
"info": {
"title": "NVIDIA NIM API for meta/muse-glimmer-30b",
"description": "The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/meta-muse-glimmer-30b for more details. Use of this trial service is governed by the NVIDIA API Trial Terms of Service and use of the model is governed by the NVIDIA Open Model Agreement. ADDITIONAL INFORMATION: The base model is governed by Apache License, Version 2.0.",
"version": "1.0.0",
"termsOfService": "https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf",
"contact": {
"name": "NVIDIA Enterprise Support",
"url": "https://www.nvidia.com/en-us/support/enterprise/"
},
"license": {
"name": "NVIDIA Open Model Agreement",
"url": "https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-agreement/"
}
},
"servers": [
{
"url": "https://integrate.api.nvidia.com/v1/"
}
],
"paths": {
"/chat/completions": {
"post": {
"operationId": "create_chat_completion_v1_chat_completions_post",
"tags": [
"Chat"
],
"summary": "Creates a model response for the given chat conversation.",
"description": "Given 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",
"requestBody": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ChatRequest"
}
}
},
"required": true
},
"responses": {
"200": {
"description": "Invocation is fulfilled",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ChatCompletion"
}
},
"text/event-stream": {
"schema": {
"$ref": "#/components/schemas/ChatCompletionChunk"
}
}
}
},
"202": {
"description": "Result is pending. Client should poll using the requestId.\n",
"content": {
"application/json": {
"example": {},
"schema": {}
}
},
"headers": {
"NVCF-REQID": {
"description": "requestId required for pooling",
"schema": {
"type": "string",
"format": "uuid"
}
},
"NVCF-STATUS": {
"description": "Invocation status",
"schema": {
"type": "string"
}
}
}
},
"422": {
"description": "Validation failed, provided entity could not be processed.",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/Errors"
},
"example": {
"type": "urn:nvcf-worker-service:problem-details:unprocessable-entity",
"title": "Unprocessable Entity",
"status": 422,
"detail": "string",
"instance": "/v2/nvcf/pexec/functions/4a58c6cb-a9b4-4014-99de-3e704d4ae687",
"requestId": "3fa85f64-5717-4562-b3fc-2c963f66afa6"
}
}
}
},
"500": {
"description": "The invocation ended with an error.",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/Errors"
},
"example": {
"type": "urn:nvcf-worker-service:problem-details:internal-server-error",
"title": "Internal Server Error",
"status": 500,
"detail": "string",
"instance": "/v2/nvcf/pexec/functions/4a58c6cb-a9b4-4014-99de-3e704d4ae687",
"requestId": "3fa85f64-5717-4562-b3fc-2c963f66afa6"
}
}
}
}
},
"x-nvai-meta": {
"name": "Create chat completion",
"returns": "Returns a [chat completion](/docs/api-reference/chat/object) object, or a streamed sequence of [chat completion chunk](/docs/api-reference/chat/streaming) objects if the request is streamed.\n",
"path": "create",
"examples": [
{
"name": "What is 17 * 23?",
"requestJson": "{\n \"model\": \"meta/muse-glimmer-30b\",\n \"temperature\": 0.95,\n \"top_p\": 1.0,\n \"max_tokens\": 2048,\n \"stream\": true,\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"What is 17 * 23?\"\n }\n ]\n}",
"responseJson": "{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"meta/muse-glimmer-30b\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"17 * 23 = 391.\",\n \"reasoning_content\": \"17 * 20 = 340, 17 * 3 = 51, 340 + 51 = 391.\"\n },\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}"
},
{
"name": "Describe an image",
"requestJson": "{\n \"model\": \"meta/muse-glimmer-30b\",\n \"temperature\": 0.95,\n \"top_p\": 1.0,\n \"max_tokens\": 2048,\n \"stream\": true,\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": [\n {\n \"type\": \"text\",\n \"text\": \"What is in this image?\"\n },\n {\n \"type\": \"image_url\",\n \"image_url\": {\n \"url\": \"https://assets.ngc.nvidia.com/products/api-catalog/phi-3-5-vision/example1b.jpg\"\n }\n }\n ]\n }\n ]\n}",
"responseJson": "{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"meta/muse-glimmer-30b\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"The image shows ...\",\n \"reasoning_content\": \"The photograph contains ...\"\n },\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}"
},
{
"name": "What is the weather in Santa Clara, CA?",
"requestJson": "{\n \"model\": \"meta/muse-glimmer-30b\",\n \"temperature\": 0.95,\n \"top_p\": 1.0,\n \"max_tokens\": 2048,\n \"stream\": false,\n \"tool_choice\": \"auto\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"What is the weather in Santa Clara, CA?\"\n }\n ],\n \"tools\": [\n {\n \"type\": \"function\",\n \"function\": {\n \"name\": \"get_current_weather\",\n \"description\": \"Get the current weather at a location.\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"location\": {\n \"type\": \"string\",\n \"description\": \"The city to get the weather for.\"\n },\n \"unit\": {\n \"type\": \"string\",\n \"enum\": [\n \"c\",\n \"f\"\n ],\n \"description\": \"Temperature unit.\"\n }\n },\n \"required\": [\n \"location\"\n ]\n }\n }\n }\n ]\n}",
"responseJson": "{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"meta/muse-glimmer-30b\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n \"id\": \"chatcmpl-tool-1\",\n \"type\": \"function\",\n \"function\": {\n \"name\": \"get_current_weather\",\n \"arguments\": \"{\\\"location\\\": \\\"Santa Clara, CA\\\"}\"\n }\n }\n ]\n },\n \"finish_reason\": \"tool_calls\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}"
}
],
"templates": [
{
"title": "Default",
"response": "{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"meta/muse-glimmer-30b\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"\\n\\nHello there, how may I assist you today?\"\n },\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}"
}
]
}
}
}
},
"security": [
{
"Token": []
}
],
"components": {
"securitySchemes": {
"Token": {
"type": "http",
"scheme": "bearer"
}
},
"schemas": {
"Errors": {
"properties": {
"type": {
"type": "string",
"description": "Error type"
},
"title": {
"type": "string",
"description": "Error title"
},
"status": {
"type": "integer",
"description": "Error status code"
},
"detail": {
"type": "string",
"description": "Detailed information about the error"
},
"instance": {
"type": "string",
"description": "Function instance used to invoke the request"
},
"requestId": {
"type": "string",
"format": "uuid",
"description": "UUID of the request"
}
},
"type": "object",
"required": [
"type",
"title",
"status",
"detail",
"instance",
"requestId"
],
"title": "InvokeError"
},
"ChatCompletion": {
"properties": {
"id": {
"description": "A unique identifier for the completion.",
"format": "uuid",
"title": "Id",
"type": "string"
},
"choices": {
"description": "The list of completion choices the model generated for the input prompt.",
"items": {
"$ref": "#/components/schemas/Choice"
},
"title": "Choices",
"type": "array"
},
"usage": {
"allOf": [
{
"$ref": "#/components/schemas/Usage"
}
],
"description": "Usage statistics for the completion request."
}
},
"required": [
"id",
"choices",
"usage"
],
"title": "ChatCompletion",
"type": "object"
},
"ChatCompletionChunk": {
"properties": {
"id": {
"description": "A unique identifier for the completion.",
"format": "uuid",
"title": "Id",
"type": "string"
},
"choices": {
"description": "The list of completion choices the model generated for the input prompt.",
"items": {
"$ref": "#/components/schemas/ChoiceChunk"
},
"title": "Choices",
"type": "array"
}
},
"required": [
"id",
"choices"
],
"title": "ChatCompletionChunk",
"type": "object"
},
"ChatRequest": {
"additionalProperties": false,
"properties": {
"model": {
"type": "string",
"title": "Model",
"default": "meta/muse-glimmer-30b"
},
"messages": {
"description": "A list of messages comprising the conversation so far. The roles of the messages must be alternating between `user` and `assistant`. The last input message should have role `user`. A message with the the `system` role is optional, and must be the very first message if it is present; `context` is also optional, but must come before a user question.",
"examples": [
[
{
"content": "I am going to Paris, what should I see?",
"role": "user"
}
]
],
"items": {
"$ref": "#/components/schemas/Message"
},
"title": "Messages",
"type": "array"
},
"temperature": {
"default": 0.95,
"description": "The sampling temperature to use for text generation. Muse Glimmer is a reasoning model and expects to be sampled rather than decoded greedily - the recommended pair is temperature 0.95 with top_p 1.0. Greedy decoding measurably degrades it.",
"maximum": 1,
"minimum": 0,
"title": "Temperature",
"type": "number"
},
"top_p": {
"default": 1,
"description": "The top-p sampling mass used for text generation. The top-p value determines the probability mass that is sampled at sampling time. For example, if top_p = 0.2, only the most likely tokens (summing to 0.2 cumulative probability) will be sampled. It is not recommended to modify both temperature and top_p in the same call.",
"maximum": 1,
"exclusiveMinimum": 0,
"title": "Top P",
"type": "number"
},
"tools": {
"anyOf": [
{
"items": {
"$ref": "#/components/schemas/ChatCompletionToolsParam"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Tools"
},
"max_tokens": {
"default": 2048,
"description": "The 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. Reasoning shares this budget, so leave headroom on reasoning-heavy prompts.",
"maximum": 131072,
"minimum": 1,
"title": "Max Tokens",
"type": "integer"
},
"seed": {
"anyOf": [
{
"maximum": 18446744073709552000,
"minimum": 0,
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"description": "If 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.",
"examples": [
42
],
"title": "Seed"
},
"stream": {
"default": false,
"description": "If 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.",
"title": "Stream",
"type": "boolean"
},
"tool_choice": {
"anyOf": [
{
"enum": [
"none",
"auto"
],
"type": "string"
},
{
"$ref": "#/components/schemas/ChatCompletionNamedToolChoiceParam"
},
{
"type": "null"
}
],
"default": "auto",
"title": "Tool Choice",
"description": "Controls which (if any) tool the model calls. `none` disables tool calling; `auto` lets the model choose."
},
"stop": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Stop",
"description": "A string or list of strings where the API stops generating further tokens. The returned text does not contain the stop sequence."
},
"frequency_penalty": {
"type": "number",
"maximum": 2,
"minimum": -2,
"default": 0,
"title": "Frequency Penalty",
"description": "Penalises new tokens by their existing frequency in the text so far, reducing verbatim repetition."
},
"presence_penalty": {
"type": "number",
"maximum": 2,
"minimum": -2,
"default": 0,
"title": "Presence Penalty",
"description": "Positive values penalise tokens that have already appeared, encouraging the model to move on to new topics."
},
"reasoning_effort": {
"enum": [
"none",
"minimal",
"low",
"medium",
"high",
"max"
],
"default": "high",
"type": "string",
"title": "Reasoning Effort",
"description": "How much reasoning the model should do before answering. Higher values generally produce a longer trace in `reasoning_content`, which shares the `max_tokens` budget with the answer."
},
"chat_template_kwargs": {
"type": "object",
"title": "Chat Template Kwargs",
"description": "Extra keyword arguments forwarded to the model's chat template, e.g. `{\"reasoning_strength\": \"low\"}`."
}
},
"required": [
"messages"
],
"title": "ChatRequest",
"type": "object"
},
"Choice": {
"properties": {
"index": {
"description": "The index of the choice in the list of choices (always 0).",
"title": "Index",
"type": "integer"
},
"message": {
"allOf": [
{
"$ref": "#/components/schemas/Message"
}
],
"description": "A chat completion message generated by the model.",
"examples": [
{
"content": "Ah, Paris, the City of Light! There are so many amazing things to see and do in this beautiful city ...",
"role": "assistant"
}
]
},
"finish_reason": {
"anyOf": [
{
"enum": [
"stop",
"length",
"tool_calls"
],
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached.",
"examples": [
"stop"
],
"title": "Finish Reason"
}
},
"required": [
"index",
"message"
],
"title": "Choice",
"type": "object"
},
"ChoiceChunk": {
"properties": {
"index": {
"description": "The index of the choice in the list of choices (always 0).",
"title": "Index",
"type": "integer"
},
"delta": {
"allOf": [
{
"$ref": "#/components/schemas/Message"
}
],
"description": "A chat completion delta generated by streamed model responses.",
"examples": [
{
"content": "Ah,",
"role": "assistant"
}
]
},
"finish_reason": {
"anyOf": [
{
"enum": [
"stop",
"length",
"tool_calls"
],
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached. Will be `null` if the model has not finished generating.",
"title": "Finish Reason"
}
},
"required": [
"index",
"delta"
],
"title": "ChoiceChunk",
"type": "object"
},
"Message": {
"additionalProperties": false,
"properties": {
"role": {
"description": "The role of the message author.",
"enum": [
"system",
"context",
"user",
"assistant",
"tool"
],
"title": "Role",
"type": "string"
},
"content": {
"description": "The contents of the message.\n
To pass media (only with role=`user`):\n
- Use content parts. Text is passed with `type`=`text`.\n
- Images are passed with `type`=`image_url`; set `image_url.url` to an image URL or a base64 data URI like `data:image/{format};base64,{base64encodedimage}`.\n
For `system` and `assistant` roles, the object list format is not supported.\n",
"title": "Content",
"anyOf": [
{
"type": "string"
},
{
"items": {
"anyOf": [
{
"$ref": "#/components/schemas/ContentPartImage"
},
{
"$ref": "#/components/schemas/ContentPartText"
}
]
},
"type": "array"
},
{
"type": "null"
}
]
},
"tool_call_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Tool Call Id",
"description": "The id of the tool call."
},
"tool_calls": {
"anyOf": [
{
"items": {
"$ref": "#/components/schemas/ToolCall"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Tool Calls",
"description": "The tool(s) called by the model."
},
"reasoning_content": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Reasoning Content",
"description": "The model's chain-of-thought, returned on its own channel rather than mixed into `content` (non-OpenAI extension). Streamed as `delta.reasoning_content`."
}
},
"required": [
"role"
],
"title": "Message",
"type": "object"
},
"ContentPartImage": {
"properties": {
"image_url": {
"$ref": "#/components/schemas/ImageURL"
},
"type": {
"type": "string",
"enum": [
"image_url"
],
"const": "image_url",
"title": "Type"
}
},
"type": "object",
"required": [
"image_url",
"type"
],
"title": "ContentPartImage"
},
"ContentPartText": {
"properties": {
"text": {
"type": "string",
"title": "Text"
},
"type": {
"type": "string",
"enum": [
"text"
],
"const": "text",
"title": "Type"
}
},
"type": "object",
"required": [
"text",
"type"
],
"title": "ContentPartText"
},
"ImageURL": {
"properties": {
"url": {
"type": "string",
"title": "Url"
}
},
"type": "object",
"required": [
"url"
],
"title": "ImageURL"
},
"ToolCall": {
"properties": {
"id": {
"type": "string",
"title": "Id"
},
"type": {
"type": "string",
"enum": [
"function"
],
"const": "function",
"title": "Type",
"default": "function"
},
"function": {
"$ref": "#/components/schemas/FunctionCall"
}
},
"additionalProperties": false,
"type": "object",
"required": [
"function"
],
"title": "ToolCall"
},
"FunctionCall": {
"properties": {
"name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Name"
},
"arguments": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Arguments"
}
},
"additionalProperties": false,
"type": "object",
"required": [
"name",
"arguments"
],
"title": "FunctionCall"
},
"ChatCompletionToolsParam": {
"properties": {
"type": {
"type": "string",
"enum": [
"function"
],
"const": "function",
"title": "Type",
"default": "function"
},
"function": {
"$ref": "#/components/schemas/FunctionDefinition"
}
},
"additionalProperties": false,
"type": "object",
"required": [
"function"
],
"title": "ChatCompletionToolsParam"
},
"ChatCompletionNamedFunction": {
"properties": {
"name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Name"
}
},
"additionalProperties": false,
"type": "object",
"required": [
"name"
],
"title": "ChatCompletionNamedFunction"
},
"ChatCompletionNamedToolChoiceParam": {
"properties": {
"function": {
"$ref": "#/components/schemas/ChatCompletionNamedFunction"
},
"type": {
"type": "string",
"enum": [
"function"
],
"const": "function",
"title": "Type",
"default": "function"
}
},
"additionalProperties": false,
"type": "object",
"required": [
"function"
],
"title": "ChatCompletionNamedToolChoiceParam"
},
"FunctionDefinition": {
"properties": {
"name": {
"type": "string",
"title": "Name"
},
"description": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Description"
},
"parameters": {
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"title": "Parameters"
}
},
"additionalProperties": false,
"type": "object",
"required": [
"name"
],
"title": "FunctionDefinition"
},
"Usage": {
"properties": {
"completion_tokens": {
"description": "Number of tokens in the generated completion.",
"examples": [
25
],
"title": "Completion Tokens",
"type": "integer"
},
"prompt_tokens": {
"description": "Number of tokens in the prompt.",
"examples": [
9
],
"title": "Prompt Tokens",
"type": "integer"
},
"total_tokens": {
"description": "Total number of tokens used in the request (prompt + completion).",
"examples": [
34
],
"title": "Total Tokens",
"type": "integer"
}
},
"required": [
"completion_tokens",
"prompt_tokens",
"total_tokens"
],
"title": "Usage",
"type": "object"
}
}
}
}
```