471:["$","$L473",null,{"data":[{"endpoint":{"artifact":{"name":"llama-4-maverick-17b-128e-instruct","displayName":"llama-4-maverick-17b-128e-instruct","publisher":"meta","shortDescription":"A general purpose multimodal, multilingual 128 MoE model with 17B parameters.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/llama-4-maverick-17b-128e-instruct.jpg","labels":["language generation","Image-to-Text","vision assistant","visual question answering"],"attributes":[{"key":"AVAILABLE","value":"false"},{"key":"PREVIEW","value":"true"}],"artifactType":"ENDPOINT","canGuestDownload":true,"createdDate":"2025-04-06T00:54:19.024Z","description":"$4a3","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","updatedDate":"2025-04-08T17:27:13.164Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"5cdb786f-fb3c-4b95-9aa6-4c8cdac0aa2f"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for meta/llama-4-maverick-17b-128e-instruct","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/meta-llama-4-maverick-17b-128e-instruct for more details.","version":"1.0.0","termsOfService":"https://nvidia.com/legal/terms-of-use","contact":{"name":"NVIDIA Support","url":"https://help.nvidia.com/"},"license":{"name":"Llama 4 License","url":"https://github.com/meta-llama/llama-models/blob/main/models/llama4/LICENSE"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1"}],"tags":[{"name":"Multimodal API","description":"This API performs inference using visual language understanding models"}],"paths":{"/meta/llama-4-maverick-17b-128e-instruct":{"post":{"tags":["Multimodal API"],"summary":"Request response from the model","description":"Invokes inference using the model chat parameters. If uploading large images, this POST should be used in conjunction with the NVCF API which allows for the upload of large assets. \nYou can find details on how to use NVCF Asset APIs here: https://docs.api.nvidia.com/cloud-functions/reference/createasset","operationId":"invokeFunction","parameters":[{"in":"header","name":"NVCF-INPUT-ASSET-REFERENCES","schema":{"type":"string","maxLength":370,"format":"uuid"},"required":false,"description":"String of asset IDs separated by commas. Data is uploaded to AWS S3 using NVCF Asset APIs and associated with these asset IDs.If the size of an image is more than 180KB, it needs to be uploaded to a presigned S3 URL bucket. The presigned URL allows for secure and temporary access to the S3 bucket for uploading the image. Once the asset is requested, an asset ID is generated for it. Please include this asset ID in this header and to use the uploaded image in a prompt, you need to refer to it using the following format: `

`."}],"requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/NIMLLMChatCompletionRequest"}}},"required":true},"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionResponse"}},"text/event-stream":{"schema":{"$ref":"#/components/schemas/ChatCompletionStreamResponse"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid","maxLength":36}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string","format":"^[a-zA-Z-]{1,64}$","maxLength":64}}}},"422":{"description":"Validation failed, provided entity could not be processed.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","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":"dog.jpeg","input":{"text":"Is there a car in this image?","images":["https://assets.ngc.nvidia.com/products/api-catalog/phi-3-5-vision/example1a.jpg"]},"output":{"text":"The image shows a small, light brown, curly-haired dog standing on a red cushion with a grey and white pillow. The dog is on a wooden deck with a white fence and greenery in the background."}},{"name":"dogs.jpeg","input":{"text":"Describe this image","images":["https://assets.ngc.nvidia.com/products/api-catalog/phi-3-5-vision/example1b.jpg"]}}],"templates":[{"title":"Default","requestEjs":{"python":"$4a4","node.js":"$4a5","curl":"stream=<%- request.stream %>\n\nif [ \"$stream\" = true ]; then\n accept_header='Accept: text/event-stream'\nelse\n accept_header='Accept: application/json'\nfi\n<% content = \"What is in this image?

\" %>\nimage_b64=$( base64 image.png )\n\necho '{\n \"model\": \"<%- request.model %>\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"<%- content %>\"\n }\n ],\n \"max_tokens\": <%- request.max_tokens %>,\n \"temperature\": <%- request.temperature.toFixed(2) %>,\n \"top_p\": <%- request.top_p.toFixed(2) %>,\n \"stream\": <%- request.stream %>\n}' > payload.json\n\ncurl https://integrate.api.nvidia.com/v1/chat/completions \\\n -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -H \"$accept_header\" \\\n -d @payload.json\n"},"response":"{\n \"choices\": [{\n \"index\": 0,\n \"model\": \"meta/llama-4-maverick-17b-128e-instruct\",\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"...\",\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}},"/status/{requestId}":{"get":{"tags":["Multimodal API"],"summary":"Gets the result of an earlier function invocation request that returned a status of 202.","operationId":"getFunctionInvocationResult","parameters":[{"name":"requestId","in":"path","description":"requestId to poll results","required":true,"schema":{"type":"string","format":"uuid","maxLength":36}}],"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionResponse"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid","maxLength":36}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string","format":"^[a-zA-Z-]{1,64}$","maxLength":64}}}},"422":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"ChatCompletionResponse":{"properties":{"id":{"type":"string","title":"Id"},"object":{"type":"string","enum":["chat.completion"],"const":"chat.completion","title":"Object","default":"chat.completion"},"created":{"type":"integer","title":"Created"},"model":{"type":"string","title":"Model"},"choices":{"items":{"$ref":"#/components/schemas/ChatCompletionResponseChoice"},"type":"array","title":"Choices"},"usage":{"$ref":"#/components/schemas/UsageInfo"}},"additionalProperties":false,"type":"object","required":["model","choices","usage"],"title":"ChatCompletionResponse"},"ChatCompletionResponseChoice":{"properties":{"index":{"type":"integer","title":"Index"},"message":{"$ref":"#/components/schemas/ChatMessage"},"finish_reason":{"anyOf":[{"type":"string","enum":["stop","length"]},{"type":"null"}],"title":"Finish Reason"},"stop_reason":{"anyOf":[{"type":"integer"},{"type":"string"},{"type":"null"}],"title":"Stop Reason"}},"additionalProperties":false,"type":"object","required":["index","message"],"title":"ChatCompletionResponseChoice"},"ChatCompletionResponseStreamChoice":{"properties":{"index":{"type":"integer","title":"Index"},"delta":{"$ref":"#/components/schemas/DeltaMessage"},"finish_reason":{"anyOf":[{"type":"string","enum":["stop","length"]},{"type":"null"}],"title":"Finish Reason"},"stop_reason":{"anyOf":[{"type":"integer"},{"type":"string"},{"type":"null"}],"title":"Stop Reason"}},"additionalProperties":false,"type":"object","required":["index","delta"],"title":"ChatCompletionResponseStreamChoice"},"ChatCompletionStreamResponse":{"properties":{"id":{"type":"string","title":"Id"},"object":{"type":"string","enum":["chat.completion.chunk"],"const":"chat.completion.chunk","title":"Object","default":"chat.completion.chunk"},"created":{"type":"integer","title":"Created"},"model":{"type":"string","title":"Model"},"choices":{"items":{"$ref":"#/components/schemas/ChatCompletionResponseStreamChoice"},"type":"array","title":"Choices"},"usage":{"anyOf":[{"$ref":"#/components/schemas/UsageInfo"},{"type":"null"}]}},"additionalProperties":false,"type":"object","required":["model","choices"],"title":"ChatCompletionStreamResponse"},"ChatMessage":{"properties":{"role":{"type":"string","title":"Role"},"content":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Content"}},"additionalProperties":false,"type":"object","required":["role"],"title":"ChatMessage"},"DeltaMessage":{"properties":{"role":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Role"},"content":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Content"}},"additionalProperties":false,"type":"object","title":"DeltaMessage"},"ErrorResponse":{"properties":{"object":{"type":"string","title":"Object","default":"error"},"message":{"type":"string","title":"Message"},"type":{"type":"string","title":"Type"},"param":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Param"},"code":{"type":"integer","title":"Code"}},"additionalProperties":false,"type":"object","required":["message","type","code"],"title":"ErrorResponse"},"HTTPValidationError":{"properties":{"detail":{"items":{"$ref":"#/components/schemas/ValidationError"},"type":"array","title":"Detail"}},"type":"object","title":"HTTPValidationError"},"ImageURL":{"properties":{"url":{"type":"string","title":"Url"}},"type":"object","required":["url"],"title":"ImageURL"},"NIMLLMChatCompletionMessage":{"properties":{"role":{"allOf":[{"$ref":"#/components/schemas/Role"}],"description":"The role of the message's author."},"content":{"anyOf":[{"type":"string"},{"items":{"anyOf":[{"$ref":"#/components/schemas/NIMVLMChatCompletionContentPartImage"},{"$ref":"#/components/schemas/NIMVLMChatCompletionContentPartText"}]},"type":"array"}],"title":"Content","description":"The contents of the message.\n
To pass images (only with role=`user`):\n
- When content is a string, image can be passed together with the text with `img` HTML tags that wraps \n an image URL (`

`), \n base64 encoded image data (`

`), \n or an NVCF asset ID (`

`."}],"requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/NIMLLMChatCompletionRequest"}}},"required":true},"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionResponse"}},"text/event-stream":{"schema":{"$ref":"#/components/schemas/ChatCompletionStreamResponse"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid","maxLength":36}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string","format":"^[a-zA-Z-]{1,64}$","maxLength":64}}}},"422":{"description":"Validation failed, provided entity could not be processed.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","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":"dog.jpeg","input":{"text":"Is there a car in this image?","images":["https://assets.ngc.nvidia.com/products/api-catalog/phi-3-5-vision/example1a.jpg"]},"output":{"text":"The image shows a small, light brown, curly-haired dog standing on a red cushion with a grey and white pillow. The dog is on a wooden deck with a white fence and greenery in the background."}},{"name":"dogs.jpeg","input":{"text":"Describe this image","images":["https://assets.ngc.nvidia.com/products/api-catalog/phi-3-5-vision/example1b.jpg"]}}],"templates":[{"title":"Default","requestEjs":{"python":"$4a7","node.js":"$4a8","curl":"stream=<%- request.stream %>\n\nif [ \"$stream\" = true ]; then\n accept_header='Accept: text/event-stream'\nelse\n accept_header='Accept: application/json'\nfi\n<% content = \"What is in this image?

\" %>\nimage_b64=$( base64 image.png )\n\necho '{\n \"model\": \"<%- request.model %>\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"<%- content %>\"\n }\n ],\n \"max_tokens\": <%- request.max_tokens %>,\n \"temperature\": <%- request.temperature.toFixed(2) %>,\n \"top_p\": <%- request.top_p.toFixed(2) %>,\n \"stream\": <%- request.stream %>\n}' > payload.json\n\ncurl https://integrate.api.nvidia.com/v1/chat/completions \\\n -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -H \"$accept_header\" \\\n -d @payload.json\n"},"response":"{\n \"choices\": [{\n \"index\": 0,\n \"model\": \"meta/llama-4-scout-17b-16e-instruct\",\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"...\",\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}},"/status/{requestId}":{"get":{"tags":["Multimodal API"],"summary":"Gets the result of an earlier function invocation request that returned a status of 202.","operationId":"getFunctionInvocationResult","parameters":[{"name":"requestId","in":"path","description":"requestId to poll results","required":true,"schema":{"type":"string","format":"uuid","maxLength":36}}],"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionResponse"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid","maxLength":36}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string","format":"^[a-zA-Z-]{1,64}$","maxLength":64}}}},"422":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"ChatCompletionResponse":{"properties":{"id":{"type":"string","title":"Id"},"object":{"type":"string","enum":["chat.completion"],"const":"chat.completion","title":"Object","default":"chat.completion"},"created":{"type":"integer","title":"Created"},"model":{"type":"string","title":"Model"},"choices":{"items":{"$ref":"#/components/schemas/ChatCompletionResponseChoice"},"type":"array","title":"Choices"},"usage":{"$ref":"#/components/schemas/UsageInfo"}},"additionalProperties":false,"type":"object","required":["model","choices","usage"],"title":"ChatCompletionResponse"},"ChatCompletionResponseChoice":{"properties":{"index":{"type":"integer","title":"Index"},"message":{"$ref":"#/components/schemas/ChatMessage"},"finish_reason":{"anyOf":[{"type":"string","enum":["stop","length"]},{"type":"null"}],"title":"Finish Reason"},"stop_reason":{"anyOf":[{"type":"integer"},{"type":"string"},{"type":"null"}],"title":"Stop Reason"}},"additionalProperties":false,"type":"object","required":["index","message"],"title":"ChatCompletionResponseChoice"},"ChatCompletionResponseStreamChoice":{"properties":{"index":{"type":"integer","title":"Index"},"delta":{"$ref":"#/components/schemas/DeltaMessage"},"finish_reason":{"anyOf":[{"type":"string","enum":["stop","length"]},{"type":"null"}],"title":"Finish Reason"},"stop_reason":{"anyOf":[{"type":"integer"},{"type":"string"},{"type":"null"}],"title":"Stop Reason"}},"additionalProperties":false,"type":"object","required":["index","delta"],"title":"ChatCompletionResponseStreamChoice"},"ChatCompletionStreamResponse":{"properties":{"id":{"type":"string","title":"Id"},"object":{"type":"string","enum":["chat.completion.chunk"],"const":"chat.completion.chunk","title":"Object","default":"chat.completion.chunk"},"created":{"type":"integer","title":"Created"},"model":{"type":"string","title":"Model"},"choices":{"items":{"$ref":"#/components/schemas/ChatCompletionResponseStreamChoice"},"type":"array","title":"Choices"},"usage":{"anyOf":[{"$ref":"#/components/schemas/UsageInfo"},{"type":"null"}]}},"additionalProperties":false,"type":"object","required":["model","choices"],"title":"ChatCompletionStreamResponse"},"ChatMessage":{"properties":{"role":{"type":"string","title":"Role"},"content":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Content"}},"additionalProperties":false,"type":"object","required":["role"],"title":"ChatMessage"},"DeltaMessage":{"properties":{"role":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Role"},"content":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Content"}},"additionalProperties":false,"type":"object","title":"DeltaMessage"},"ErrorResponse":{"properties":{"object":{"type":"string","title":"Object","default":"error"},"message":{"type":"string","title":"Message"},"type":{"type":"string","title":"Type"},"param":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Param"},"code":{"type":"integer","title":"Code"}},"additionalProperties":false,"type":"object","required":["message","type","code"],"title":"ErrorResponse"},"HTTPValidationError":{"properties":{"detail":{"items":{"$ref":"#/components/schemas/ValidationError"},"type":"array","title":"Detail"}},"type":"object","title":"HTTPValidationError"},"ImageURL":{"properties":{"url":{"type":"string","title":"Url"}},"type":"object","required":["url"],"title":"ImageURL"},"NIMLLMChatCompletionMessage":{"properties":{"role":{"allOf":[{"$ref":"#/components/schemas/Role"}],"description":"The role of the message's author."},"content":{"anyOf":[{"type":"string"},{"items":{"anyOf":[{"$ref":"#/components/schemas/NIMVLMChatCompletionContentPartImage"},{"$ref":"#/components/schemas/NIMVLMChatCompletionContentPartText"}]},"type":"array"}],"title":"Content","description":"The contents of the message.\n
To pass images (only with role=`user`):\n
- When content is a string, image can be passed together with the text with `img` HTML tags that wraps \n an image URL (`

`), \n base64 encoded image data (`

`), \n or an NVCF asset ID (`

`) \n when the container is hosted in NVCF and the payload exceeds 200KB.\n
- When content is a list of objects, images can be passed as objects with type=`image_url`.\n
- In both cases, images can be PNG, JPG or JPEG.\n
For `system` and `assistant` roles, the object list format is not supported.\n "}},"type":"object","required":["role","content"],"title":"NIMLLMChatCompletionMessage"},"NIMLLMChatCompletionRequest":{"properties":{"messages":{"items":{"$ref":"#/components/schemas/NIMLLMChatCompletionMessage"},"type":"array","minItems":1,"title":"Messages","description":"A list of messages comprising the conversation so far."},"model":{"type":"string","title":"Model","description":"The model to use.","default":"meta/llama-4-scout-17b-16e-instruct"},"frequency_penalty":{"anyOf":[{"type":"number","maximum":2,"minimum":-2},{"type":"null"}],"title":"Frequency Penalty","description":"Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.","default":0},"max_tokens":{"anyOf":[{"type":"integer","maximum":8192,"minimum":1},{"type":"null"}],"title":"Max Tokens","description":"The maximum number of tokens that can be generated.","default":512},"presence_penalty":{"anyOf":[{"type":"number","maximum":2,"minimum":-2},{"type":"null"}],"title":"Presence Penalty","description":"Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.","default":0},"seed":{"anyOf":[{"type":"integer","maximum":9223372036854776000,"minimum":-9223372036854776000},{"type":"null"}],"title":"Seed","description":"Changing the seed will produce a different response with similar characteristics. Fixing the seed will reproduce the same results if all other parameters are also kept constant."},"stop":{"anyOf":[{"type":"string"},{"items":{"type":"string"},"type":"array"},{"type":"null"}],"title":"Stop","description":"Sequences where the API will stop generating further tokens."},"stream":{"anyOf":[{"type":"boolean"},{"type":"null"}],"title":"Stream","description":"If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a `data: [DONE]`","default":false},"temperature":{"anyOf":[{"type":"number","maximum":2,"minimum":0},{"type":"null"}],"title":"Temperature","description":"What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.","default":1},"top_p":{"anyOf":[{"type":"number","maximum":1,"exclusiveMinimum":0},{"type":"null"}],"title":"Top P","description":"An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both.","default":1}},"additionalProperties":false,"type":"object","required":["messages","model"],"title":"NIMLLMChatCompletionRequest"},"NIMVLMChatCompletionContentPartImage":{"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":"NIMVLMChatCompletionContentPartImage"},"NIMVLMChatCompletionContentPartText":{"properties":{"text":{"type":"string","title":"Text"},"type":{"type":"string","enum":["text"],"const":"text","title":"Type"}},"type":"object","required":["text","type"],"title":"NIMVLMChatCompletionContentPartText"},"Role":{"type":"string","enum":["assistant","user"],"title":"Role"},"UsageInfo":{"properties":{"prompt_tokens":{"type":"integer","title":"Prompt Tokens","default":0},"total_tokens":{"type":"integer","title":"Total Tokens","default":0},"completion_tokens":{"anyOf":[{"type":"integer"},{"type":"null"}],"title":"Completion Tokens","default":0}},"additionalProperties":false,"type":"object","title":"UsageInfo"},"ValidationError":{"properties":{"loc":{"items":{"anyOf":[{"type":"string"},{"type":"integer"}]},"type":"array","title":"Location"},"msg":{"type":"string","title":"Message"},"type":{"type":"string","title":"Error Type"}},"type":"object","required":["loc","msg","type"],"title":"ValidationError"}}}},"namespace":"qc69jvmznzxy","updatedDate":"2025-04-06T05:31:52.620Z","nvcfFunctionId":"b6bb6e01-780e-4ba0-a5b8-379f00ed9b1c","createdDate":"2025-04-05T21:45:09.055Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/meta-llama-4-scout-17b-16e-instruct","termsOfUse":"GOVERNING TERMS: This trial service is governed by the NVIDIA API Trial Terms of Service; and the use of this model is governed by the NVIDIA Community Model License . ADDITIONAL INFORMATION Llama 4 Community Model License .\n","showUnavailableBanner":false,"playground":{"type":"chatWithImages","options":{"image":{"singleTurn":false,"limit":5}}}},"artifactName":"llama-4-scout-17b-16e-instruct"},"config":{"name":"llama-4-scout-17b-16e-instruct","type":"model"}},{"endpoint":{"artifact":{"name":"llama-3_1-nemotron-ultra-253b-v1","displayName":"llama-3.1-nemotron-ultra-253b-v1","publisher":"nvidia","shortDescription":"Superior inference efficiency with highest accuracy for scientific and complex math reasoning, coding, tool calling, and instruction following.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/llama-3_1-nemotron-ultra-253b-v1.jpg","labels":["advanced reasoning","function calling","instruction following","math"],"attributes":[{"key":"AVAILABLE","value":"false"},{"key":"PREVIEW","value":"true"}],"artifactType":"ENDPOINT","bias":"| Field: | Response: |\n| :----------------------------------------------------------------------------------------------------------: | :-------: |\n| Participation considerations from adversely impacted groups (protected classes) in model design and testing: | None |\n| Measures taken to mitigate against unwanted bias: | None |","canGuestDownload":true,"createdDate":"2025-04-08T21:40:13.191Z","description":"$4a9","explainability":"$4aa","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","privacy":"$4ab","safetyAndSecurity":"$4ac","updatedDate":"2025-04-17T22:03:39.317Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"dd970a6b-b4e4-47ce-82f7-19aacddbebfc"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for nvidia/llama-3.1-nemotron-ultra-253b-v1","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/nvidia-llama-3_1-nemotron-ultra-253b-v1 for more details.","version":"1.0.0","termsOfService":"https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/","contact":{"name":"NVIDIA Enterprise Support","url":"https://www.nvidia.com/en-us/support/enterprise/"},"license":{"name":"Llama 3.1 License","url":"https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1/"}],"paths":{"/chat/completions":{"post":{"operationId":"create_chat_completion_v1_chat_completions_post","tags":["Chat"],"summary":"Creates a model response for the given chat conversation.","description":"Given a list of messages comprising a conversation, the model will return a response. Compatible with OpenAI. See https://platform.openai.com/docs/api-reference/chat/create","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionRequest"}}},"required":true},"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionResponse"}}}},"402":{"description":"Payment Required","content":{"application/json":{"schema":{"$ref":"#/components/schemas/PaymentRequiredError"}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}},"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":"Write a limerick about the wonders of GPU computing.","requestJson":"{\n \"model\": \"nvidia/llama-3.1-nemotron-ultra-253b-v1\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a helpful assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"Write a limerick about the wonders of GPU computing.\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 16384,\n \"seed\": 42,\n \"stop\": null,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"nvidia/llama-3.1-nemotron-ultra-253b-v1\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Here's a short poem on...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"},{"name":"What can I see at NVIDIA's GPU Technology Conference?","requestJson":"{\n \"model\": \"nvidia/llama-3.1-nemotron-ultra-253b-v1\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a helpful assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"What can I see at NVIDIA's GPU Technology Conference?\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 16384,\n \"seed\": 42,\n \"stop\": null,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"nvidia/llama-3.1-nemotron-ultra-253b-v1\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"At NVIDIA's GTC conference...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}],"templates":[{"title":"No Streaming","requestEjs":{"python":"from openai import OpenAI\n\nclient = OpenAI(\n base_url = \"https://integrate.api.nvidia.com/v1\",\n api_key = \"$NVIDIA_API_KEY\"\n)\n\ncompletion = client.chat.completions.create(\n model=\"<%- request.model %>\",\n messages=<%- JSON.stringify(request.messages) %>,\n temperature=<%- request.temperature %>,\n top_p=<%- request.top_p %>,\n max_tokens=<%- request.max_tokens %>,\n frequency_penalty=<%- request.frequency_penalty %>,\n presence_penalty=<%- request.presence_penalty %>,\n stream=<%- request.stream?.toString()[0].toUpperCase() + request.stream?.toString().slice(1) %>\n)\n<% if (request.stream) { %>\nfor chunk in completion:\n if chunk.choices[0].delta.content is not None:\n print(chunk.choices[0].delta.content, end=\"\")\n<% } else { %>\nprint(completion.choices[0].message)\n<% } %>\n","node.js":"import OpenAI from 'openai';\n\nconst openai = new OpenAI({\n apiKey: '$NVIDIA_API_KEY',\n baseURL: 'https://integrate.api.nvidia.com/v1',\n})\n\nasync function main() {\n const completion = await openai.chat.completions.create({\n model: \"<%- request.model %>\",\n messages: <%- JSON.stringify(request.messages) %>,\n temperature: <%- request.temperature %>,\n top_p: <%- request.top_p %>,\n max_tokens: <%- request.max_tokens %>,\n frequency_penalty: <%- request.frequency_penalty %>,\n presence_penalty: <%- request.presence_penalty %>,\n stream: <%- request.stream %>,\n })\n <% if (request.stream) { %>\n for await (const chunk of completion) {\n process.stdout.write(chunk.choices[0]?.delta?.content || '')\n }\n <% } else { %>\n process.stdout.write(completion.choices[0]?.message?.content);\n <% } %>\n}\n\nmain();","curl":"curl https://integrate.api.nvidia.com/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n -d '{\n \"model\": \"nvidia/llama-3.1-nemotron-ultra-253b-v1\",\n \"messages\": <%- JSON.stringify(request.messages).replaceAll(\"'\", \"'\\\"'\\\"'\") %>,\n \"temperature\": <%- request.temperature %>, \n \"top_p\": <%- request.top_p %>,\n \"max_tokens\": <%- request.max_tokens %>,\n \"frequency_penalty\": <%- request.frequency_penalty %>,\n \"presence_penalty\": <%- request.presence_penalty %>,\n \"stream\": <%- request.stream %> \n }'\n"},"response":"{\n \"id\": \"chatcmpl-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"nvidia/llama-3.1-nemotron-ultra-253b-v1\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\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 \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"ChatCompletionRequest":{"properties":{"model":{"type":"string","title":"Model","default":"nvidia/llama-3.1-nemotron-ultra-253b-v1"},"max_tokens":{"type":"integer","minimum":1,"title":"Max Tokens","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.","default":4096,"maximum":16384},"stream":{"type":"boolean","title":"Stream","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.","default":false},"temperature":{"type":"number","maximum":1,"minimum":0,"title":"Temperature","description":"The 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.","default":0.6},"top_p":{"type":"number","maximum":1,"exclusiveMinimum":0,"title":"Top P","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.","default":0.95},"stop":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"string"},{"type":"null"}],"title":"Stop","description":"A string or a list of strings where the API will stop generating further tokens. The returned text will not contain the stop sequence.","examples":[null]},"frequency_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Frequency Penalty","description":"Indicates how much to penalize new tokens based on their existing frequency in the text so far, decreasing model likelihood to repeat the same line verbatim."},"presence_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Presence Penalty","description":"Positive values penalize new tokens based on whether they appear in the text so far, increasing model likelihood to talk about new topics."},"seed":{"type":"integer","maximum":18446744073709552000,"minimum":0,"title":"Seed","description":"The model generates random results. Changing the input seed alone will produce a different response with similar characteristics. It is possible to reproduce results by fixing the input seed (assuming all other hyperparameters are also fixed).","default":0},"messages":{"anyOf":[{"items":{"additionalProperties":{"type":"string"},"type":"object"},"type":"array"}],"title":"Messages","description":"A list of messages comprising the conversation so far.","examples":[[{"role":"user","content":"Write a limerick about the wonders of GPU computing."}]]}},"additionalProperties":false,"type":"object","required":["messages"],"title":"ChatCompletionRequest","description":"OpenAI ChatCompletionRequest"},"ChatCompletionResponse":{"properties":{"id":{"type":"string","title":"Id","description":"A unique identifier for the completion."},"object":{"type":"string","title":"Object","default":"chat.completion"},"created":{"type":"integer","title":"Created"},"model":{"type":"string","title":"Model","example":"nvidia/llama-3.1-nemotron-ultra-253b-v1"},"choices":{"items":{"$ref":"#/components/schemas/ChatCompletionResponseChoice"},"type":"array","title":"Choices","description":"The list of completion choices the model generated for the input prompt."},"usage":{"$ref":"#/components/schemas/UsageInfo","description":"Usage statistics for the completion request."}},"type":"object","required":["model","choices","usage"],"title":"ChatCompletionResponse"},"ChatCompletionResponseChoice":{"properties":{"index":{"type":"integer","title":"Index","description":"The index of the choice in the list of choices (always 0)."},"message":{"$ref":"#/components/schemas/ChatMessage","description":"A chat completion message generated by the model."},"finish_reason":{"anyOf":[{"type":"string","enum":["stop","length"]},{"type":"null"}],"title":"Finish Reason","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"}},"type":"object","required":["index","message"],"title":"ChatCompletionResponseChoice"},"ChatMessage":{"properties":{"role":{"type":"string","title":"Role","description":"The role of the message author."},"content":{"type":"string","title":"Content","description":"The contents of the message."}},"type":"object","required":["role","content"],"title":"ChatMessage"},"HTTPValidationError":{"properties":{"detail":{"items":{"$ref":"#/components/schemas/ValidationError"},"type":"array","title":"Detail","description":"Detailed information about the error."}},"type":"object","title":"HTTPValidationError"},"PaymentRequiredError":{"properties":{"detail":{"type":"string","description":"Contains specific information related to the error and why it occurred.","example":"You have reached your limit of credits."}},"type":"object","title":"PaymentRequiredError"},"UsageInfo":{"properties":{"prompt_tokens":{"type":"integer","title":"Prompt Tokens","description":"Number of tokens in the prompt.","default":0},"total_tokens":{"type":"integer","title":"Total Tokens","description":"Total number of tokens used in the request (prompt + completion).","default":0},"completion_tokens":{"anyOf":[{"type":"integer"},{"type":"null"}],"title":"Completion Tokens","description":"Number of tokens in the generated completion.","default":0}},"type":"object","title":"UsageInfo"},"ValidationError":{"properties":{"loc":{"items":{"anyOf":[{"type":"string"},{"type":"integer"}]},"type":"array","title":"Location"},"msg":{"type":"string","title":"Message","description":"The error message."},"type":{"type":"string","title":"Error Type","description":"Error type"}},"type":"object","required":["loc","msg","type"],"title":"ValidationError"}}}},"namespace":"qc69jvmznzxy","updatedDate":"2025-04-17T22:03:39.735Z","nvcfFunctionId":"84bf12ff-edbd-4435-baea-0fa6a7453d2e","createdDate":"2025-04-08T21:40:13.453Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/nvidia-llama-3_1-nemotron-ultra-253b-v1","termsOfUse":"GOVERNING TERMS: This trial service is governed by the NVIDIA API Trial Terms of Service. Use of this model is governed by the AI Foundation Models Community License Agreement . ADDITIONAL INFORMATION: Llama 3.1 Community License Agreement , Built with Llama.\n","showUnavailableBanner":false,"playground":{"type":"chatWithThinking","options":{"chat":{"reasoning":{"defaultEnabled":true,"systemPromptEnabled":"detailed thinking on","systemPromptDisabled":"detailed thinking off","toolsEnabledWithReasoning":false,"toolsEnabledWithoutReasoning":true}}}},"leaderboard":[{"name":"reasoning, coding and math","url":"https://developer.nvidia.com/blog/nvidia-llama-nemotron-ultra-open-model-delivers-groundbreaking-reasoning-accuracy/","position":1}]},"artifactName":"llama-3_1-nemotron-ultra-253b-v1"},"config":{"name":"llama-3_1-nemotron-ultra-253b-v1","type":"model"}},{"endpoint":{"artifact":{"name":"llama-3_3-nemotron-super-49b-v1","displayName":"llama-3.3-nemotron-super-49b-v1","publisher":"nvidia","shortDescription":"High efficiency model with leading accuracy for reasoning, tool calling, chat, and instruction following.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/llama-3_3-nemotron-super-49b-v1.jpg","labels":["advanced reasoning","function calling","instruction following","math"],"attributes":[{"key":"AVAILABLE","value":"true"},{"key":"PREVIEW","value":"false"}],"artifactType":"ENDPOINT","bias":"|Field:|Response:|\n|:---:|:---:|\n|Participation considerations from adversely impacted groups (protected classes) in model design and testing:|None|\n|Measures taken to mitigate against unwanted bias:|None|","canGuestDownload":true,"createdDate":"2025-03-18T18:56:30.758Z","description":"$4ad","explainability":"$4ae","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","privacy":"|Field:|Response:|\n|:---:|:---:|\n|Generatable or Reverse engineerable personally-identifiable information?|None|\n|Was consent obtained for any personal data used?|None Known|\n|Personal data used to create this model?|None Known|\n|How often is dataset reviewed?|Before Release|\n|Is there provenance for all datasets used in training?|Yes|\n|Does data labeling (annotation, metadata) comply with privacy laws?|Yes|\n|Applicable NVIDIA Privacy Policy|https://www.nvidia.com/en-us/about-nvidia/privacy-policy/|","safetyAndSecurity":"|Field:|Response:|\n|:---:|:---:|\n|Model Application(s):|Chat, Instruction Following, Chatbot Development, Code Generation, Reasoning|\n|Describe life critical application (if present):|None Known (please see referenced Known Risks in the Explainability subcard).|\n|Use Case Restrictions:|Your use of this model is governed by the [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/). Additional Information: [Llama 3.3 Community License Agreement](https://www.llama.com/llama3_3/license/). Built with Llama.|\n|Model and Dataset Restrictions:|The Principle of least privilege (PoLP) is applied limiting access for dataset generation. Restrictions enforce dataset access during training, and dataset license constraints adhered to. Model checkpoints are made available on Hugging Face and NGC, and may become available on cloud providers' model catalog.|","updatedDate":"2025-03-25T21:52:27.860Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"49544ae9-c37f-4033-9acc-5eeee0e9d1e5"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for nvidia/llama-3.3-nemotron-super-49b-v1","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/nvidia-llama-3_3-nemotron-super-49b-v1 for more details.","version":"1.0.0","termsOfService":"https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/","contact":{"name":"NVIDIA Enterprise Support","url":"https://www.nvidia.com/en-us/support/enterprise/"},"license":{"name":"Llama 3.3 License","url":"https://github.com/meta-llama/llama-models/blob/main/models/llama3_3/LICENSE"}},"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/ChatCompletionRequest"}}},"required":true},"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionResponse"}}}},"402":{"description":"Payment Required","content":{"application/json":{"schema":{"$ref":"#/components/schemas/PaymentRequiredError"}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}},"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":"Write a limerick about the wonders of GPU computing.","requestJson":"{\n \"model\": \"nvidia/llama-3.3-nemotron-super-49b-v1\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a helpful assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"Write a limerick about the wonders of GPU computing.\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"seed\": 42,\n \"stop\": null,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"nvidia/llama-3.3-nemotron-super-49b-v1\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Here's a short poem on...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"},{"name":"What can I see at NVIDIA's GPU Technology Conference?","requestJson":"{\n \"model\": \"nvidia/llama-3.3-nemotron-super-49b-v1\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a helpful assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"What can I see at NVIDIA's GPU Technology Conference?\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"seed\": 42,\n \"stop\": null,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"nvidia/llama-3.3-nemotron-super-49b-v1\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"At NVIDIA's GTC conference...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}],"templates":[{"title":"No Streaming","requestEjs":{"python":"from openai import OpenAI\n\nclient = OpenAI(\n base_url = \"https://integrate.api.nvidia.com/v1\",\n api_key = \"$NVIDIA_API_KEY\"\n)\n\ncompletion = client.chat.completions.create(\n model=\"<%- request.model %>\",\n messages=<%- JSON.stringify(request.messages) %>,\n temperature=<%- request.temperature %>,\n top_p=<%- request.top_p %>,\n max_tokens=<%- request.max_tokens %>,\n frequency_penalty=<%- request.frequency_penalty %>,\n presence_penalty=<%- request.presence_penalty %>,\n stream=<%- request.stream?.toString()[0].toUpperCase() + request.stream?.toString().slice(1) %>\n)\n<% if (request.stream) { %>\nfor chunk in completion:\n if chunk.choices[0].delta.content is not None:\n print(chunk.choices[0].delta.content, end=\"\")\n<% } else { %>\nprint(completion.choices[0].message)\n<% } %>\n","node.js":"import OpenAI from 'openai';\n\nconst openai = new OpenAI({\n apiKey: '$NVIDIA_API_KEY',\n baseURL: 'https://integrate.api.nvidia.com/v1',\n})\n\nasync function main() {\n const completion = await openai.chat.completions.create({\n model: \"<%- request.model %>\",\n messages: <%- JSON.stringify(request.messages) %>,\n temperature: <%- request.temperature %>,\n top_p: <%- request.top_p %>,\n max_tokens: <%- request.max_tokens %>,\n frequency_penalty: <%- request.frequency_penalty %>,\n presence_penalty: <%- request.presence_penalty %>,\n stream: <%- request.stream %>,\n })\n <% if (request.stream) { %>\n for await (const chunk of completion) {\n process.stdout.write(chunk.choices[0]?.delta?.content || '')\n }\n <% } else { %>\n process.stdout.write(completion.choices[0]?.message?.content);\n <% } %>\n}\n\nmain();","curl":"curl https://integrate.api.nvidia.com/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n -d '{\n \"model\": \"nvidia/llama-3.3-nemotron-super-49b-v1\",\n \"messages\": <%- JSON.stringify(request.messages).replaceAll(\"'\", \"'\\\"'\\\"'\") %>,\n \"temperature\": <%- request.temperature %>, \n \"top_p\": <%- request.top_p %>,\n \"max_tokens\": <%- request.max_tokens %>,\n \"frequency_penalty\": <%- request.frequency_penalty %>,\n \"presence_penalty\": <%- request.presence_penalty %>,\n \"stream\": <%- request.stream %> \n }'\n"},"response":"{\n \"id\": \"chatcmpl-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"nvidia/llama-3.3-nemotron-super-49b-v1\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\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 \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"ChatCompletionRequest":{"properties":{"model":{"type":"string","title":"Model","default":"nvidia/llama-3.3-nemotron-super-49b-v1"},"max_tokens":{"type":"integer","minimum":1,"title":"Max Tokens","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.","default":4096,"maximum":16384},"stream":{"type":"boolean","title":"Stream","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.","default":false},"temperature":{"type":"number","maximum":1,"minimum":0,"title":"Temperature","description":"The 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.","default":0.6},"top_p":{"type":"number","maximum":1,"exclusiveMinimum":0,"title":"Top P","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.","default":0.95},"stop":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"string"},{"type":"null"}],"title":"Stop","description":"A string or a list of strings where the API will stop generating further tokens. The returned text will not contain the stop sequence.","examples":[null]},"frequency_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Frequency Penalty","description":"Indicates how much to penalize new tokens based on their existing frequency in the text so far, decreasing model likelihood to repeat the same line verbatim."},"presence_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Presence Penalty","description":"Positive values penalize new tokens based on whether they appear in the text so far, increasing model likelihood to talk about new topics."},"seed":{"type":"integer","maximum":18446744073709552000,"minimum":0,"title":"Seed","description":"The model generates random results. Changing the input seed alone will produce a different response with similar characteristics. It is possible to reproduce results by fixing the input seed (assuming all other hyperparameters are also fixed).","default":0},"messages":{"anyOf":[{"items":{"additionalProperties":{"type":"string"},"type":"object"},"type":"array"}],"title":"Messages","description":"A list of messages comprising the conversation so far.","examples":[[{"role":"user","content":"Write a limerick about the wonders of GPU computing."}]]}},"additionalProperties":false,"type":"object","required":["messages"],"title":"ChatCompletionRequest","description":"OpenAI ChatCompletionRequest"},"ChatCompletionResponse":{"properties":{"id":{"type":"string","title":"Id","description":"A unique identifier for the completion."},"object":{"type":"string","title":"Object","default":"chat.completion"},"created":{"type":"integer","title":"Created"},"model":{"type":"string","title":"Model","example":"nvidia/llama-3.3-nemotron-super-49b-v1"},"choices":{"items":{"$ref":"#/components/schemas/ChatCompletionResponseChoice"},"type":"array","title":"Choices","description":"The list of completion choices the model generated for the input prompt."},"usage":{"$ref":"#/components/schemas/UsageInfo","description":"Usage statistics for the completion request."}},"type":"object","required":["model","choices","usage"],"title":"ChatCompletionResponse"},"ChatCompletionResponseChoice":{"properties":{"index":{"type":"integer","title":"Index","description":"The index of the choice in the list of choices (always 0)."},"message":{"$ref":"#/components/schemas/ChatMessage","description":"A chat completion message generated by the model."},"finish_reason":{"anyOf":[{"type":"string","enum":["stop","length"]},{"type":"null"}],"title":"Finish Reason","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"}},"type":"object","required":["index","message"],"title":"ChatCompletionResponseChoice"},"ChatMessage":{"properties":{"role":{"type":"string","title":"Role","description":"The role of the message author."},"content":{"type":"string","title":"Content","description":"The contents of the message."}},"type":"object","required":["role","content"],"title":"ChatMessage"},"HTTPValidationError":{"properties":{"detail":{"items":{"$ref":"#/components/schemas/ValidationError"},"type":"array","title":"Detail","description":"Detailed information about the error."}},"type":"object","title":"HTTPValidationError"},"PaymentRequiredError":{"properties":{"detail":{"type":"string","description":"Contains specific information related to the error and why it occurred.","example":"You have reached your limit of credits."}},"type":"object","title":"PaymentRequiredError"},"UsageInfo":{"properties":{"prompt_tokens":{"type":"integer","title":"Prompt Tokens","description":"Number of tokens in the prompt.","default":0},"total_tokens":{"type":"integer","title":"Total Tokens","description":"Total number of tokens used in the request (prompt + completion).","default":0},"completion_tokens":{"anyOf":[{"type":"integer"},{"type":"null"}],"title":"Completion Tokens","description":"Number of tokens in the generated completion.","default":0}},"type":"object","title":"UsageInfo"},"ValidationError":{"properties":{"loc":{"items":{"anyOf":[{"type":"string"},{"type":"integer"}]},"type":"array","title":"Location"},"msg":{"type":"string","title":"Message","description":"The error message."},"type":{"type":"string","title":"Error Type","description":"Error type"}},"type":"object","required":["loc","msg","type"],"title":"ValidationError"}}}},"namespace":"qc69jvmznzxy","updatedDate":"2025-03-25T21:52:28.660Z","nvcfFunctionId":"a2646582-44bd-4899-bdf4-acf8c9df702c","createdDate":"2025-03-18T18:56:31.023Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/nvidia-llama-3_3-nemotron-super-49b-v1","termsOfUse":"b>GOVERNING TERMS: This trial service is governed by the NVIDIA API Trial Terms of Service. Use of this model is governed by the AI Foundation Models Community License Agreement . ADDITIONAL INFORMATION: Llama 3.3 Community License Agreement , Built with Llama.\n","showUnavailableBanner":false,"cta":{"text":"Apply to Self-Host","url":"https://www.nvidia.com/en-us/ai/nim-notifyme/"},"playground":{"type":"chatWithThinking","options":{"chat":{"reasoning":{"defaultEnabled":true,"systemPromptEnabled":"detailed thinking on","systemPromptDisabled":"detailed thinking off","toolsEnabledWithReasoning":false,"toolsEnabledWithoutReasoning":true}}}},"deploy":[{"label":"Linux with Docker","filename":"linux.md","contents":"$4af"}]},"artifactName":"llama-3_3-nemotron-super-49b-v1"},"config":{"name":"llama-3_3-nemotron-super-49b-v1","type":"model"}},{"endpoint":{"artifact":{"name":"deepseek-r1","displayName":"deepseek-r1","publisher":"deepseek-ai","shortDescription":"State-of-the-art, high-efficiency LLM excelling in reasoning, math, and coding.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/deepseek-r1.jpg","labels":["Math","advanced reasoning","chat"],"attributes":[{"key":"AVAILABLE","value":"true"},{"key":"PREVIEW","value":"false"}],"artifactType":"ENDPOINT","canGuestDownload":true,"createdDate":"2025-01-30T23:29:47.817Z","description":"$4b0","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","updatedDate":"2025-04-18T05:41:53.357Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"15a3de61-4dd0-4f85-ae7e-39d1e0e1be3b"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for deepseek-ai/deepseek-r1","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/deepseek-ai-deepseek-r1 for more details.","version":"1.0.0","termsOfService":"https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/","contact":{"name":"NVIDIA Enterprise Support","url":"https://www.nvidia.com/en-us/support/enterprise/"},"license":{"name":"MIT License","url":"https://huggingface.co/deepseek-ai/deepseek-r1/blob/main/LICENSE"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1/"}],"paths":{"/chat/completions":{"post":{"operationId":"create_chat_completion_v1_chat_completions_post","tags":["Chat"],"summary":"Creates a model response for the given chat conversation.","description":"Given a list of messages comprising a conversation, the model will return a response. Compatible with OpenAI. See https://platform.openai.com/docs/api-reference/chat/create","requestBody":{"content":{"application/json":{"schema":{"$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":"Which number is larger, 9.11 or 9.8?","requestJson":"{\n \"model\": \"deepseek-ai/deepseek-r1\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"Which number is larger, 9.11 or 9.8?\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 4096,\n \"seed\": 42,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"deepseek-ai/deepseek-r1\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"The number 9.11 is...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"},{"name":"How many 'r's are in 'strawberry'?","requestJson":"{\n \"model\": \"deepseek-ai/deepseek-r1\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"How many 'r's are in 'strawberry'?\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 4096,\n \"seed\": 42,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"deepseek-ai/deepseek-r1\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"In the word strawberry...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}],"templates":[{"title":"No Streaming","requestEjs":{"python":"$4b1","langChain":"from langchain_nvidia_ai_endpoints import ChatNVIDIA\n\nclient = ChatNVIDIA(\n model=\"<%- request.model %>\",\n api_key=\"$NVIDIA_API_KEY\", \n temperature=<%- request.temperature %>,\n top_p=<%- request.top_p %>,\n max_tokens=<%- request.max_tokens %>,\n)\n<% if (request.stream) { %>\nfor chunk in client.stream(<%- JSON.stringify(request.messages) %>): \n print(chunk.content, end=\"\")\n<% } else { %>\nresponse = client.invoke(<%- JSON.stringify(request.messages) %>)\nprint(response.content)\n<% } %>\n","node.js":"$4b2","curl":"$4b3"},"response":"{\n \"id\": \"chatcmpl-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"deepseek-ai/deepseek-r1\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"\\n\\nHello there, how may I assist you today?\",\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"Errors":{"properties":{"type":{"type":"string","description":"Error type"},"title":{"type":"string","description":"Error title"},"status":{"type":"integer","description":"Error status code"},"detail":{"type":"string","description":"Detailed information about the error"},"instance":{"type":"string","description":"Function instance used to invoke the request"},"requestId":{"type":"string","format":"uuid","description":"UUID of the request"}},"type":"object","required":["type","title","status","detail","instance","requestId"],"title":"InvokeError"},"ChatCompletion":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$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":"deepseek-ai/deepseek-r1"},"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":0.6,"description":"The 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.","maximum":1,"minimum":0,"title":"Temperature","type":"number"},"top_p":{"default":0.7,"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"},"frequency_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Frequency Penalty","description":"Indicates how much to penalize new tokens based on their existing frequency in the text so far, decreasing model likelihood to repeat the same line verbatim."},"presence_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Presence Penalty","description":"Positive values penalize new tokens based on whether they appear in the text so far, increasing model likelihood to talk about new topics."},"max_tokens":{"default":4096,"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.","maximum":4096,"minimum":1,"title":"Max Tokens","type":"integer"},"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"},"stop":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"string"},{"type":"null"}],"title":"Stop","description":"A string or a list of strings where the API will stop generating further tokens. The returned text will not contain the stop sequence."}},"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"],"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"],"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":["user","assistant"],"title":"Role","type":"string"},"content":{"description":"The contents of the message.","title":"Content","anyOf":[{"type":"string"},{"type":"null"}]}},"required":["role","content"],"title":"Message","type":"object"},"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"}}}},"namespace":"qc69jvmznzxy","updatedDate":"2025-04-18T05:41:53.862Z","nvcfFunctionId":"854db4e5-9be7-45a0-a730-183cadf87e50","createdDate":"2025-01-30T23:29:48.101Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/deepseek-ai-deepseek-r1","termsOfUse":"GOVERNING TERMS: The trial service is governed by the NVIDIA API Trial Terms of Service. Use of this model is governed by the NVIDIA Community Model License. Additional Information: MIT License\n","showUnavailableBanner":true,"playground":{"type":"chatWithThinking"},"deploy":[{"label":"Linux with Docker","filename":"linux.md","contents":"$4b4"}]},"artifactName":"deepseek-r1"},"config":{"name":"deepseek-r1","type":"model"}},{"endpoint":{"artifact":{"name":"llama-3_1-nemotron-nano-8b-v1","displayName":"llama-3.1-nemotron-nano-8b-v1","publisher":"nvidia","shortDescription":"Leading reasoning and agentic AI accuracy model for PC and edge.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/llama-3_3-nemotron-49b-instruct.jpg","labels":["advanced reasoning","function calling","instruction following","math"],"attributes":[{"key":"PREVIEW","value":"true"}],"artifactType":"ENDPOINT","bias":"|Field:|Response:|\n|:---:|:---:|\n|Participation considerations from adversely impacted groups (protected classes) in model design and testing:|None|\n|Measures taken to mitigate against unwanted bias:|None|","canGuestDownload":true,"createdDate":"2025-03-18T18:56:30.361Z","description":"$4b5","explainability":"$4b6","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","privacy":"|Field:|Response:|\n|:---:|:---:|\n|Generatable or Reverse engineerable personally-identifiable information?|None|\n|Was consent obtained for any personal data used?|None Known|\n|Personal data used to create this model?|None Known|\n|How often is dataset reviewed?|Before Release|\n|Is there provenance for all datasets used in training?|Yes|\n|Does data labeling (annotation, metadata) comply with privacy laws?|Yes|\n|Applicable NVIDIA Privacy Policy|https://www.nvidia.com/en-us/about-nvidia/privacy-policy/|","safetyAndSecurity":"|Field:|Response:|\n|:---:|:---:|\n|Model Application(s):|Chat, Instruction Following, Chatbot Development, Code Generation, Reasoning|\n|Describe life critical application (if present):|None Known (please see referenced Known Risks in the Explainability subcard).|\n|Use Case Restrictions:|Your use of this model is governed by the [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/). Additional Information: [Llama 3.1 Community License Agreement](https://www.llama.com/llama3_1/license/). Built with Llama.|\n|Model and Dataset Restrictions:|The Principle of least privilege (PoLP) is applied limiting access for dataset generation. Restrictions enforce dataset access during training, and dataset license constraints adhered to. Model checkpoints are made available on Hugging Face and NGC, and may become available on cloud providers' model catalog.|","updatedDate":"2025-03-18T18:56:30.361Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"1e15a863-a2fa-4414-8bd7-ac106f60f992"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for nvidia/llama-3.1-nemotron-nano-8b-v1","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/nvidia-llama-3_1-nemotron-nano-8b-v1 for more details.","version":"1.0.0","termsOfService":"https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/","contact":{"name":"NVIDIA Enterprise Support","url":"https://www.nvidia.com/en-us/support/enterprise/"},"license":{"name":"Llama 3.1 License","url":"https://github.com/meta-llama/llama-models/blob/main/License/Llama3.1.txt"}},"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/ChatCompletionRequest"}}},"required":true},"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionResponse"}}}},"402":{"description":"Payment Required","content":{"application/json":{"schema":{"$ref":"#/components/schemas/PaymentRequiredError"}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}},"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":"Explain how a transformer neural network works.","requestJson":"{\n \"model\": \"nvidia/llama-3.1-nemotron-nano-8b-v1\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a helpful assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"Explain how a transformer neural network works.\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 4096,\n \"seed\": 42,\n \"stop\": null,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"nvidia/llama-3.1-nemotron-nano-8b-v1\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"A transformer neural network is an architecture...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"},{"name":"Write a Python function to find the nth Fibonacci number using dynamic programming.","requestJson":"{\n \"model\": \"nvidia/llama-3.1-nemotron-nano-8b-v1\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a helpful assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"Write a Python function to find the nth Fibonacci number using dynamic programming.\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 4096,\n \"seed\": 42,\n \"stop\": null,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"nvidia/llama-3.1-nemotron-nano-8b-v1\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Here's a Python function to...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}],"templates":[{"title":"No Streaming","requestEjs":{"python":"from openai import OpenAI\n\nclient = OpenAI(\n base_url = \"https://integrate.api.nvidia.com/v1\",\n api_key = \"$NVIDIA_API_KEY\"\n)\n\ncompletion = client.chat.completions.create(\n model=\"<%- request.model %>\",\n messages=<%- JSON.stringify(request.messages) %>,\n temperature=<%- request.temperature %>,\n top_p=<%- request.top_p %>,\n max_tokens=<%- request.max_tokens %>,\n frequency_penalty=<%- request.frequency_penalty %>,\n presence_penalty=<%- request.presence_penalty %>,\n stream=<%- request.stream?.toString()[0].toUpperCase() + request.stream?.toString().slice(1) %>\n)\n<% if (request.stream) { %>\nfor chunk in completion:\n if chunk.choices[0].delta.content is not None:\n print(chunk.choices[0].delta.content, end=\"\")\n<% } else { %>\nprint(completion.choices[0].message)\n<% } %>\n","node.js":"import OpenAI from 'openai';\n\nconst openai = new OpenAI({\n apiKey: '$NVIDIA_API_KEY',\n baseURL: 'https://integrate.api.nvidia.com/v1',\n})\n\nasync function main() {\n const completion = await openai.chat.completions.create({\n model: \"<%- request.model %>\",\n messages: <%- JSON.stringify(request.messages) %>,\n temperature: <%- request.temperature %>,\n top_p: <%- request.top_p %>,\n max_tokens: <%- request.max_tokens %>,\n frequency_penalty: <%- request.frequency_penalty %>,\n presence_penalty: <%- request.presence_penalty %>,\n stream: <%- request.stream %>,\n })\n <% if (request.stream) { %>\n for await (const chunk of completion) {\n process.stdout.write(chunk.choices[0]?.delta?.content || '')\n }\n <% } else { %>\n process.stdout.write(completion.choices[0]?.message?.content);\n <% } %>\n}\n\nmain();","curl":"curl https://integrate.api.nvidia.com/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n -d '{\n \"model\": \"nvidia/llama-3.1-nemotron-nano-8b-v1\",\n \"messages\": <%- JSON.stringify(request.messages).replaceAll(\"'\", \"'\\\"'\\\"'\") %>,\n \"temperature\": <%- request.temperature %>, \n \"top_p\": <%- request.top_p %>,\n \"max_tokens\": <%- request.max_tokens %>,\n \"frequency_penalty\": <%- request.frequency_penalty %>,\n \"presence_penalty\": <%- request.presence_penalty %>,\n \"stream\": <%- request.stream %> \n }'\n"},"response":"{\n \"id\": \"chatcmpl-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"nvidia/llama-3.1-nemotron-nano-8b-v1\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\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 \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"ChatCompletionRequest":{"properties":{"model":{"type":"string","title":"Model","default":"nvidia/llama-3.1-nemotron-nano-8b-v1"},"max_tokens":{"type":"integer","minimum":1,"title":"Max Tokens","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.","default":4096,"maximum":16384},"stream":{"type":"boolean","title":"Stream","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.","default":false},"temperature":{"type":"number","maximum":1,"minimum":0,"title":"Temperature","description":"The 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.","default":0.6},"top_p":{"type":"number","maximum":1,"exclusiveMinimum":0,"title":"Top P","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.","default":0.95},"stop":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"string"},{"type":"null"}],"title":"Stop","description":"A string or a list of strings where the API will stop generating further tokens. The returned text will not contain the stop sequence.","examples":[null]},"frequency_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Frequency Penalty","description":"Indicates how much to penalize new tokens based on their existing frequency in the text so far, decreasing model likelihood to repeat the same line verbatim."},"presence_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Presence Penalty","description":"Positive values penalize new tokens based on whether they appear in the text so far, increasing model likelihood to talk about new topics."},"seed":{"type":"integer","maximum":18446744073709552000,"minimum":0,"title":"Seed","description":"The model generates random results. Changing the input seed alone will produce a different response with similar characteristics. It is possible to reproduce results by fixing the input seed (assuming all other hyperparameters are also fixed).","default":0},"messages":{"anyOf":[{"items":{"additionalProperties":{"type":"string"},"type":"object"},"type":"array"}],"title":"Messages","description":"A list of messages comprising the conversation so far.","examples":[[{"role":"user","content":"Write a limerick about the wonders of GPU computing."}]]}},"additionalProperties":false,"type":"object","required":["messages"],"title":"ChatCompletionRequest","description":"OpenAI ChatCompletionRequest"},"ChatCompletionResponse":{"properties":{"id":{"type":"string","title":"Id","description":"A unique identifier for the completion."},"object":{"type":"string","title":"Object","default":"chat.completion"},"created":{"type":"integer","title":"Created"},"model":{"type":"string","title":"Model","example":"nvidia/llama-3.1-nemotron-nano-8b-v1"},"choices":{"items":{"$ref":"#/components/schemas/ChatCompletionResponseChoice"},"type":"array","title":"Choices","description":"The list of completion choices the model generated for the input prompt."},"usage":{"$ref":"#/components/schemas/UsageInfo","description":"Usage statistics for the completion request."}},"type":"object","required":["model","choices","usage"],"title":"ChatCompletionResponse"},"ChatCompletionResponseChoice":{"properties":{"index":{"type":"integer","title":"Index","description":"The index of the choice in the list of choices (always 0)."},"message":{"$ref":"#/components/schemas/ChatMessage","description":"A chat completion message generated by the model."},"finish_reason":{"anyOf":[{"type":"string","enum":["stop","length"]},{"type":"null"}],"title":"Finish Reason","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"}},"type":"object","required":["index","message"],"title":"ChatCompletionResponseChoice"},"ChatMessage":{"properties":{"role":{"type":"string","title":"Role","description":"The role of the message author."},"content":{"type":"string","title":"Content","description":"The contents of the message."}},"type":"object","required":["role","content"],"title":"ChatMessage"},"HTTPValidationError":{"properties":{"detail":{"items":{"$ref":"#/components/schemas/ValidationError"},"type":"array","title":"Detail","description":"Detailed information about the error."}},"type":"object","title":"HTTPValidationError"},"PaymentRequiredError":{"properties":{"detail":{"type":"string","description":"Contains specific information related to the error and why it occurred.","example":"You have reached your limit of credits."}},"type":"object","title":"PaymentRequiredError"},"UsageInfo":{"properties":{"prompt_tokens":{"type":"integer","title":"Prompt Tokens","description":"Number of tokens in the prompt.","default":0},"total_tokens":{"type":"integer","title":"Total Tokens","description":"Total number of tokens used in the request (prompt + completion).","default":0},"completion_tokens":{"anyOf":[{"type":"integer"},{"type":"null"}],"title":"Completion Tokens","description":"Number of tokens in the generated completion.","default":0}},"type":"object","title":"UsageInfo"},"ValidationError":{"properties":{"loc":{"items":{"anyOf":[{"type":"string"},{"type":"integer"}]},"type":"array","title":"Location"},"msg":{"type":"string","title":"Message","description":"The error message."},"type":{"type":"string","title":"Error Type","description":"Error type"}},"type":"object","required":["loc","msg","type"],"title":"ValidationError"}}}},"namespace":"qc69jvmznzxy","nvcfFunctionId":"07587d89-2056-4eb8-a448-4b05463d2478","createdDate":"2025-03-18T18:56:30.714Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/nvidia-llama-3_1-nemotron-nano-8b-v1","termsOfUse":"GOVERNING TERMS: This trial service is governed by the NVIDIA API Trial Terms of Service. Use of this model is governed by the AI Foundation Models Community License Agreement . ADDITIONAL INFORMATION: Llama 3.1 Community License Agreement, Built with Llama.\n","showUnavailableBanner":false,"cta":{"text":"Apply to Self-Host","url":"https://www.nvidia.com/en-us/ai/nim-notifyme/"},"playground":{"type":"chatWithThinking","options":{"chat":{"reasoning":{"defaultEnabled":false,"systemPromptEnabled":"detailed thinking on","systemPromptDisabled":"detailed thinking off","toolsEnabledWithReasoning":false,"toolsEnabledWithoutReasoning":true}}}}},"artifactName":"llama-3_1-nemotron-nano-8b-v1"},"config":{"name":"llama-3_1-nemotron-nano-8b-v1","type":"model"}},{"endpoint":{"artifact":{"name":"gemma-3-27b-it","displayName":"gemma-3-27b-it","publisher":"google","shortDescription":"Cutting-edge open multimodal model exceling in high-quality reasoning from images.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/gemma-3-27b-it.jpg","labels":["Language Generation","Vision Assistant","Visual Question Answering","Image-to-Text"],"attributes":[{"key":"PREVIEW","value":"true"}],"artifactType":"ENDPOINT","canGuestDownload":true,"createdDate":"2025-03-13T17:31:09.671Z","description":"$4b7","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","updatedDate":"2025-03-14T19:44:50.785Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"e86be197-7a5a-4af0-b131-20b07fbadd27"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for google/gemma-3-27b-it","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/google-gemma-3-27b-it for more details.","version":"1.0.0","termsOfService":"https://nvidia.com/legal/terms-of-use","contact":{"name":"NVIDIA Support","url":"https://help.nvidia.com/"},"license":{"name":"Gemma Terms of Use","url":"https://ai.google.dev/gemma/terms"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1"}],"tags":[{"name":"Multimodal API","description":"This API performs inference using multi-modal large language models (MLLMs)."}],"paths":{"/chat/completions":{"post":{"tags":["Multimodal API"],"summary":"Request response from the model","description":"Invokes inference using the model chat parameters. If uploading large images, this POST should be used in conjunction with the NVCF API which allows for the upload of large assets. \nYou can find details on how to use NVCF Asset APIs here: https://docs.api.nvidia.com/cloud-functions/reference/createasset","operationId":"invokeFunction","parameters":[{"in":"header","name":"NVCF-INPUT-ASSET-REFERENCES","schema":{"type":"string","maxLength":370,"format":"uuid"},"required":false,"description":"String of asset IDs separated by commas. Data is uploaded to AWS S3 using NVCF Asset APIs and associated with these asset IDs.If the size of an image is more than 180KB, it needs to be uploaded to a presigned S3 URL bucket. The presigned URL allows for secure and temporary access to the S3 bucket for uploading the image. Once the asset is requested, an asset ID is generated for it. Please include this asset ID in this header and to use the uploaded image in a prompt, you need to refer to it using the following format: `

`."}],"requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/NIMLLMChatCompletionRequest"}}},"required":true},"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionResponse"}},"text/event-stream":{"schema":{"$ref":"#/components/schemas/ChatCompletionStreamResponse"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid","maxLength":36}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string","format":"^[a-zA-Z-]{1,64}$","maxLength":64}}}},"422":{"description":"Validation failed, provided entity could not be processed.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","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":"image_captioning","input":{"text":"What is shown in this image?","images":["https://assets.ngc.nvidia.com/products/api-catalog/gemma3/traffic_sign.jpg"]},"output":{"text":"**A red stop sign:** Prominently displayed in the foreground..."}},{"name":"visual_qa","input":{"text":"Where is the cow standing?","images":["https://assets.ngc.nvidia.com/products/api-catalog/gemma3/cow_on_the_beach.jpg"]},"output":{"text":"On a beach."}}],"templates":[{"title":"Default","requestEjs":{"python":"$4b8","node.js":"$4b9","curl":"stream=<%- request.stream %>\n\nif [ \"$stream\" = true ]; then\n accept_header='Accept: text/event-stream'\nelse\n accept_header='Accept: application/json'\nfi\n<% content = \"What is in this image?

\" %>\nimage_b64=$( base64 image.png )\n\necho '{\n \"model\": \"<%- request.model %>\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"<%- content %>\"\n }\n ],\n \"max_tokens\": <%- request.max_tokens %>,\n \"temperature\": <%- request.temperature.toFixed(2) %>,\n \"top_p\": <%- request.top_p.toFixed(2) %>,\n \"stream\": <%- request.stream %>\n}' > payload.json\n\ncurl https://integrate.api.nvidia.com/v1/chat/completions \\\n -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -H \"$accept_header\" \\\n -d @payload.json\n"},"response":"{\n \"choices\": [{\n \"index\": 0,\n \"model\": \"google/gemma-3-27b-it\",\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"...\",\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}},"/status/{requestId}":{"get":{"tags":["Multimodal API"],"summary":"Gets the result of an earlier function invocation request that returned a status of 202.","operationId":"getFunctionInvocationResult","parameters":[{"name":"requestId","in":"path","description":"requestId to poll results","required":true,"schema":{"type":"string","format":"uuid","maxLength":36}}],"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionResponse"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid","maxLength":36}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string","format":"^[a-zA-Z-]{1,64}$","maxLength":64}}}},"422":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"ChatCompletionResponse":{"properties":{"id":{"type":"string","title":"Id"},"object":{"type":"string","enum":["chat.completion"],"const":"chat.completion","title":"Object","default":"chat.completion"},"created":{"type":"integer","title":"Created"},"model":{"type":"string","title":"Model"},"choices":{"items":{"$ref":"#/components/schemas/ChatCompletionResponseChoice"},"type":"array","title":"Choices"},"usage":{"$ref":"#/components/schemas/UsageInfo"}},"additionalProperties":false,"type":"object","required":["model","choices","usage"],"title":"ChatCompletionResponse"},"ChatCompletionResponseChoice":{"properties":{"index":{"type":"integer","title":"Index"},"message":{"$ref":"#/components/schemas/ChatMessage"},"finish_reason":{"anyOf":[{"type":"string","enum":["stop","length"]},{"type":"null"}],"title":"Finish Reason"},"stop_reason":{"anyOf":[{"type":"integer"},{"type":"string"},{"type":"null"}],"title":"Stop Reason"}},"additionalProperties":false,"type":"object","required":["index","message"],"title":"ChatCompletionResponseChoice"},"ChatCompletionResponseStreamChoice":{"properties":{"index":{"type":"integer","title":"Index"},"delta":{"$ref":"#/components/schemas/DeltaMessage"},"finish_reason":{"anyOf":[{"type":"string","enum":["stop","length"]},{"type":"null"}],"title":"Finish Reason"},"stop_reason":{"anyOf":[{"type":"integer"},{"type":"string"},{"type":"null"}],"title":"Stop Reason"}},"additionalProperties":false,"type":"object","required":["index","delta"],"title":"ChatCompletionResponseStreamChoice"},"ChatCompletionStreamResponse":{"properties":{"id":{"type":"string","title":"Id"},"object":{"type":"string","enum":["chat.completion.chunk"],"const":"chat.completion.chunk","title":"Object","default":"chat.completion.chunk"},"created":{"type":"integer","title":"Created"},"model":{"type":"string","title":"Model"},"choices":{"items":{"$ref":"#/components/schemas/ChatCompletionResponseStreamChoice"},"type":"array","title":"Choices"},"usage":{"anyOf":[{"$ref":"#/components/schemas/UsageInfo"},{"type":"null"}]}},"additionalProperties":false,"type":"object","required":["model","choices"],"title":"ChatCompletionStreamResponse"},"ChatMessage":{"properties":{"role":{"type":"string","title":"Role"},"content":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Content"}},"additionalProperties":false,"type":"object","required":["role"],"title":"ChatMessage"},"DeltaMessage":{"properties":{"role":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Role"},"content":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Content"}},"additionalProperties":false,"type":"object","title":"DeltaMessage"},"ErrorResponse":{"properties":{"object":{"type":"string","title":"Object","default":"error"},"message":{"type":"string","title":"Message"},"type":{"type":"string","title":"Type"},"param":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Param"},"code":{"type":"integer","title":"Code"}},"additionalProperties":false,"type":"object","required":["message","type","code"],"title":"ErrorResponse"},"HTTPValidationError":{"properties":{"detail":{"items":{"$ref":"#/components/schemas/ValidationError"},"type":"array","title":"Detail"}},"type":"object","title":"HTTPValidationError"},"ImageURL":{"properties":{"url":{"type":"string","title":"Url"}},"type":"object","required":["url"],"title":"ImageURL"},"NIMLLMChatCompletionMessage":{"properties":{"role":{"allOf":[{"$ref":"#/components/schemas/Role"}],"description":"The role of the message's author."},"content":{"anyOf":[{"type":"string"},{"items":{"anyOf":[{"$ref":"#/components/schemas/NIMVLMChatCompletionContentPartImage"},{"$ref":"#/components/schemas/NIMVLMChatCompletionContentPartText"}]},"type":"array"}],"title":"Content","description":"The contents of the message.\n
To pass images (only with role=`user`):\n
- When content is a string, image can be passed together with the text with `img` HTML tags that wraps \n an image URL (`

`), \n base64 encoded image data (`

`), \n or an NVCF asset ID (`

`. Insert an uploaded audio in a prompt using the following format: `