19:[["$","$L21",null,{"flag":"killswitches/quick-actions.enabled","initialData":true,"children":["$","div",null,{"className":"-mx-4 -mt-4 mb-4 border-b border-n700 p-4 md:-mx-8 md:p-8","children":[["$","$L37",null,{"quickStartCardProps":{"optionsData":{"options":[{"name":"llama-4-maverick-17b-128e-instruct"},{"name":"llama-4-scout-17b-16e-instruct"},{"name":"deepseek-r1"},{"name":"llama-3_3-nemotron-49b-instruct"},{"name":"llama-3_3-70b-instruct"},{"name":"deepseek-r1-distill-llama-70b"},{"name":"embed-qa-4"},{"name":"qwen2_5-coder-32b-instruct"}]},"optionSpecs":[{"endpointSpec":{"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":{"properties":{"messages":{"items":{"properties":{"role":{"allOf":[{"type":"string","enum":["assistant","user"],"title":"Role"}],"description":"The role of the message's author."},"content":{"anyOf":[{"type":"string"},{"items":{"anyOf":[{"properties":{"image_url":{"properties":{"url":{"type":"string","title":"Url"}},"type":"object","required":["url"],"title":"ImageURL"},"type":{"type":"string","enum":["image_url"],"const":"image_url","title":"Type"}},"type":"object","required":["image_url","type"],"title":"NIMVLMChatCompletionContentPartImage"},{"properties":{"text":{"type":"string","title":"Text"},"type":{"type":"string","enum":["text"],"const":"text","title":"Type"}},"type":"object","required":["text","type"],"title":"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"},"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-maverick-17b-128e-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"}}},"required":true},"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"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":{"properties":{"index":{"type":"integer","title":"Index"},"message":{"properties":{"role":{"type":"string","title":"Role"},"content":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Content"}},"additionalProperties":false,"type":"object","required":["role"],"title":"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"},"type":"array","title":"Choices"},"usage":{"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"}},"additionalProperties":false,"type":"object","required":["model","choices","usage"],"title":"ChatCompletionResponse"}},"text/event-stream":{"schema":{"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":{"properties":{"index":{"type":"integer","title":"Index"},"delta":{"properties":{"role":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Role"},"content":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Content"}},"additionalProperties":false,"type":"object","title":"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"},"type":"array","title":"Choices"},"usage":{"anyOf":["$38",{"type":"null"}]}},"additionalProperties":false,"type":"object","required":["model","choices"],"title":"ChatCompletionStreamResponse"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid","maxLength":36}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string","format":"^[a-zA-Z-]{1,64}$","maxLength":64}}}},"422":{"description":"Validation failed, provided entity could not be processed.","content":{"application/json":{"schema":{"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"},"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":"$40","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":"$4b","node.js":"$4c","curl":"stream=<%- request.stream %>\n\nif [ \"$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?

`), \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"},"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"}}},"required":true},"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"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":{"properties":{"index":{"type":"integer","title":"Index"},"message":{"properties":{"role":{"type":"string","title":"Role"},"content":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Content"}},"additionalProperties":false,"type":"object","required":["role"],"title":"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"},"type":"array","title":"Choices"},"usage":{"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"}},"additionalProperties":false,"type":"object","required":["model","choices","usage"],"title":"ChatCompletionResponse"}},"text/event-stream":{"schema":{"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":{"properties":{"index":{"type":"integer","title":"Index"},"delta":{"properties":{"role":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Role"},"content":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Content"}},"additionalProperties":false,"type":"object","title":"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"},"type":"array","title":"Choices"},"usage":{"anyOf":["$13b",{"type":"null"}]}},"additionalProperties":false,"type":"object","required":["model","choices"],"title":"ChatCompletionStreamResponse"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid","maxLength":36}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string","format":"^[a-zA-Z-]{1,64}$","maxLength":64}}}},"422":{"description":"Validation failed, provided entity could not be processed.","content":{"application/json":{"schema":{"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"},"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":"$143","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":"$14e","node.js":"$14f","curl":"stream=<%- request.stream %>\n\nif [ \"$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":"$150"}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid","maxLength":36}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string","format":"^[a-zA-Z-]{1,64}$","maxLength":64}}}},"422":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":"$143","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":"$143","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":"$150","ChatCompletionResponseChoice":"$158","ChatCompletionResponseStreamChoice":"$16f","ChatCompletionStreamResponse":"$187","ChatMessage":"$15b","DeltaMessage":"$172","ErrorResponse":"$143","HTTPValidationError":{"properties":{"detail":{"items":{"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"},"type":"array","title":"Detail"}},"type":"object","title":"HTTPValidationError"},"ImageURL":"$193","NIMLLMChatCompletionMessage":"$197","NIMLLMChatCompletionRequest":"$1af","NIMVLMChatCompletionContentPartImage":"$1a3","NIMVLMChatCompletionContentPartText":"$1a8","Role":"$19b","UsageInfo":"$13b","ValidationError":"$1d6"}}},"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"},"artifact":{"artifact":{"name":"llama-4-scout-17b-16e-instruct","displayName":"llama-4-scout-17b-16e-instruct","publisher":"meta","shortDescription":"A multimodal, multilingual 16 MoE model with 17B parameters.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/llama-4-scout-17b-16e-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":"2025-04-05T21:45:08.750Z","description":"$1e0","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","updatedDate":"2025-04-06T05:31:52.218Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"4db835b1-8885-416a-b5f4-58dbc4d3d30f"}},"openApiSpec":"$1e1"},{"endpointSpec":{"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":{"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":{"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"},"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"}}},"required":true},"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"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":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"message":{"allOf":["$23e"],"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"},"title":"Choices","type":"array"},"usage":{"allOf":[{"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"}],"description":"Usage statistics for the completion request."}},"required":["id","choices","usage"],"title":"ChatCompletion","type":"object"}},"text/event-stream":{"schema":{"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":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"delta":{"allOf":["$23e"],"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"},"title":"Choices","type":"array"}},"required":["id","choices"],"title":"ChatCompletionChunk","type":"object"}}}},"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":{"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"},"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":"$247","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":"$250","langChain":"from langchain_nvidia_ai_endpoints import ChatNVIDIA\n\nclient = ChatNVIDIA(\n model=\"<%- request.model %>\",\n api_key=\"$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":"$251","curl":"$252"},"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":"$247","ChatCompletion":"$253","ChatCompletionChunk":"$271","ChatRequest":"$283","Choice":"$257","ChoiceChunk":"$275","Message":"$23e","Usage":"$267"}}},"namespace":"qc69jvmznzxy","updatedDate":"2025-04-18T18:41:54.866Z","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":false,"playground":{"type":"chatWithThinking"},"deploy":[{"label":"Linux with Docker","filename":"linux.md","contents":"$297"}]},"artifactName":"deepseek-r1"},"artifact":{"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":"$298","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","updatedDate":"2025-04-18T18:41:54.461Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"96d5219a-d90e-435a-8d06-6906c2cb5772"}},"openApiSpec":"$299"},null,{"endpointSpec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for meta/llama-3.3-70b-instruct","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/meta-llama-3_3-70b-instruct 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://www.llama.com/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":{"additionalProperties":false,"properties":{"model":{"type":"string","title":"Model","default":"meta/llama-3.3-70b-instruct"},"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":{"additionalProperties":false,"properties":{"role":{"description":"The role of the message author.","enum":["system","context","user","assistant","tool"],"title":"Role","type":"string"},"content":{"description":"The contents of the message.","title":"Content","anyOf":[{"type":"string"},{"type":"null"}]},"tool_call_id":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Tool Call Id","description":"The id of the tool call."},"tool_calls":{"anyOf":[{"items":{"properties":{"id":{"type":"string","title":"Id"},"type":{"type":"string","enum":["function"],"const":"function","title":"Type","default":"function"},"function":{"properties":{"name":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Name"},"arguments":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Arguments"}},"additionalProperties":false,"type":"object","required":["name","arguments"],"title":"FunctionCall"}},"additionalProperties":false,"type":"object","required":["function"],"title":"ToolCall"},"type":"array"},{"type":"null"}],"title":"Tool Calls","description":"The tool(s) called by the model."}},"required":["role","content"],"title":"Message","type":"object"},"title":"Messages","type":"array"},"temperature":{"default":0.2,"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"},"tools":{"anyOf":[{"items":{"properties":{"type":{"type":"string","enum":["function"],"const":"function","title":"Type","default":"function"},"function":{"properties":{"name":{"type":"string","title":"Name"},"description":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Description"},"parameters":{"anyOf":[{"type":"object"},{"type":"null"}],"title":"Parameters"}},"additionalProperties":false,"type":"object","required":["name"],"title":"FunctionDefinition"}},"additionalProperties":false,"type":"object","required":["function"],"title":"ChatCompletionToolsParam"},"type":"array"},{"type":"null"}],"title":"Tools"},"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":1024,"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"}}},"required":true},"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"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":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"message":{"allOf":["$2ce"],"description":"A chat completion message generated by the model.","examples":[{"content":"Ah, Paris, the City of Light! There are so many amazing things to see and do in this beautiful city ...","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length","tool_calls"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached.","examples":["stop"],"title":"Finish Reason"}},"required":["index","message"],"title":"Choice","type":"object"},"title":"Choices","type":"array"},"usage":{"allOf":[{"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"}],"description":"Usage statistics for the completion request."}},"required":["id","choices","usage"],"title":"ChatCompletion","type":"object"}},"text/event-stream":{"schema":{"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":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"delta":{"allOf":["$2ce"],"description":"A chat completion delta generated by streamed model responses.","examples":[{"content":"Ah,","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length","tool_calls"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached. Will be `null` if the model has not finished generating.","title":"Finish Reason"}},"required":["index","delta"],"title":"ChoiceChunk","type":"object"},"title":"Choices","type":"array"}},"required":["id","choices"],"title":"ChatCompletionChunk","type":"object"}}}},"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":{"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"},"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":"$2f0","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":"Write a limerick about the wonders of GPU computing.","requestJson":"{\n \"model\": \"meta/llama-3.3-70b-instruct\",\n \"messages\": [\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 \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"meta/llama-3.3-70b-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"The python functions...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"},{"name":"Tell me about Dumbledore.","requestJson":"$2f9","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"meta/llama-3.3-70b-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"At NVIDIA's GPU Technology Conference (GTC)...\"\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 is the weather in Santa Clara, CA?","requestJson":"$2fa","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"meta/llama-3.3-70b-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"At NVIDIA's GPU Technology Conference (GTC)...\"\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":"$2fb","langChain":"from langchain_nvidia_ai_endpoints import ChatNVIDIA\n\nclient = ChatNVIDIA(\n model=\"<%- request.model %>\",\n api_key=\"$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 \n","node.js":"$2fc","curl":"$2fd"},"response":"{\n \"id\": \"chatcmpl-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"meta/llama-3.3-70b-instruct\",\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":"$2f0","ChatCompletion":"$2fe","ChatCompletionChunk":"$31c","ChatRequest":"$32e","Choice":"$302","ChoiceChunk":"$320","Message":"$2ce","ToolCall":"$2dd","FunctionCall":"$2e2","ChatCompletionToolsParam":"$33a","ChatCompletionNamedFunction":{"properties":{"name":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Name"}},"additionalProperties":false,"type":"object","required":["name"],"title":"ChatCompletionNamedFunction"},"ChatCompletionNamedToolChoiceParam":{"properties":{"function":"$357","type":{"type":"string","enum":["function"],"const":"function","title":"Type","default":"function"}},"additionalProperties":false,"type":"object","required":["function"],"title":"ChatCompletionNamedToolChoiceParam"},"FunctionDefinition":"$33e","Usage":"$312"}}},"namespace":"qc69jvmznzxy","updatedDate":"2025-04-15T23:48:57.508Z","nvcfFunctionId":"84eb5de1-166b-4bb4-a01b-4f51bd90aa52","createdDate":"2024-12-06T17:04:43.514Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/meta-llama-3_3-70b-instruct","termsOfUse":"GOVERNING TERMS: This 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: 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/","nim_available_override_url":"https://catalog.ngc.nvidia.com/orgs/nim/teams/meta/containers/llama-3.3-70b-instruct"},"playground":{"type":"chatWithTools"},"deploy":[{"label":"Linux with Docker","filename":"linux.md","contents":"$35e"}]},"artifactName":"llama-3_3-70b-instruct"},"artifact":{"artifact":{"name":"llama-3_3-70b-instruct","displayName":"llama-3.3-70b-instruct","publisher":"meta","shortDescription":"Advanced LLM for reasoning, math, general knowledge, and function calling","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/llama-3_3-70b-instruct.jpg","labels":["Instruction following","Math","Reasoning","Text-to-Text","Code Generation"],"attributes":[{"key":"AVAILABLE","value":"true"},{"key":"PREVIEW","value":"false"}],"artifactType":"ENDPOINT","canGuestDownload":true,"createdDate":"2024-12-06T17:04:43.078Z","description":"$35f","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","updatedDate":"2025-04-15T23:48:57.098Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"e8a5184b-d73a-41fd-bfc4-4fb8886accb0"}},"openApiSpec":"$360"},null,{"endpointSpec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for nvidia/embed-qa-4","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/nvidia-embed-qa-4 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":"CC-BY-NC-4.0","url":"https://spdx.org/licenses/CC-BY-NC-4.0"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1"}],"paths":{"/embeddings":{"post":{"tags":["Embeddings"],"summary":"Creates an embedding vector from the input text.","operationId":"create_embedding","requestBody":{"required":true,"content":{"application/json":{"schema":{"type":"object","properties":{"input":{"description":"Input text to embed. Max length depends on model.","oneOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"minLength":1,"maxLength":4096,"title":"Input"},"model":{"type":"string","description":"ID of the embedding model.","example":"nvidia/embed-qa-4","title":"Model"},"input_type":{"type":"string","enum":["passage","query"],"description":"nvidia/embed-qa-4 and E5 models operate in `passage` or `query` mode, and thus require the `input_type` parameter. `passage` is used when generating embeddings during indexing. `query` is used when generating embeddings during querying. It is very important to use the correct `input_type`. Failure to do so will result in large drops in retrieval accuracy. As an alternative, it is possible to add the `-query` or `-passage` suffix to the `model` parameter like `nvidia/embed-qa-4-query` and not use the `input_type` field at all for OpenAI API compliance. Please note that the GTE model _does not_ accept the `input_type` parameter since both the query and passage are processed in the same way.","title":"Input Type"},"encoding_format":{"type":"string","description":"The format to return the embeddings in.","enum":["float","base64"],"default":"float","title":"Encoding Format"},"truncate":{"type":"string","description":"Specifies how inputs longer than the maximum token length of the model are handled. Passing `START` discards the start of the input. `END` discards the end of the input. In both cases, input is discarded until the remaining input is exactly the maximum input token length for the model. If `NONE` is selected, when the input exceeds the maximum input token length an error will be returned.","enum":["NONE","START","END"],"default":"NONE","title":"Truncate"},"user":{"type":"string","description":"Not implemented, but provided for API compliance. This field is ignored.","title":"User"}},"required":["input","model"]}}}},"x-nvai-meta":{"name":"Create Text Embedding","description":"Generates an embedding vector from the provided text\nusing a specified model. The embedding can be returned\nin either float array or base64-encoded format.\n","path":"create","examples":[{"name":"Embedding vector for text input","requestJson":"{\n \"input\": \"What is the capital of France?\",\n \"model\": \"nvidia/embed-qa-4\",\n \"input_type\": \"query\",\n \"encoding_format\": \"float\",\n \"truncate\": \"NONE\"\n}\n","responseJson":"$39d"}],"templates":[{"title":"Synchronous requests","requestEjs":{"curl":"curl -X POST https://integrate.api.nvidia.com/v1/embeddings \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n -d '{\n \"input\": [\"<%- request.input.replaceAll('\"', '\\\\\"').replaceAll(\"'\", \"'\\\"'\\\"'\") %>\"],\n \"model\": \"nvidia/embed-qa-4\",\n \"input_type\": \"<%- request.input_type %>\",\n \"encoding_format\": \"<%- request.encoding_format %>\",\n \"truncate\": \"<%- request.truncate %>\"\n }'\n","python":"from openai import OpenAI\n\nclient = OpenAI(\n api_key=\"$NVIDIA_API_KEY\",\n base_url=\"https://integrate.api.nvidia.com/v1\"\n)\n\nresponse = client.embeddings.create(\n input=[<%- JSON.stringify(request.input) %>],\n model=\"nvidia/embed-qa-4\",\n encoding_format=\"<%- request.encoding_format %>\",\n extra_body={\"input_type\": \"<%- request.input_type %>\", \"truncate\": \"<%- request.truncate %>\"}\n)\n\nprint(response.data[0].embedding)\n","langchain":"from langchain_nvidia_ai_endpoints import NVIDIAEmbeddings\n\nclient = NVIDIAEmbeddings(\n model=\"NV-Embed-QA\", \n api_key=\"$NVIDIA_API_KEY\", \n truncate=\"<%- request.truncate %>\", \n )\n\nembedding = client.embed_query(<%- JSON.stringify(request.input) %>)\nprint(embedding)\n"},"response":"$39e"}]},"responses":{"200":{"description":"Successful response","content":{"application/json":{"schema":{"type":"object","properties":{"object":{"type":"string","example":"list"},"data":{"type":"array","items":{"type":"object","properties":{"object":{"type":"string","example":"embedding"},"embedding":{"oneOf":[{"type":"array","items":{"type":"number"},"description":"The embedding vector as a list of floats. The length of the vector depends on the model."},{"type":"string","description":"The embedding vector as a Base64 string. The length of the string depends on the model."}]},"index":{"type":"integer","description":"The index of the embedding in the list of embeddings."}},"required":["object","embedding","index"]}},"model":{"type":"string","example":"nre-001"},"usage":{"type":"object","description":"Not implemented, but provided for API compliance. This field will contain zeros.","properties":{"prompt_tokens":{"type":"integer","example":0},"total_tokens":{"type":"integer","example":0}}}}}}}},"400":{"description":"Bad request","content":{"application/json":{"schema":{"type":"object","properties":{"object":{"type":"string"},"message":{"type":"string"},"detail":{"type":"object","additionalProperties":true},"type":{"type":"string"}}}}}}}}}},"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"EmbeddingObject":"$39f"}}},"namespace":"qc69jvmznzxy","updatedDate":"2025-01-17T20:00:27.769Z","nvcfFunctionId":"09c64e32-2b65-4892-a285-2f585408d118","createdDate":"2024-03-17T01:57:28.382Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/nvidia-embed-qa-4","termsOfUse":"GOVERNING TERMS: Your use of this API is governed by the NVIDIA API Trial Service Terms of Use; and the use of this model is governed by the MIT License.\n","showUnavailableBanner":false},"artifactName":"embed-qa-4"},"artifact":{"artifact":{"name":"embed-qa-4","displayName":"embed-qa-4","publisher":"nvidia","shortDescription":"GPU-accelerated generation of text embeddings used for question-answering retrieval.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/embed-qa-4.jpg","labels":["Embeddings","Retrieval Augmented Generation","Retrieval Augmented Generation","Text-to-Embedding"],"attributes":[{"key":"AVAILABLE","value":"false"},{"key":"PREVIEW","value":"true"}],"artifactType":"ENDPOINT","bias":"Field | Response\n:---------------------------------------------------------------------------------------------------|:---------------\nParticipation considerations from adversely impacted groups [protected classes](https://www.senate.ca.gov/content/protected-classes) in model design and testing: | None\nMeasures taken to mitigate against unwanted bias: | None","canGuestDownload":true,"createdDate":"2024-03-17T01:57:28.083Z","description":"$3a9","explainability":"$3aa","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","privacy":"$3ab","safetyAndSecurity":"| Field | Response |\n|:-------------------|:---------|\n|Model Application(s): | Text Embedding for Retrieval |\n|Describe the life-critical impact (if present). | Not Applicable |\n|Use Case Restrictions:| Evaluation license for Non-Commerical Use Only. |\n|Model and dataset restrictions:| The Principle of least privilege (PoLP) is applied limiting access for dataset generation and model development. Restrictions enforce dataset access during training, and dataset license constraints adhered to. |","updatedDate":"2025-01-17T20:00:27.231Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"862287c6-2325-4a76-a355-b0c99d667b43"}},"openApiSpec":"$3ac"},{"endpointSpec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for qwen/qwen2.5-coder-32b-instruct","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/qwen-qwen2_5-coder-32b-instruct 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":"Apache 2.0","url":"https://apache.org/licenses/LICENSE-2.0"}},"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":{"additionalProperties":false,"properties":{"model":{"type":"string","title":"Model","default":"qwen/qwen2.5-coder-32b-instruct"},"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":{"additionalProperties":false,"properties":{"role":{"description":"The role of the message author.","enum":["system","context","user","assistant"],"title":"Role","type":"string"},"content":{"description":"The contents of the message.","title":"Content","type":"string"}},"required":["role","content"],"title":"Message","type":"object"},"title":"Messages","type":"array"},"temperature":{"default":0.2,"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,"exclusiveMinimum":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"},"max_tokens":{"default":1024,"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":4000,"minimum":1,"title":"Max Tokens","type":"integer"},"seed":{"anyOf":[{"maximum":18446744073709552000,"minimum":0,"type":"integer"},{"type":"null"}],"default":null,"description":"If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.","examples":[42],"title":"Seed"},"stream":{"default":false,"description":"If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events (SSE) as they become available (JSON responses are prefixed by `data: `), with the stream terminated by a `data: [DONE]` message.","title":"Stream","type":"boolean"},"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"}}},"required":true},"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"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":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"message":{"allOf":["$3eb"],"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"},"title":"Choices","type":"array"},"usage":{"allOf":[{"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"}],"description":"Usage statistics for the completion request."}},"required":["id","choices","usage"],"title":"ChatCompletion","type":"object"}},"text/event-stream":{"schema":{"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":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"delta":{"allOf":["$3eb"],"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"},"title":"Choices","type":"array"}},"required":["id","choices"],"title":"ChatCompletionChunk","type":"object"}}}},"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":{"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"},"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":"$3f1","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":"Write a limerick about the wonders of GPU computing.","requestJson":"{\n \"model\": \"qwen/qwen2.5-coder-32b-instruct\",\n \"messages\": [\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 \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"qwen/qwen2.5-coder-32b-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"The python functions...\"\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\": \"qwen/qwen2.5-coder-32b-instruct\",\n \"messages\": [\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 \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"qwen/qwen2.5-coder-32b-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"At NVIDIA's GPU Technology Conference (GTC)...\"\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 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","langChain":"from langchain_nvidia_ai_endpoints import ChatNVIDIA\n\nclient = ChatNVIDIA(\n model=\"<%- request.model %>\",\n api_key=\"$NVIDIA_API_KEY\", \n temperature=<%- request.temperature %>,\n top_p=<%- request.top_p %>,\n max_tokens=<%- request.max_tokens %>,\n)\n<% if (request.stream) { %>\nfor chunk in client.stream(<%- JSON.stringify(request.messages) %>): \n print(chunk.content, end=\"\")\n<% } else { %>\nresponse = client.invoke(<%- JSON.stringify(request.messages) %>)\nprint(response.content)\n<% } %>\n","node.js":"import OpenAI from 'openai';\n\nconst openai = new OpenAI({\n apiKey: '$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 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\": \"qwen/qwen2.5-coder-32b-instruct\",\n \"messages\": <%- JSON.stringify(request.messages).replaceAll(\"'\", \"'\\\"'\\\"'\") %>,\n \"temperature\": <%- request.temperature %>, \n \"top_p\": <%- request.top_p %>,\n \"max_tokens\": <%- request.max_tokens %>,\n \"stream\": <%- request.stream %> \n }'\n"},"response":"{\n \"id\": \"chatcmpl-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"qwen/qwen2.5-coder-32b-instruct\",\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":"$3f1","ChatCompletion":"$3fa","ChatCompletionChunk":"$418","ChatRequest":"$42a","Choice":"$3fe","ChoiceChunk":"$41c","Message":"$3eb","Usage":"$40e"}}},"namespace":"qc69jvmznzxy","nvcfFunctionId":"f3160eb9-d42a-46a6-b7da-aad54d4b2134","createdDate":"2024-12-20T16:43:06.694Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/qwen-qwen2_5-coder-32b-instruct","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 Open Model License Agreement. Additional Information: Apache License Version 2.0\n","showUnavailableBanner":false,"playground":{"type":"chat"}},"artifactName":"qwen2_5-coder-32b-instruct"},"artifact":{"artifact":{"name":"qwen2_5-coder-32b-instruct","displayName":"qwen2.5-coder-32b-instruct","publisher":"qwen","shortDescription":"Advanced LLM for code generation, reasoning, and fixing across popular programming languages.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/qwen2_5-coder-32b-instruct.jpg","labels":["code completion","code generation","text-to-code"],"attributes":[{"key":"AVAILABLE","value":"false"},{"key":"PREVIEW","value":"true"}],"artifactType":"ENDPOINT","canGuestDownload":true,"createdDate":"2024-12-20T16:43:06.305Z","description":"$441","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","updatedDate":"2024-12-20T16:43:06.305Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"c1141f20-5983-4af1-8108-d5dda9d84dac"}},"openApiSpec":"$442"}]}}],["$","$L16",null,{"parallelRouterKey":"top","segmentPath":["children","(app-bar-layout)","children","explore","top"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L18",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":"$undefined","notFoundStyles":"$undefined"}]]}]}],["$","div",null,{"className":"-mx-4 -mt-4 p-4 md:-mx-8 md:p-8","children":["$","div",null,{"className":"mx-auto flex max-w-[1600px]","children":[["$","div",null,{"className":"hidden w-[220px] md:block","children":["$","$L474",null,{"initialData":{"models":[{"title":"Reasoning","config":"/reasoning"},{"title":"Vision","config":"/vision"},{"title":"Visual Design","config":"/visual-design"},{"title":"Retrieval","config":"/retrieval"},{"title":"Speech","config":"/speech"},{"title":"Biology","config":"/biology"},{"title":"Simulation","config":"/simulation"},{"title":"Climate & Weather","config":"/climate-weather"},{"title":"Safety & Moderation","config":"/safety-moderation"}],"industries":[{"title":"Automotive","config":"/automotive"},{"title":"Gaming","config":"/gaming"},{"title":"Healthcare","config":"/healthcare"},{"title":"Industrial","config":"/industrial"},{"title":"Robotics","config":"/robotics"}]}}]}],["$","div",null,{"className":"flex w-full min-w-0 flex-1 flex-col border-n700 md:border-l md:pl-8","children":["$","$L16",null,{"parallelRouterKey":"children","segmentPath":["children","(app-bar-layout)","children","explore","children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L18",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":"$undefined","notFoundStyles":"$undefined"}]}]]}]}]]