4b:I[510592,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/434amnen8yqdi.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/2tbc_4m20jg4-.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/295ffwyuqa4b6.js"],"PlaygroundContextProvider"] 4c:T3850,# Kimi-K2-Instruct ## Description Kimi K2 Instruct is a state-of-the-art mixture-of-experts (MoE) language model with 32 billion activated parameters and 1 trillion total parameters. Trained with the Muon optimizer, Kimi K2 achieves exceptional performance across frontier knowledge, reasoning, and coding tasks while being meticulously optimized for agentic capabilities. *This model is ready for commercial/non-commercial use.* --- ## Third-Party Community Consideration: This model is not owned or developed by NVIDIA. This model has been developed and built to a third-party's requirements for this application and use case; see link to Non-NVIDIA [Kimi-K2-Instruct Model Card](https://huggingface.co/moonshotai/Kimi-K2-Instruct) --- ## License and Terms of Use: **GOVERNING TERMS:** This trial service is governed by the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). Use of this model is governed by the [NVIDIA Community Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-community-models-license/). Additional Information: [Modified MIT License](https://huggingface.co/moonshotai/Kimi-K2-Instruct/blob/main/LICENSE). --- ## Deployment Geography: Global --- ## Use Case: This model is designed for agentic AI and tool use, including advanced code generation, complex problem-solving, and multilingual applications. It can be used for building autonomous agents that can interact with external systems and APIs, for multi-step reasoning tasks, mathematical problem-solving, and analytical workflows. **Key Features** - Large-Scale Training: Pre-trained a 1T parameter MoE model on 15.5T tokens with zero training instability. - MuonClip Optimizer: We apply the Muon optimizer to an unprecedented scale, and develop novel optimization techniques to resolve instabilities while scaling up. - Agentic Intelligence: Specifically designed for tool use, reasoning, and autonomous problem-solving. --- ## Release Date: **Build.NVIDIA.com** 07/2025 via [link](https://build.nvidia.com/moonshotai/kimi-k2-instruct)
**Huggingface** 07/12/2025 via [link](https://huggingface.co/moonshotai/Kimi-K2-Instruct) --- ## Reference(s): **References:** * [moonshotai/Kimi-K2-Instruct - Simon Willison's Weblog](https://simonwillison.net/2025/Jul/11/kimi-k2/) * [Kimi-k2 : The best Open-Sourced AI model with 1 Trillion params | by Mehul Gupta - Medium](https://medium.com/data-science-in-your-pocket/kimi-k2-the-best-open-sourced-ai-model-with-1-trillion-params-c647779496a5) * [How to Run Kimi K2 Inside Claude Code: The Ultimate Open-Source AI Coding Combo](https://annie-wellington.medium.com/how-to-run-kimi-k2-inside-claude-code-the-ultimate-open-source-ai-coding-combo-b13df29b019e) --- ## Model Architecture: **Architecture Type:** Transformer
- **Network Architecture:** Mixture-of-Experts (MoE)
- **Total Parameters:** 1T
- **Active Parameters:** 32B
- **Number of Layers (Dense layer included):** 61
- **Attention Hidden Dimension:** 7168
- **MoE Hidden Dimension (per Expert):** 2048
- **Number of Attention Heads:** 64
- **Number of Experts:** 384
- **Selected Experts per Token:** 8
- **Number of Shared Experts:** 1
- **Vocabulary Size:** 160K
- **Context Length:** 128K
- **Attention Mechanism:** MLA
- **Activation Function:** SwiGLU
- **Base Model:** Kimi-K2-Base
### Input: **Input Types:** Text
**Input Formats:** String
**Input Parameters:** One Dimensional (1D)
**Other Input Properties:** The model has a context window of up to 128,000 tokens.
**Input Context Length (ISL):** 128K
### Output: **Output Format:** String
**Output Parameters:** One Dimensional (1D)
**Other Output Properties:** Not applicable.
--- __Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA's hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.__ --- ## Software Integration: **Runtime Engines:** - NVIDIA NeMo
- NVIDIA Riva
**Supported Hardware:** - **NVIDIA Blackwell:** B100, B200, GB200
- **NVIDIA Hopper:** H100, H200
**Operating Systems:** Linux --- ## Model Version(s): Kimi-K2-Instruct v1.0 --- ## Training, Testing, and Evaluation Datasets: ### Training Dataset **Training Data Collection:** Undisclosed
**Training Labeling:** Undisclosed
**Training Properties:** Trained on 15.5 trillion tokens.
### Testing Dataset **Testing Data Collection:** Undisclosed
**Testing Labeling:** Undisclosed
**Testing Properties:** Undisclosed
### Evaluation Dataset **Evaluation Benchmark Score:** * LiveCodeBench: 53.7% Pass@1 * SWE-bench Verified: 65.8% single-attempt accuracy * MMLU: 89.5% exact match * Tau2 retail tasks: 70.6% Avg@4
**Evaluation Data Collection:** Undisclosed
**Evaluation Labeling:** Undisclosed
**Evaluation Properties:** LiveCodeBench, SWE-bench, MMLU, Tau2 #### Evaluation Results | Benchmark | Metric | Kimi K2 Instruct | DeepSeek-V3-0324 | Qwen3-235B-A22B (non-thinking) | Claude Sonnet 4 (w/o extended thinking) | Claude Opus 4 (w/o extended thinking) | GPT-4.1 | Gemini 2.5 Flash Preview (05-20) | | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | | **Coding Tasks** | | | | | | | | | | LiveCodeBench v6(Aug 24 - May 25) | Pass@1 | **53.7** | 46.9 | 37.0 | 48.5 | 47.4 | 44.7 | 44.7 | | OJBench | Pass@1 | **27.1** | 24.0 | 11.3 | 15.3 | 19.6 | 19.5 | 19.5 | | MultiPL-E | Pass@1 | **85.7** | 83.1 | 78.2 | 88.6 | **89.6** | 86.7 | 85.6 | | SWE-bench Verified (Agentless Coding) | Single Patch w/o Test (Acc) | **51.8** | 36.6 | 39.4 | 50.2 | **53.0** | 40.8 | 32.6 | | SWE-bench Verified (Agentic Coding) | Single Attempt (Acc) | **65.8** | 38.8 | 34.4 | **72.7*** | 72.5* | 54.6 | — | | SWE-bench Verified (Agentic Coding) | Multiple Attempts (Acc) | **71.6** | — | — | **80.2** | 79.4* | — | — | | SWE-bench Multilingual (Agentic Coding) | Single Attempt (Acc) | **47.3** | 25.8 | 20.9 | **51.0** | — | 31.5 | — | | TerminalBench | Inhouse Framework (Acc) | **30.0** | — | — | 35.5 | **43.2** | 8.3 | — | | TerminalBench | Terminus (Acc) | **25.0** | 16.3 | 6.6 | — | — | **30.3** | 16.8 | | Aider-Polyglot | Acc | 60.0 | 55.1 | **61.8** | 56.4 | **70.7** | 52.4 | 44.0 | | **Tool Use Tasks** | | | | | | | | | | Tau2 retail | Avg@4 | **70.6** | 69.1 | 57.0 | 75.0 | **81.8** | 74.8 | 64.3 | | Tau2 airline | Avg@4 | **56.5** | 39.0 | 26.5 | 55.5 | **60.0** | 54.5 | 42.5 | | Tau2 telecom | Avg@4 | **65.8** | 32.5 | 22.1 | 45.2 | 57.0 | 38.6 | 16.9 | | AceBench | Acc | **76.5** | 72.7 | 70.5 | 76.2 | 75.6 | **80.1** | 74.5 | | **Math & STEM Tasks** | | | | | | | | | | AIME 2024 | Avg@64 | **69.6** | 59.4* | 40.1* | 43.4 | 48.2 | 46.5 | 61.3 | | AIME 2025 | Avg@64 | **49.5** | 46.7 | 24.7* | 33.1* | 33.9* | 37.0 | 46.6 | | MATH-500 | Acc | **97.4** | 94.0* | 91.2* | 94.0 | 94.4 | 92.4 | 95.4 | | HMMT 2025 | Avg@32 | **38.8** | 27.5 | 11.9 | 15.9 | 15.9 | 19.4 | 34.7 | | CNMO 2024 | Avg@16 | 74.3 | **74.7** | 48.6 | 60.4 | 57.6 | 56.6 | **75.0** | | PolyMath-en | Avg@4 | **65.1** | 59.5 | 51.9 | 52.8 | 49.8 | 54.0 | 49.9 | | ZebraLogic | Acc | **89.0** | 84.0 | 37.7* | 73.7 | 59.3 | 58.5 | 57.9 | | AutoLogi | Acc | **89.5** | 88.9 | 83.3 | **89.8** | 86.1 | 88.2 | 84.1 | | GPQA-Diamond | Avg@8 | **75.1** | 68.4* | 62.9* | 70.0* | 74.9* | 66.3 | 68.2 | | SuperGPQA | Acc | **57.2** | 53.7 | 50.2 | 55.7 | 56.5 | 50.8 | 49.6 | | Humanity's Last Exam(Text Only) | - | 4.7 | 5.2 | **5.7** | 5.8 | **7.1** | 3.7 | 5.6 | | **General Tasks** | | | | | | | | | | MMLU | EM | **89.5** | 89.4 | 87.0 | 91.5 | **92.9** | 90.4 | 90.1 | | MMLU-Redux | EM | **92.7** | 90.5 | 89.2 | 93.6 | **94.2** | 92.4 | 90.6 | | MMLU-Pro | EM | 81.1 | **81.2*** | 77.3 | 83.7 | **86.6** | 81.8 | 79.4 | | IFEval | Prompt Strict | **89.8** | 81.1 | 83.2\* | 87.6 | 87.4 | 88.0 | 84.3 | | Multi-Challenge | Acc | **54.1** | 31.4 | 34.0 | 46.8 | 49.0 | 36.4 | 39.5 | | SimpleQA | Correct | **31.0** | 27.7 | 13.2 | 15.9 | 22.8 | **42.3** | 23.3 | | Livebench | Pass@1 | **76.4** | 72.4 | 67.6 | 74.8 | 74.6 | 69.8 | 67.8 | * Bold denotes global SOTA, and underlined denotes open-source SOTA. * Data points marked with \* are taken directly from the model's tech report or blog. * All metrics, except for SWE-bench Verified (Agentless), are evaluated with an 8k output token length. SWE-bench Verified (Agentless) is limited to a 16k output token length. * Kimi K2 achieves 65.8% pass@1 on the SWE-bench Verified tests with bash/editor tools (single-attempt patches, no test-time compute). It also achieves a 47.3% pass@1 on the SWE-bench Multilingual tests under the same conditions. Additionally, we report results on SWE-bench Verified tests (71.6%) that leverage parallel test-time compute by sampling multiple sequences and selecting the single best via an internal scoring model. * To ensure the stability of the evaluation, we employed avg@k on the AIME, HMMT, CNMO, PolyMath-en, GPQA-Diamond, EvalPlus, Tau2. * Some data points have been omitted due to prohibitively expensive evaluation costs. --- ## Inference **Acceleration Engine:** vLLM
**Test Hardware:** NVIDIA DGX B200
--- ## Additional Details ### Deployment > You can access Kimi K2's API on https://platform.moonshot.ai , we provide OpenAI/Anthropic-compatible API for you. > > The Anthropic-compatible API maps temperature by `real_temperature = request_temperature * 0.6` for better compatible with existing applications. Our model checkpoints are stored in the block-fp8 format, you can find it on [Huggingface](https://huggingface.co/moonshotai/Kimi-K2-Instruct). Currently, Kimi-K2 is recommended to run on the following inference engines: * vLLM * SGLang * KTransformers * TensorRT-LLM Deployment examples for vLLM and SGLang can be found in the [Model Deployment Guide](https://huggingface.co/moonshotai/Kimi-K2-Instruct/blob/main/docs/deploy_guidance.md). --- ### Model Usage Once the local inference service is up, you can interact with it through the chat endpoint: ```python def simple_chat(client: OpenAI, model_name: str): messages = [ {"role": "system", "content": "You are Kimi, an AI assistant created by Moonshot AI."}, {"role": "user", "content": [{"type": "text", "text": "Please give a brief self-introduction."}]}, ] response = client.chat.completions.create( model=model_name, messages=messages, stream=False, temperature=0.6, max_tokens=256 ) print(response.choices[0].message.content) ``` > [!NOTE] > The recommended temperature for Kimi-K2-Instruct is `temperature = 0.6`. > If no special instructions are required, the system prompt above is a good default. --- ### Tool Calling Kimi-K2-Instruct has strong tool-calling capabilities. To enable them, you need to pass the list of available tools in each request, then the model will autonomously decide when and how to invoke them. The following example demonstrates calling a weather tool end-to-end: ```python # Your tool implementation def get_weather(city: str) -> dict: return {"weather": "Sunny"} # Tool schema definition tools = [{ "type": "function", "function": { "name": "get_weather", "description": "Retrieve current weather information. Call this when the user asks about the weather.", "parameters": { "type": "object", "required": ["city"], "properties": { "city": { "type": "string", "description": "Name of the city" } } } } }] # Map tool names to their implementations tool_map = { "get_weather": get_weather } def tool_call_with_client(client: OpenAI, model_name: str): messages = [ {"role": "system", "content": "You are Kimi, an AI assistant created by Moonshot AI."}, {"role": "user", "content": "What's the weather like in Beijing today? Use the tool to check."} ] finish_reason = None while finish_reason is None or finish_reason == "tool_calls": completion = client.chat.completions.create( model=model_name, messages=messages, temperature=0.6, tools=tools, # tool list defined above tool_choice="auto" ) choice = completion.choices[0] finish_reason = choice.finish_reason if finish_reason == "tool_calls": messages.append(choice.message) for tool_call in choice.message.tool_calls: tool_call_name = tool_call.function.name tool_call_arguments = json.loads(tool_call.function.arguments) tool_function = tool_map[tool_call_name] tool_result = tool_function(**tool_call_arguments) print("tool_result:", tool_result) messages.append({ "role": "tool", "tool_call_id": tool_call.id, "name": tool_call_name, "content": json.dumps(tool_result) }) print("-" * 100) print(choice.message.content) ``` The `tool_call_with_client` function implements the pipeline from user query to tool execution. This pipeline requires the inference engine to support Kimi-K2’s native tool-parsing logic. For streaming output and manual tool-parsing, see the [Tool Calling Guide](https://huggingface.co/moonshotai/Kimi-K2-Instruct/blob/main/docs/tool_call_guidance.md). --- ## Ethical Considerations NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/)4d:T506,from openai import OpenAI client = OpenAI( base_url = "https://integrate.api.nvidia.com/v1", api_key = "$NVIDIA_API_KEY" ) <% if (request.tools) { %> completion = client.chat.completions.create( model="<%- request.model %>", messages=<%- JSON.stringify(request.messages) %>, temperature=<%- request.temperature %>, top_p=<%- request.top_p %>, max_tokens=<%- request.max_tokens %>, stream=<%- request.stream?.toString()[0].toUpperCase() + request.stream?.toString().slice(1) %>, tools=<%- JSON.stringify(request.tools) %>, <% if (request.tool_choice) { %>tool_choice=<%- JSON.stringify(request.tool_choice) %><% } %> )<% } else { %> completion = client.chat.completions.create( model="<%- request.model %>", messages=<%- JSON.stringify(request.messages) %>, temperature=<%- request.temperature %>, top_p=<%- request.top_p %>, max_tokens=<%- request.max_tokens %>, stream=<%- request.stream?.toString()[0].toUpperCase() + request.stream?.toString().slice(1) %> )<% } %> <% if (request.stream) { %> for chunk in completion: if not getattr(chunk, "choices", None): continue if chunk.choices and chunk.choices[0].delta.content is not None: print(chunk.choices[0].delta.content, end="") <% } else { %> print(completion.choices[0].message) <% } %> 4e:T504,import OpenAI from 'openai'; const openai = new OpenAI({ apiKey: '$NVIDIA_API_KEY', baseURL: 'https://integrate.api.nvidia.com/v1', }) <% if (request.tools) { %> async function main() { const completion = await openai.chat.completions.create({ model: "<%- request.model %>", messages: <%- JSON.stringify(request.messages) %>, temperature: <%- request.temperature %>, top_p: <%- request.top_p %>, max_tokens: <%- request.max_tokens %>, stream: <%- request.stream %>, <% if (request.tools) { %>tools: <%- JSON.stringify(request.tools) %>,<% } %> <% if (request.tool_choice) { %>tool_choice: <%- JSON.stringify(request.tool_choice) %>,<% } %> })<% } else { %> async function main() { const completion = await openai.chat.completions.create({ model: "<%- request.model %>", messages: <%- JSON.stringify(request.messages) %>, temperature: <%- request.temperature %>, top_p: <%- request.top_p %>, max_tokens: <%- request.max_tokens %>, stream: <%- request.stream %> })<% } %> <% if (request.stream) { %> for await (const chunk of completion) { process.stdout.write(chunk.choices[0]?.delta?.content || '') } <% } else { %> process.stdout.write(completion.choices[0]?.message?.content); <% } %> } main();4f:T66f,<% if (request.tools) { %> "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\": \"moonshotai/kimi-k2-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 %> <% if (request.tools) { %>,\n \"tools\": <%- JSON.stringify(request.tools).replaceAll(\"'\", \"'\\\"'\\\"'\") %><% } %> <% if (request.tool_choice) { %>,\n \"tool_choice\": <%- JSON.stringify(request.tool_choice).replaceAll(\"'\", \"'\\\"'\\\"'\") %><% } %> }'\n"<% } else { %> "curl https://integrate.api.nvidia.com/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n -d '{\n \"model\": \"moonshotai/kimi-k2-instruct\",\n \"messages\": <%- JSON.stringify(request.messages).replaceAll(\"'\", \"'\\\"'\\\"'\") %>,\n \"temperature\": <%- request.temperature %>,\n \"top_p\": <%- request.top_p %>,\n \"max_tokens\": <%- request.max_tokens %>,\n \"stream\": <%- request.stream %> <% if (request.tools) { %>,\n \"tools\": <%- JSON.stringify(request.tools).replaceAll(\"'\", \"'\\\"'\\\"'\") %><% } %> <% if (request.tool_choice) { %>,\n \"tool_choice\": <%- JSON.stringify(request.tool_choice).replaceAll(\"'\", \"'\\\"'\\\"'\") %><% } %> }'\n"<% } %>4a:["$","$L4b",null,{"initialState":{"artifact":{"artifactType":"ENDPOINT","name":"kimi-k2-instruct","displayName":"kimi-k2-instruct","publisher":"moonshotai","shortDescription":"State-of-the-art open mixture-of-experts model with strong reasoning, coding, and agentic capabilities","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/kimi-k2-instruct.jpg","labels":["advanced reasoning","agentic","chat","cloudPartnerType:endpoint:cloud_partner_type_deepinfra","coding","nimType:endpoint:nim_type_preview","nimType:endpoint:nim_type_upgrade_available","playgroundType:endpoint:playgroundtype_chat"],"attributes":[{"key":"AVAILABLE","value":"false"},{"key":"DEPRECATION","value":"05/12/2026"},{"key":"PREVIEW","value":"true"}],"updatedDate":"2025-07-18T20:58:25.601Z","canGuestDownload":true,"createdDate":"2025-07-18T20:58:25.601Z","description":"$4c","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy"},"specAttributes":"$44:props:spec:attributes","modelPath":"/moonshotai/kimi-k2-instruct","openApiSpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for moonshotai/kimi-k2-instruct","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/moonshotai-kimi-k2-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":"MIT License","url":"https://opensource.org/license/MIT"}},"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":"moonshotai/kimi-k2-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":0.6,"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":0.9,"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":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":16384,"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":[{"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"}],"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":[{"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"}],"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":{"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: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\": \"moonshotai/kimi-k2-instruct\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"Write a limerick about the wonders of GPU computing\"\n }\n ],\n \"top_p\": 0.9,\n \"temperature\": 0.6,\n \"max_tokens\": 1024,\n \"seed\": 21,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"moonshotai/kimi-k2-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\": \"moonshotai/kimi-k2-instruct\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a helpful assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"At NVIDIA's GPU Technology Conference (GTC)...\"\n }\n ],\n \"top_p\": 0.9,\n \"temperature\": 0.6,\n \"max_tokens\": 1024,\n \"seed\": 21,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"moonshotai/kimi-k2-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":"$4d","langChain":"from langchain_nvidia_ai_endpoints import ChatNVIDIA\n\nclient = ChatNVIDIA(\n model=\"<%- request.model %>\",\n api_key=\"$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":"$4e","curl":"$4f"},"response":"{\n \"id\": \"chatcmpl-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"moonshotai/kimi-k2-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":{"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":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"message":{"allOf":[{"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"}],"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"},"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":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"delta":{"allOf":[{"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"}],"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"},"ChatRequest":{"additionalProperties":false,"properties":{"model":{"type":"string","title":"Model","default":"moonshotai/kimi-k2-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":0.6,"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":0.9,"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":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":16384,"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":[{"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"}],"description":"A chat completion message generated by the model.","examples":[{"content":"Ah, Paris, the City of Light! There are so many amazing things to see and do in this beautiful city ...","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length","tool_calls"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached.","examples":["stop"],"title":"Finish Reason"}},"required":["index","message"],"title":"Choice","type":"object"},"ChoiceChunk":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"delta":{"allOf":[{"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"}],"description":"A chat completion delta generated by streamed model responses.","examples":[{"content":"Ah,","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length","tool_calls"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached. Will be `null` if the model has not finished generating.","title":"Finish Reason"}},"required":["index","delta"],"title":"ChoiceChunk","type":"object"},"Message":{"additionalProperties":false,"properties":{"role":{"description":"The role of the message author.","enum":["system","context","user","assistant","tool"],"title":"Role","type":"string"},"content":{"description":"The contents of the message.","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"},"ToolCall":{"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"},"FunctionCall":{"properties":{"name":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Name"},"arguments":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Arguments"}},"additionalProperties":false,"type":"object","required":["name","arguments"],"title":"FunctionCall"},"ChatCompletionToolsParam":{"properties":{"type":{"type":"string","enum":["function"],"const":"function","title":"Type","default":"function"},"function":{"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"},"ChatCompletionNamedFunction":{"properties":{"name":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Name"}},"additionalProperties":false,"type":"object","required":["name"],"title":"ChatCompletionNamedFunction"},"ChatCompletionNamedToolChoiceParam":{"properties":{"function":{"properties":{"name":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Name"}},"additionalProperties":false,"type":"object","required":["name"],"title":"ChatCompletionNamedFunction"},"type":{"type":"string","enum":["function"],"const":"function","title":"Type","default":"function"}},"additionalProperties":false,"type":"object","required":["function"],"title":"ChatCompletionNamedToolChoiceParam"},"FunctionDefinition":{"properties":{"name":{"type":"string","title":"Name"},"description":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Description"},"parameters":{"anyOf":[{"type":"object"},{"type":"null"}],"title":"Parameters"}},"additionalProperties":false,"type":"object","required":["name"],"title":"FunctionDefinition"},"Usage":{"properties":{"completion_tokens":{"description":"Number of tokens in the generated completion.","examples":[25],"title":"Completion Tokens","type":"integer"},"prompt_tokens":{"description":"Number of tokens in the prompt.","examples":[9],"title":"Prompt Tokens","type":"integer"},"total_tokens":{"description":"Total number of tokens used in the request (prompt + completion).","examples":[34],"title":"Total Tokens","type":"integer"}},"required":["completion_tokens","prompt_tokens","total_tokens"],"title":"Usage","type":"object"}}}},"pageLayout":"v3"},"children":["$L50","$L51","$L52"]}]