4a: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"] 4b:T4b74,# Kimi-K2-Thinking ## Description Kimi K2 Thinking is the most capable open-source thinking model. Starting with Kimi K2 Thinking, we built it as a thinking agent that reasons step-by-step while dynamically invoking tools. It sets a new state-of-the-art on Humanity's Last Exam (HLE), BrowseComp, and other benchmarks by dramatically scaling multi-step reasoning depth and maintaining stable tool-use across 200–300 sequential calls. At the same time, Kimi K2 Thinking is a native INT4 quantization model with 256k context window, achieving lossless reductions in inference latency and GPU memory usage. *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-Thinking Model Card](https://huggingface.co/moonshotai/Kimi-K2-Thinking) --- ## 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 Open Model License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/). Additional Information: [Modified MIT License](https://huggingface.co/moonshotai/Kimi-K2-Thinking/blob/main/LICENSE). --- ## Deployment Geography: Global --- ## Use Case: This model is designed for advanced reasoning, agentic AI with deep thinking capabilities, multi-step problem-solving with tool orchestration, complex mathematical reasoning, coding with autonomous workflows, and research tasks requiring long-horizon agency. It can be used for autonomous research workflows, complex coding projects spanning hundreds of steps, mathematical problem-solving with extended reasoning, web browsing and information synthesis, and tool-orchestrated task execution. **Key Features** - Deep Thinking & Tool Orchestration: End-to-end trained to interleave chain-of-thought reasoning with function calls, enabling autonomous research, coding, and writing workflows that last hundreds of steps without drift. - Native INT4 Quantization: Quantization-Aware Training (QAT) is employed in post-training stage to achieve lossless 2x speed-up in low-latency mode. - Stable Long-Horizon Agency: Maintains coherent goal-directed behavior across up to 200–300 consecutive tool invocations, surpassing prior models that degrade after 30–50 steps. --- ## Release Date: **build.nvidia.com** 12/08/2025: Available via [link](https://build.nvidia.com/moonshotai/kimi-k2-thinking)
**Huggingface** Available via [link](https://huggingface.co/moonshotai/Kimi-K2-Thinking) --- ## Reference(s): **References:** * [Kimi K2: Open Agentic Intelligence - Tech Blog](https://www.moonshot.cn) * [Hugging Face Model Card](https://huggingface.co/moonshotai/Kimi-K2-Thinking) * [Moonshot AI Platform](https://platform.moonshot.ai) --- ## Model Architecture: **Architecture Type:** Transformer
- **Network Architecture:** Mixture-of-Experts (MoE)
- **Total Parameters:** 1T
- **Activated Parameters:** 32B
- **Number of Layers (Dense layer included):** 61
- **Number of Dense Layers:** 1
- **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:** 256K
- **Attention Mechanism:** MLA
- **Activation Function:** SwiGLU
- **Base Model:** Kimi-K2-Base
### Input: **Input Types:** Text, Tool Definitions
**Input Formats:** String, JSON
**Input Parameters:** One-Dimensional (1D)
**Other Input Properties:** The model has a context window of up to 256,000 tokens. Supports interleaved reasoning traces and tool calls.
**Input Context Length (ISL):** 256K
### Output: **Output Format:** String, JSON (for tool calls)
**Output Parameters:** One-Dimensional (1D)
**Other Output Properties:** Includes separate reasoning_content traces alongside final responses. Supports streaming and non-streaming modes.
--- __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:** - vLLM
- SGLang
- KTransformers
**Supported Hardware:** - **NVIDIA Blackwell:** B100, B200, GB200
- **NVIDIA Hopper:** H100, H200
**Operating Systems:** Linux --- ## Model Version(s): Kimi K2 Thinking v1.0 --- ## Training, Testing, and Evaluation Datasets: ### Training Dataset **Training Data Collection:** Undisclosed
**Training Labeling:** Undisclosed
**Training Properties:** Trained with Quantization-Aware Training (QAT) during post-training phase for native INT4 support.
### Testing Dataset **Testing Data Collection:** Undisclosed
**Testing Labeling:** Undisclosed
**Testing Properties:** Undisclosed
### Evaluation Dataset **Evaluation Benchmark Score:** * HLE (Text-only) with tools: 44.9% * HLE Heavy Mode: 51.0% * AIME25 with python: 99.1% * AIME25 Heavy Mode: 100.0% * HMMT25 with python: 95.1% * HMMT25 Heavy Mode: 97.5% * GPQA (no tools): 84.5% * BrowseComp with tools: 60.2% * BrowseComp-ZH with tools: 62.3% * SWE-bench Verified with tools: 71.3% * MMLU-Pro (no tools): 84.6% * LiveCodeBench: 64.8% Pass@1
**Evaluation Data Collection:** Hybrid: Human, Automated
**Evaluation Labeling:** Human
**Evaluation Properties:** HLE, AIME25, HMMT25, IMO-AnswerBench, GPQA, MMLU-Pro, MMLU-Redux, Longform Writing, HealthBench, BrowseComp, BrowseComp-ZH, Seal-0, FinSearchComp-T3, Frames, SWE-bench Verified, SWE-bench Multilingual, Multi-SWE-bench, SciCode, LiveCodeBench, Terminal-Bench #### Evaluation Results

Benchmark	Setting	^{Kimi K2 Thinking}	^{GPT-5 (High)}	^{Claude Sonnet 4.5 (Thinking)}	^{K2 0905}	^{DeepSeek-V3.2}	^Grok-4
Reasoning Tasks
HLE (Text-only)	no tools	23.9	26.3	19.8*	7.9	19.8	25.4
HLE	w/ tools	44.9	41.7*	32.0*	21.7	20.3*	41.0
HLE	heavy	51.0	42.0	-	-	-	50.7
AIME25	no tools	94.5	94.6	87.0	51.0	89.3	91.7
AIME25	w/ python	99.1	99.6	100.0	75.2	58.1*	98.8
AIME25	heavy	100.0	100.0	-	-	-	100.0
HMMT25	no tools	89.4	93.3	74.6*	38.8	83.6	90.0
HMMT25	w/ python	95.1	96.7	88.8*	70.4	49.5*	93.9
HMMT25	heavy	97.5	100.0	-	-	-	96.7
IMO-AnswerBench	no tools	78.6	76.0*	65.9*	45.8	76.0*	73.1
GPQA	no tools	84.5	85.7	83.4	74.2	79.9	87.5
Agentic Search Tasks
BrowseComp	w/ tools	60.2	54.9	24.1	7.4	40.1	-
BrowseComp-ZH	w/ tools	62.3	63.0*	42.4*	22.2	47.9	-
Seal-0	w/ tools	56.3	51.4*	53.4*	25.2	38.5*	-
FinSearchComp-T3	w/ tools	47.4	48.5*	44.0*	10.4	27.0*	-
Frames	w/ tools	87.0	86.0*	85.0*	58.1	80.2*	-
Coding Tasks
SWE-bench Verified	w/ tools	71.3	74.9	77.2	69.2	67.8	-
SWE-bench Multilingual	w/ tools	61.1	55.3*	68.0	55.9	57.9	-
Multi-SWE-bench	w/ tools	41.9	39.3*	44.3	33.5	30.6	-
SciCode	no tools	44.8	42.9	44.7	30.7	37.7	-
LiveCodeBench	no tools	64.8	64.4	60.4	49.8	60.8	-
Terminal-Bench	w/ tools	36.8	42.0	-	5.0	26.7	-
General Tasks
MMLU-Pro	no tools	84.6	87.1	87.5	81.9	85.0	-
MMLU-Redux	no tools	94.4	95.3	95.6	92.7	93.7	-
Longform Writing	no tools	73.8	71.4	79.8	62.8	72.5	-
HealthBench	no tools	58.0	67.2	44.2	43.8	46.9	-

^{• Bold denotes best score for the benchmark.}
^{• Data points marked with * are taken directly from the model's tech report or blog.}
^{• All benchmark results are reported under INT4 precision.}
^{• Heavy Mode employs an efficient parallel strategy: it first rolls out eight trajectories simultaneously, then reflectively aggregates all outputs to generate the final result.} --- ## Inference **Acceleration Engine:** vLLM, SGLang, KTransformers
**Test Hardware:** NVIDIA H100, NVIDIA A100
--- ## Additional Details ### Deployment > You can access Kimi K2 Thinking's API on https://platform.moonshot.ai , we provide OpenAI/Anthropic-compatible API for you. Currently, Kimi K2 Thinking is recommended to run on the following inference engines: * vLLM * SGLang * KTransformers Deployment examples can be found in the [Model Deployment Guide](https://huggingface.co/moonshotai/Kimi-K2-Thinking/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.OpenAI, model_name: str): messages = [ {"role": "system", "content": "You are Kimi, an AI assistant created by Moonshot AI."}, {"role": "user", "content": [{"type": "text", "text": "which one is bigger, 9.11 or 9.9? think carefully."}]}, ] response = client.chat.completions.create( model=model_name, messages=messages, stream=False, temperature=1.0, max_tokens=4096 ) print(f"k2 answer: {response.choices[0].message.content}") print("=====below is reasoning content======") print(f"reasoning content: {response.choices[0].message.reasoning_content}") ``` > [!NOTE] > The recommended temperature for Kimi K2 Thinking is `temperature = 1.0`. > If no special instructions are required, the system prompt above is a good default. --- ### Tool Calling Kimi K2 Thinking has the same tool calling settings as Kimi K2 Instruct. 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=1.0, 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 Thinking's native tool-parsing logic. For more information, see the [Tool Calling Guide](https://huggingface.co/moonshotai/Kimi-K2-Thinking/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/)4c:T68d,from openai import OpenAI import json client = OpenAI( base_url="https://integrate.api.nvidia.com/v1", api_key="$NVIDIA_API_KEY" ) completion = client.chat.completions.create( model="<%- request.model %>", messages=<%- JSON.stringify(request.messages, null, 2) %>, temperature=<%- request.temperature %>, top_p=<%- request.top_p %>, max_tokens=<%- request.max_tokens %>, stream=<%- request.stream ? 'True' : 'False' %><% if (request.tools) { %>, tools=<%- JSON.stringify(request.tools, null, 2) %><% } %><% if (request.tool_choice) { %>, tool_choice=<%- JSON.stringify(request.tool_choice) %><% } %> ) <% if (request.stream) { %> for chunk in completion: if not getattr(chunk, "choices", None): continue reasoning = getattr(chunk.choices[0].delta, "reasoning_content", None) if reasoning: print(reasoning, end="") if chunk.choices[0].delta.content: print(chunk.choices[0].delta.content, end="")<% if (request.tools) { %> if chunk.choices[0].delta.tool_calls: for tool_call in chunk.choices[0].delta.tool_calls: if tool_call.function.name: print(f"\n{tool_call.function.name}") if tool_call.function.arguments: print(tool_call.function.arguments, end="")<% } %> <% } else { %> message = completion.choices[0].message reasoning = getattr(message, "reasoning_content", None) if reasoning: print(reasoning) if message.content: print(message.content)<% if (request.tools) { %> if message.tool_calls: for tool_call in message.tool_calls: print(json.dumps({ "function": tool_call.function.name, "arguments": json.loads(tool_call.function.arguments) }, indent=2))<% } %> <% } %> 4d:T770,import OpenAI from 'openai'; const openai = new OpenAI({ apiKey: '$NVIDIA_API_KEY', baseURL: 'https://integrate.api.nvidia.com/v1', }); async function main() { const completion = await openai.chat.completions.create({ model: "<%- request.model %>", messages: <%- JSON.stringify(request.messages, null, 2) %>, temperature: <%- request.temperature %>, top_p: <%- request.top_p %>, max_tokens: <%- request.max_tokens %>, stream: <%- request.stream || false %><% if (request.tools) { %>, tools: <%- JSON.stringify(request.tools, null, 2) %><% } %><% if (request.tool_choice) { %>, tool_choice: <%- JSON.stringify(request.tool_choice) %><% } %> }); <% if (request.stream) { %> for await (const chunk of completion) { const delta = chunk.choices[0]?.delta; const reasoning = delta?.reasoning_content; if (reasoning) { process.stdout.write(reasoning); } if (delta?.content) { process.stdout.write(delta.content); }<% if (request.tools) { %> if (delta?.tool_calls) { for (const toolCall of delta.tool_calls) { if (toolCall.function?.name) { console.log(`\n${toolCall.function.name}`); } if (toolCall.function?.arguments) { process.stdout.write(toolCall.function.arguments); } } }<% } %> } <% } else { %> const message = completion.choices[0]?.message; const reasoning = message?.reasoning_content; if (reasoning) { console.log(reasoning); } if (message?.content) { console.log(message.content); }<% if (request.tools) { %> if (message?.tool_calls) { for (const toolCall of message.tool_calls) { console.log(JSON.stringify({ function: toolCall.function.name, arguments: JSON.parse(toolCall.function.arguments) }, null, 2)); } }<% } %> <% } %> } main().catch(console.error);49:["$","$L4a",null,{"initialState":{"artifact":{"artifactType":"ENDPOINT","name":"kimi-k2-thinking","displayName":"kimi-k2-thinking","publisher":"moonshotai","shortDescription":"Open reasoning model with 256K context window, native INT4 quantization and enhanced tool use.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/kimi-k2-thinking.jpg","labels":["Conversational","Function Calling","Long Context","Reasoning","cloudPartnerType:endpoint:cloud_partner_type_deepinfra","cloudPartnerType:endpoint:cloud_partner_type_gmicloud","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":"2025-12-09T14:43:59.311Z","canGuestDownload":true,"createdDate":"2025-12-09T14:43:59.311Z","description":"$4b","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy"},"specAttributes":"$44:props:spec:attributes","modelPath":"/moonshotai/kimi-k2-thinking","openApiSpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for moonshotai/kimi-k2-thinking","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/moonshotai-kimi-k2-thinking 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-thinking"},"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":1,"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"},"max_tokens":{"default":16384,"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":32768,"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"}},"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-thinking\",\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\": 1.0,\n \"max_tokens\": 16384,\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-thinking\",\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":"Which number is larger, 9.11 or 9.8?","requestJson":"{\n \"model\": \"moonshotai/kimi-k2-thinking\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"Which number is larger, 9.11 or 9.8?\"\n }\n ],\n \"top_p\": 0.9,\n \"temperature\": 1.0,\n \"max_tokens\": 16384,\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-thinking\",\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":"$4c","langChain":"from langchain_nvidia_ai_endpoints import ChatNVIDIA\n\nclient = ChatNVIDIA(\n model=\"<%- request.model %>\",\n api_key=\"$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 if chunk.additional_kwargs and \"reasoning_content\" in chunk.additional_kwargs:\n print(chunk.additional_kwargs[\"reasoning_content\"], end=\"\")\n print(chunk.content, end=\"\")\n<% } else { %>\nresponse = client.invoke(<%- JSON.stringify(request.messages) %>)\nif response.additional_kwargs and \"reasoning_content\" in response.additional_kwargs:\n print(response.additional_kwargs[\"reasoning_content\"])\nprint(response.content)\n<% } %>\n","node.js":"$4d","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 @- <<'EOF'\n<%- JSON.stringify({\n model: \"moonshotai/kimi-k2-thinking\",\n messages: request.messages,\n temperature: request.temperature,\n top_p: request.top_p,\n max_tokens: request.max_tokens,\n stream: request.stream,\n ...(request.tools && { tools: request.tools }),\n ...(request.tool_choice && { tool_choice: request.tool_choice })\n}, null, 2) %>\nEOF"},"response":"{\n \"id\": \"chatcmpl-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"moonshotai/kimi-k2-thinking\",\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-thinking"},"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":1,"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"},"max_tokens":{"default":16384,"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":32768,"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"}},"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":["$L4e","$L4f","$L50"]}]