> This page is for Model APIs. > Sarvam Voice Agents (Samvaad) is a voice AI agent platform for Indian languages: build, test and deploy AI calling agents on your own phone numbers, from ₹3 a minute. Start here: https://docs.sarvam.ai/voice-agents/why-voice-agents. > For clean Markdown of any page, append `.md` to the page URL. > For a complete documentation index, see https://docs.sarvam.ai/llms.txt. For a section index, append `/llms.txt` to any section URL (for example https://docs.sarvam.ai/voice-agents/llms.txt). > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.sarvam.ai/_mcp/server. # Kimi K3 > Kimi K3 is an open-weight reasoning model with text, image, and video input, a 1,048,576-token context window, and tool calling. Kimi K3 is a general-purpose [open-weight model](/api/token-factory/models) served on Sarvam infrastructure. It accepts **text, images, and video** and has a **1,048,576-token context window**. > **Note** > > Kimi K3 is in **beta**. Its behaviour, limits, and availability may change before general availability. Beta models must be enabled for your API key; without access, requests return `400 invalid_request_error` ("This model is currently in beta"). [Contact us](/api/getting-started/help) to request access. See [Beta models](/api-reference/beta-apis). ## At a glance | | | | ------------------ | ------------------------------------------------------------------------------------------------------------------------------------ | | **Model ID** | `kimi-k3` | | **Best for** | Agentic workflows and reasoning over images and video | | **Context window** | 1,048,576 tokens | | **Input → output** | Text + image + video (beta, short clips only) → text | | **Reasoning** | Always on: **`low`**, **`high`**, or **`max`** (default). See [Reasoning](#reasoning) | | **Tool calling** | Supported, including parallel tool calls | | **APIs** | [`POST /v2/chat/completions`](/api-reference/chat/chat-completions-v2) and [`POST /v2/responses`](/api-reference/responses/create) | | **Pricing** | ₹270 input · ₹27 cached input · ₹1,350 output per 1M tokens; reasoning is billed as output ([Pricing](/api/getting-started/pricing)) | ## Key capabilities #### Long context Process up to 1,048,576 tokens across the prompt, reasoning, and generated output. #### Image and video input Send base64 images and short base64 video clips alongside text. #### Reasoning Receive reasoning in `reasoning_content` separately from the final answer in `content`. #### Tool calling Use OpenAI-compatible `tools` and `tool_choice` for agentic workflows. #### Structured output Constrain answers with `response_format` JSON schemas. #### Log probabilities Request `logprobs` and `top_logprobs`, and `n` > 1 choices. > **Tip** > > Moving from [OpenRouter](/api/token-factory/migrations/from-openrouter/overview), [Fireworks AI](/api/token-factory/migrations/from-fireworks/overview), or [Together AI](/api/token-factory/migrations/from-together/overview)? The migration guides map model IDs and request fields to Sarvam. ## Quickstart #### Python ```python from sarvamai import SarvamAI client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY") response = client.chat.completions_v2( model="kimi-k3", messages=[ { "role": "user", "content": "Plan a three-step approach to migrate a monolith to microservices.", } ], max_tokens=4000, ) print(response.choices[0].message.content) ``` #### JavaScript ```javascript import { SarvamAIClient } from "sarvamai"; const client = new SarvamAIClient({ apiSubscriptionKey: "YOUR_SARVAM_API_KEY", }); async function main() { const response = await client.chat.completionsV2({ model: "kimi-k3", messages: [ { role: "user", content: "Plan a three-step approach to migrate a monolith to microservices.", }, ], max_tokens: 4000, }); console.log(response.choices[0].message.content); } main(); ``` #### cURL ```bash curl -X POST https://api.sarvam.ai/v2/chat/completions \ -H "api-subscription-key: $SARVAM_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "kimi-k3", "messages": [ { "role": "user", "content": "Plan a three-step approach to migrate a monolith to microservices." } ], "max_tokens": 4000 }' ``` ## Supported parameters `model: "kimi-k3"` on [Chat Completion V2](/api-reference/chat/chat-completions-v2) and [Responses](/api-reference/responses/create). Full request/response schemas live on those API reference pages; this table covers what's actually accepted for this model. | Parameter | Chat Completion V2 | Responses | | ----------------------------------------------------- | :---------------------------------------------------: | :---------------------------------------------------------------------------------------------------: | | Streaming (`stream`) | | | | Image input (base64) | `image_url` | `input_image` | | Video input (base64, beta) | `video_url`, short clips only | `400` | | Audio input | `400` | `400` | | Tool calling (`tools`, `tool_choice`) | | | | `parallel_tool_calls: false` enforced | | | | Structured output (`response_format` / `text.format`) | | | | Log probabilities (`logprobs`, `top_logprobs`) | | send `top_logprobs` with `include: ["message.output_text.logprobs"]`; `logprobs: true` returns `400` | | Multiple choices (`n` > 1) | requires `temperature` > `0` | N/A — Responses has no `n` | | Reasoning control | `reasoning_effort`: `low`, `high`, or `max` (default) | `reasoning.effort`: same values | | Turn reasoning off | always thinks | always thinks | > **Warning** > > On `POST /v2/responses`, `logprobs` is only populated when the request includes > `"include": ["message.output_text.logprobs"]`. Without it, `output[].content[].logprobs` > is always an empty array even if `top_logprobs` is set. Verified against the live API on > 2026-10-22. ## Reasoning Thinking is always on and can't be turned off. Effort levels: `low`, `high`, `max` (default `max`). Set them with `reasoning_effort` on chat or `reasoning.effort` on Responses. Read the reasoning trace from `choices[].message.reasoning_content` on chat. On Responses, `output` starts with a `reasoning` item; read its `content[0].text` (`summary` is empty). Reasoning tokens are billed as output tokens and count against `max_tokens` / `max_output_tokens`. On Responses, when the model calls tools, `output` has one `reasoning` item followed by the `function_call` items for that turn (sometimes with a `message` item between them). ## Image input Send images **inline as base64 data URIs** in an `image_url` content part on chat, or an `input_image` part on Responses. Supported formats are PNG, JPEG, WebP, GIF, BMP, and TIFF. Images sent by `file_id` are not supported. ```python import base64 with open("chart.png", "rb") as f: data_uri = "data:image/png;base64," + base64.b64encode(f.read()).decode() response = client.chat.completions_v2( model="kimi-k3", messages=[ { "role": "user", "content": [ {"type": "text", "text": "Summarise this chart."}, {"type": "image_url", "image_url": {"url": data_uri}}, ], } ], max_tokens=2000, ) ``` Images are resized to about 12.8 megapixels. Images above about 179 megapixels are rejected. ## Video input (beta) Send a video **inline as a base64 data URI** in a `video_url` content part on Chat Completion V2. Remote video URLs return `400`, and the Responses API doesn't accept video. > **Warning** > > Kimi K3 understands only **very short clips**, about four frames. Longer clips can come back > as blank or repeated frames, and the answer describes only part of the video. For longer > videos, use [MiMo V2.6 Flash](/api/token-factory/models/mimo-v2.6-flash) or > [MiMo V2.6 Pro](/api/token-factory/models/mimo-v2.6-pro). ```python import base64 with open("clip.mp4", "rb") as f: video_uri = "data:video/mp4;base64," + base64.b64encode(f.read()).decode() response = client.chat.completions_v2( model="kimi-k3", messages=[ { "role": "user", "content": [ {"type": "text", "text": "Describe what happens in this clip."}, {"type": "video_url", "video_url": {"url": video_uri}}, ], } ], max_tokens=2000, ) ``` Audio input is not supported and returns `400`. ## Tool calling Pass OpenAI-compatible `tools`. `tool_choice` accepts `"auto"`, `"none"`, `"required"`, or a named function (`{"type": "function", "function": {"name": "..."}}`). The model can return several tool calls in one turn; set `parallel_tool_calls: false` to get at most one. ## Multiple choices `n` > 1 needs `temperature` greater than `0`. Sending `n` > 1 with `temperature: 0` returns `400`. ## Known limitations * Video input is beta and reliable only for very short clips (see [Video input](#video-input-beta)). * Reasoning and the final answer share the **`max_tokens`** / **`max_output_tokens`** budget. * A `stop` string can match inside the thinking, which ends the response early with `content: null`. Use stop strings that won't appear in reasoning. * Set **`max_tokens`** explicitly. When it's omitted, generation isn't capped at a small default and long answers can run to tens of thousands of tokens. ## Limits and errors | Area | Limit or condition | API response | Recommended action | | -------------- | ---------------------------------------------------- | ---------------------------------------------------------- | ------------------------------------------------------------------------------------------- | | Output | `max_tokens` exceeds 1,048,576 | `400 invalid_request_error` | Set `max_tokens` within the context window. | | Request size | Request body exceeds 40 MiB (41,943,040 bytes) | `413 invalid_request_error`, with the limit in the message | Send smaller or fewer media files. Base64 adds about 33%, so about 30 MB of raw media fits. | | Media URL | An image, audio, or video part uses an `http(s)` URL | `400 invalid_request_error` | Send the file inline as a base64 data URI. | | Media count | More than 999 images or 999 videos in one request | `400 invalid_request_error` | Split the request. | | Image size | Image above about 179 megapixels | `400 invalid_request_error` | Downscale the image. | | Modality | Request includes audio input | `400 invalid_request_error` | Send text, image, or video input. | | Choices | `n` > 1 with `temperature: 0` | `400 invalid_request_error` | Set `temperature` above `0`. | | Reasoning | Reasoning consumes the full `max_tokens` budget | `200` with `finish_reason: "length"` | Raise `max_tokens` or lower the reasoning effort. | | Authentication | API key is missing or invalid | `403 invalid_api_key_error` | Check the `api-subscription-key` header. | | Model | Model ID is unknown or unavailable | `404 not_found_error` | Check the spelling; model IDs are case-sensitive. | | Quota | No credits remain | `402 insufficient_quota_error` | Add credits in the [dashboard](https://indus.sarvam.ai/billing?ref=docs). | | Rate limit | Request or concurrency limit is exceeded | `429 rate_limit_exceeded_error` | Back off and retry. | | Availability | Model remains overloaded after retries | `503 model_overloaded` | Retry later. |