Kimi K3.1 Pro
Kimi K3.1 Pro is a general-purpose open-weight model served on Sarvam infrastructure. It accepts text, images, and video and has a 1,048,576-token context window.
Kimi K3.1 Pro is available on Provisioned Throughput: capacity is set up for your workload and enabled for your organisation. Without access, requests return 404 not_found_error and the model isn’t listed in GET /v2/models. Contact us to request access. See Provisioned Throughput.
At a glance
Key capabilities
Moving from OpenRouter, Fireworks AI, or Together AI? The migration guides map model IDs and request fields to Sarvam.
Quickstart
Supported parameters
model: "kimi-k3.1-pro" on Chat Completion V2
and Responses. Full request/response schemas live on
those API reference pages; this table covers what’s actually accepted for this model.
Reasoning
Thinking is always on and can’t be turned off. Effort levels: low, medium, high, max
(default max); medium runs as high. Set them with reasoning_effort on chat or
reasoning.effort on Responses. "none", "minimal", and "xhigh" return 400, and so does
turning thinking off with thinking or chat_template_kwargs.
Read the reasoning trace from choices[].message.reasoning_content on chat. On Responses,
output starts with a reasoning item; read its content[0].text. Its summary is empty unless you set
reasoning.summary.
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.
Images are resized to about 12.8 megapixels, so any image at or above that size costs about 16,700 input tokens. Images above about 179 megapixels are rejected.
Video input
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.
The model follows what happens across the clip, in order. A 40-second clip with four scenes was described correctly in tests; for long videos, keep the request under the request size limit or sample key frames and send them as images.
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.
Known limitations
- Reasoning and the final answer share the
max_tokens/max_output_tokensbudget. - Log probabilities,
n> 1, andseedare not supported. - Set
max_tokensexplicitly to bound cost and latency.