Skip to content

Model detail

Kimi K3

Provided by Moonshot
Pay-as-you-go

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at navigating large repositories, using tools, debugging, and iterating against images, logs, tests, and runtime feedback. Its architecture uses KDA and Attention Residuals for computational efficiency.

Model specs

Model ID
kimi-k3
Context length
1.048576M
Max output
1.048576M
I/O modalities
Released
2026-07

02

API endpoints

One MixRoute gateway, OpenAI-compatible

  • OpenAI-compatible /v1/chat/completions POST

03

Pricing

Flat rate, unit: /1M Tokens

Input

$3.0000 /1M Tokens

Completion

$15.0000 /1M Tokens

Cache read

$0.3000 /1M Tokens

05

Selection summary

Quickly judge whether it fits your workload

What is this model good for?

Flagship model for complex reasoning and agentic workflows

Kimi K3: Kimi's most capable model to date, with 2.8 trillion parameters, native visual understanding, and a 1M-token context window, designed for frontier intelligence scenarios such as so. 1,000,000-token context.

What should you check before using it?

1,000,000 context, 1,000,000 output, text, image, video

Moonshot model. Supports tool calling and structured outputs.

Why use it through MixRoute?

Drop-in via OpenAI-compatible endpoint on MixRoute

Set the model parameter to "kimi-k3" and use your MixRoute API key.

07

Capabilities & compatibility

Unconfirmed capabilities stay "Unknown," no guesses

Available:

Tool calling

Kimi K3 supports function and tool calls.

EX Send a tools definition; the response returns tool_calls to execute and feed results back.
Available:

Structured output

Kimi K3 can produce JSON-formatted output on demand.

EX response_format: { type: "json_schema" } forces valid JSON output.
Available:

Streaming

Kimi K3 supports streamed responses.

EX stream: true streams tokens incrementally, so chat UIs render as they arrive.
Available:

Prompt caching

Kimi K3 supports prompt caching under supported routing conditions.

EX Keep the system prompt and tool definitions at the start of the request; repeated prefixes are automatically billed at the cache-read rate.
Available:

Vision input

Kimi K3 can process image inputs alongside text.

EX Pass a base64-encoded image in a image_url content part alongside text messages.
Available:

OpenAI SDK

Call Kimi K3 through MixRoute's OpenAI-compatible endpoint.

EX Change base_url to https://api.mixroute.ai/v1; everything else follows the OpenAI style.

08

Token cost estimator

Live estimate from this page's pricing, not an actual bill

Share of the same prefix read repeatedly, up to 100%

09

FAQ

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at navigating large repositories, using tools, debugging, and iterating against images, logs, tests, and runtime feedback.

One endpoint, a testable decision

Test this model and alternate routes with the same request format

Start from a real workload, then let quality, total cost, and failure conditions decide whether to send production traffic.

Create an API key View integration docs