Model Configuration

This page covers the models Kimi Code provides and how to switch between them in each client.

Model Overview

Kimi Code currently offers three models—K3, K2.8 Preview, and K2.7 Code HighSpeed—across four model IDs, selectable by model ID in clients or third-party tools. Model specs:

Recommended model launch

K2.8 Preview is now fully rolled out in Kimi Code — kimi-for-coding is upgraded in place with no configuration changes: performance close to K3, with low / high / max thinking effort levels and up to 1M context. See What's New.

Model ID	k3	k3-256k	kimi-for-coding	kimi-for-coding-highspeed
Model version	K3	K3	K2.8 Preview	K2.7 Code HighSpeed
Description	The most capable flagship coding model: 2.8T parameters, 1M context window	The 256K context version of K3 — k3 (1M) consumes about twice as much quota as k3-256k	Performance close to K3 with more efficient thinking; good at code completion and routine development tasks	The high-speed version of K2.7 Code, with the same coding ability and ~5–6× faster output
Speed	Regular	Regular	Regular	HighSpeed (6× speed, 3× quota usage)
Context window	1048576 (for higher-tier members)	262144 only	1048576	262144
Reasoning	reasoning_effort:low / high / max (default high)	reasoning_effort:low / high / max (default high)	reasoning_effort:low / high / max (default max)	Thinking:ON
Availability (new plans)	Plus and above 1M context for Pro and above	Plus and above	Plus and above	Pro and above
Availability (legacy plans)	Moderato and above 1M context for Allegretto and above	Moderato and above	Andante and above	Allegretto and above
Multimodal input	Image, video	Image only	Image, video	Image, video

Need a higher membership plan?

Different membership plans unlock different models, context windows, and speeds. Upgrade your plan →

Why did usage go up after the new model launched?

After switching models, the context cache built earlier no longer hits on the new model, so that context has to be re-prefilled. Usage therefore looks higher right after switching. Recommended action:

• Start a new session when using the new model: this gives better results and lower consumption.

Why do I still get a 401 with the correct model ID?

When the requested capability exceeds your plan's entitlements, the server returns 401. Three common cases:

• No K3 access: your plan is below Moderato / Plus and can't call k3, k3-256k (the new Go tier has no coding quota) — upgrade to Moderato / Plus or above.
• No 1M access: on a Moderato / Plus plan, k3 supports up to 256K context; up to 1M context is available on Allegretto / Pro or above. k3-256k has a fixed 256K context limit.
• No HighSpeed access: some plans don't include HighSpeed — upgrade to Allegretto / Pro or above to call kimi-for-coding-highspeed.

For the full error text and how to handle it, see the Error Reference.

Why isn't HighSpeed noticeably faster?

Two common reasons:

• Mistyped model ID: the HighSpeed ID must be kimi-for-coding-highspeed; a wrong value silently falls back to the standard kimi-for-coding — no error, no speedup.
• Tools and scripts dominate: HighSpeed only speeds up model output. Tool calls (reading/writing files, running commands, etc.) and script execution are unaffected, so when they take up most of a turn the overall speedup feels small.

How to reduce the overhead of switching reasoning effort?

Switching reasoning effort invalidates the context cache you've built up, so context that would have hit the cache must be re-prefilled. To avoid triggering re-prefill too often:

• Pick an effort that fits the task and keep it consistent within a session;
• When you genuinely need a different effort, start a new session rather than switching back and forth in a long session.

Switching between K3 (1M) and K3-256k

Switching from K3 (1M) to K3-256k: if the current session's context already exceeds 256k, some coding tools (such as Kimi Code CLI and Claude Code) will perform a compact on the tool side. Recommendations:

1. Manually run compact once before switching to compress the context to within 256k. This preserves the key points of the task, keeps the session intact, and lets you benefit from more durable quota after switching.
2. If the conversation history includes video files, switching directly will fail because K3-256k does not support video input. Please compact first, then switch.

Switching from K3-256k to K3 (1M): if k3-256k is close to the 256k limit and you don't want compact to lose information, you can switch directly to 1M. The current version switching from 256k to 1M does not affect the cache.

How to Switch Models

Usage notes

• Start a new session when switching model IDs: switching models invalidates the context cache you've built up. We recommend starting a new session to get the best experience and avoid extra token consumption.
• Fill in the Model ID, not the model version name: when calling a model, use one of the Model IDs from the table above (k3, k3-256k, kimi-for-coding, kimi-for-coding-highspeed). Entering a model version name like K3 or K2.8 Preview will cause the call to fail.
• Thinking off routes to K2.8 Preview (no thinking): with thinking disabled, requests to the K3 series and K2.8 Preview are served by K2.8 Preview with thinking off.

Ways to switch to the target model:

Official clients

• Kimi Code Desktop: switch models in the model picker inside the Composer; if the target model isn't listed yet, restart the app or sign in again.
• Official Kimi Code CLI: type /model to switch models—no config changes needed; if the latest model isn't listed yet, /logout and sign in again with /login.
• Kimi Code for VS Code: pick the target model from the dropdown menu in the input bar; if it isn't listed yet, restart VS Code or reinstall the extension.

Third-party tools

Set the tool's Model ID to the target model. Detailed steps:

1. Create an API Key in the Kimi Code Console.
2. Fill in the Base URL and the corresponding Model ID in your tool.

Kimi Code API supports both OpenAI and Anthropic protocols. Base URLs:

Protocol	Base URL
OpenAI compatible	China https://api.kimi.com/coding/v1 Overseas https://api.kimi.ai/coding/v1
Anthropic compatible	China https://api.kimi.com/coding/ Overseas https://api.kimi.ai/coding/

For detailed setup steps, see the corresponding tool guide:

Claude CodeAnthropic's command-line coding assistantOpenCodeA terminal-based coding agentCodexOpenAI's coding agent

Effort mapping in third-party tools

Both K3 and K2.8 Preview support low / high / max thinking effort levels; the effort a tool sends is mapped as below:

# default
null / undefined       → model default (high for K3, max for K2.8 Preview)
any other unknown       → HTTP 400 error

# → max
ultra / max / xhigh     → max

# → high (recommended)
high / medium           → high

# → low
low / minimum / light   → low

# → thinking disabled
none                    → thinking.type disabled