查看中文版 →

Deutsche Version ansehen →

Открыть русскую версию →

Ver versión en español →

Log inChoose a plan
Tools · Kimi Code

The coding plan
for Kimi Code.

Keep Kimi Code CLI as it is. Add CodingPass as a provider with base_url and your API key in config.toml, and run Claude Sonnet 5.5, Opus 5.5 and Kimi K2.7 Code on one monthly coding plan.

$10/mo until you cancel.

  • Setup in 60s
  • No surprise charges
  • Full refund if you've used 5% or less
~/.kimi-code/config.toml
default_model = "codingpass/claude-sonnet-5-5" [providers.codingpass]type = "openai"base_url = "https://codingpass.ai/v1"api_key = "cp-live-…" [models."codingpass/claude-sonnet-5-5"]provider = "codingpass"model = "claude-sonnet-5-5"max_context_size = 200000capabilities = ["thinking", "tool_use"]
Model ID for your plan
Go
claude-sonnet-5-5
Plus
claude-opus-5-5
Pro
claude-fable-5-2
Strengths

Moonshot AI's agent, open to any model.

A terminal coding agent with subagents, editor integration and video input, and all of it runs on CodingPass. Running several agents? Magpie is a local gateway that puts Kimi Code and the others on one provider.

Open-source Claude Code alternative

Works like Claude Code in your terminal: it reads and edits code, runs commands and hands work to coder, explore and plan subagents. It's MIT-licensed, and /import-sessions brings over your recent Claude Code and Codex sessions.

Fewer tokens per task

In a third-party test it finished the same tasks with a fraction of the tokens Claude Code used, so each task takes less of your allowance.

One binary, no Node.js

Installs with one command and needs no Node.js. The interface is ready in milliseconds.

Zed, JetBrains and video input

kimi acp lets Zed, JetBrains or any Agent Client Protocol editor drive a session. Drop a screen recording into the chat and the agent watches what is hard to describe.

Plans

Which plan for Kimi Code?

Every plan works with Kimi Code. Pick the Claude flagship you want as your default; all open-weight models, Kimi K2.7 Code included, come with every plan and share the same monthly allowance.

Go

Go: Claude Sonnet 5.5

Best forDaily coding, with Kimi for the routine work

$10/mo

$60 Sonnet allowance a month

Requests / month
≈2,050
Per 5-hour window
≈342req
Each open-weight model
$40/mo
Model ID
claude-sonnet-5-5
Choose Go
Recommended
Plus

Plus: Claude Opus 5.5

Best forLarge refactors, long agent sessions

$30/mo

$200 Opus allowance a month

Requests / month
≈3,420
Per 5-hour window
≈570req
Each open-weight model
$125/mo
Model ID
claude-opus-5-5
Choose Plus
Pro

Pro: Claude Fable 5.2

Best forParallel subagents and the hardest problems

$100/mo

$500 Fable allowance a month

Requests / month
≈5,090
Per 5-hour window
≈848req
Each open-weight model
$300/mo
Model ID
claude-fable-5-2
Choose Pro

Estimates from CodingPass traffic: about 100K tokens per request at roughly 5% input, 1% output and 94% cache read. A single Kimi Code task usually makes several requests. Allowances are metered at official API prices.

Setup

Three steps.
About a minute.

Kimi Code reads providers and models from config.toml. Add CodingPass once and every session runs through it.

  1. Create a key

    Sign in with Google, GitHub or email and pick a plan. Then go to Dashboard → Keys → New key. Keys start with cp-live-.

  2. Add the provider

    Paste the block into ~/.kimi-code/config.toml with your key. Add one [models."codingpass/…"] table per model you want to switch to.

    ~/.kimi-code/config.toml
  3. Run kimi

    Start it in your project; the default model applies. On Plus or Pro, set default_model to your plan's flagship. Get your request ID.

    kimi
~/acme-blogExample sessionzsh
$ kimi

> The RSS feed shows drafts. Fix it and add a test.

● explore src/feed · 4 files
● Edited src/feed/rss.ts (+6 −2)
● Ran npm test · 14 passing
  The feed now filters on published: true, like the index page.
Sonnet 5.5$2.80 / $60.00resets in 11d
Tips

Get more out of every allowance.

One monthly allowance covers every model, with 5-hour and weekly caps. The right model for the task makes it go further.

Add Kimi K2.7 Code for routine work

Kimi Code works out of the box with Kimi models. Add kimi-k2.7-code as a second model and switch to it for routine work: on Go it can use up to $40 a month from the shared allowance.

[models."codingpass/kimi-k2.7-code"]provider = "codingpass"model = "kimi-k2.7-code"max_context_size = 200000capabilities = ["thinking", "tool_use"]

Compact long sessions

In a long session, run /compact when the task moves on to its next part. Kimi Code compresses the context, so every later request sends fewer tokens. Add a note on what to keep:

/compact keep the API changes and the failing test output
FAQ

Questions about Kimi Code.

Is this allowed? Could my account get banned?
You use only your CodingPass key. You never log in to, share or relay anyone's account, so your own Claude or ChatGPT account isn't involved. Your requests follow each vendor's usage policy.
Do I need a Kimi account?
No. With the CodingPass provider in config.toml you can skip /login; requests use your CodingPass key only.
Is this the old Python Kimi CLI?
No. This guide is for Kimi Code CLI, which replaced the archived Python Kimi CLI. Its config lives in ~/.kimi-code/.
What happens when I hit the 5-hour cap?
Each 5-hour window allows 1/6 of the monthly allowance (on Go, $10 of Sonnet 5.5, about 342 requests). The cap counts all models together, so CodingPass then returns 429 with the reset time for every model. Wait for the reset, buy a reset card for the current window, or upgrade. How caps and 429s work.
Boarding

Run Kimi Code on a fixed monthly bill.

Sonnet 5.5 and Kimi K2.7 Code from $10 a month. One config file, no surprises, cancel anytime.

  • Request ID on every response
  • Full refund if you've used 5% or less
  • No surprise charges
Choose GoFull plan details

$10/mo until you cancel.