Moonshot AI (Kimi)

Moonshot provides the Kimi API with OpenAI-compatible endpoints. Configure the provider and set the default model to moonshot/kimi-k2.6, or use Kimi Coding with kimi/kimi-code.

Moonshot and Kimi Coding are separate providers. Keys are not interchangeable, endpoints differ, and model refs differ (moonshot/... vs kimi/...).

Built-in model catalog

Model ref	Name	Reasoning	Input	Context	Max output
`moonshot/kimi-k2.6`	Kimi K2.6	No	text, image	262,144	262,144
`moonshot/kimi-k2.5`	Kimi K2.5	No	text, image	262,144	262,144
`moonshot/kimi-k2-thinking`	Kimi K2 Thinking	Yes	text	262,144	262,144
`moonshot/kimi-k2-thinking-turbo`	Kimi K2 Thinking Turbo	Yes	text	262,144	262,144
`moonshot/kimi-k2-turbo`	Kimi K2 Turbo	No	text	256,000	16,384

Bundled cost estimates for current Moonshot-hosted K2 models use Moonshot’s published pay-as-you-go rates: Kimi K2.6 is

0.16/MTok cache hit,

0.95/MTok input, and

4.00/MTok output; Kimi K2.5 is

0.10/MTok cache hit,

0.60/MTok input, and

3.00/MTok output. Other legacy catalog entries keep zero-cost placeholders unless you override them in config.

Getting started

Choose your provider and follow the setup steps.

Moonshot API
Kimi Coding

Best for: Kimi K2 models via the Moonshot Open Platform.

Choose your endpoint region

Auth choice	Endpoint	Region
`moonshot-api-key`	`https://api.moonshot.ai/v1`	International
`moonshot-api-key-cn`	`https://api.moonshot.cn/v1`	China

Run onboarding

fluffbuzz onboard --auth-choice moonshot-api-key

Or for the China endpoint:

fluffbuzz onboard --auth-choice moonshot-api-key-cn

Set a default model

{
  agents: {
    defaults: {
      model: { primary: "moonshot/kimi-k2.6" },
    },
  },
}

Verify models are available

fluffbuzz models list --provider moonshot

Run a live smoke test

Use an isolated state dir when you want to verify model access and cost tracking without touching your normal sessions:

FLUFFBUZZ_CONFIG_PATH=/tmp/fluffbuzz-kimi/fluffbuzz.json \
FLUFFBUZZ_STATE_DIR=/tmp/fluffbuzz-kimi \
fluffbuzz agent --local \
  --session-id live-kimi-cost \
  --message 'Reply exactly: KIMI_LIVE_OK' \
  --thinking off \
  --json

The JSON response should report provider: "moonshot" and model: "kimi-k2.6". The assistant transcript entry stores normalized token usage plus estimated cost under usage.cost when Moonshot returns usage metadata.

Config example

{
  env: { MOONSHOT_API_KEY: "sk-..." },
  agents: {
    defaults: {
      model: { primary: "moonshot/kimi-k2.6" },
      models: {
        // moonshot-kimi-k2-aliases:start
        "moonshot/kimi-k2.6": { alias: "Kimi K2.6" },
        "moonshot/kimi-k2.5": { alias: "Kimi K2.5" },
        "moonshot/kimi-k2-thinking": { alias: "Kimi K2 Thinking" },
        "moonshot/kimi-k2-thinking-turbo": { alias: "Kimi K2 Thinking Turbo" },
        "moonshot/kimi-k2-turbo": { alias: "Kimi K2 Turbo" },
        // moonshot-kimi-k2-aliases:end
      },
    },
  },
  models: {
    mode: "merge",
    providers: {
      moonshot: {
        baseUrl: "https://api.moonshot.ai/v1",
        apiKey: "${MOONSHOT_API_KEY}",
        api: "openai-completions",
        models: [
          // moonshot-kimi-k2-models:start
          {
            id: "kimi-k2.6",
            name: "Kimi K2.6",
            reasoning: false,
            input: ["text", "image"],
            cost: { input: 0.95, output: 4, cacheRead: 0.16, cacheWrite: 0 },
            contextWindow: 262144,
            maxTokens: 262144,
          },
          {
            id: "kimi-k2.5",
            name: "Kimi K2.5",
            reasoning: false,
            input: ["text", "image"],
            cost: { input: 0.6, output: 3, cacheRead: 0.1, cacheWrite: 0 },
            contextWindow: 262144,
            maxTokens: 262144,
          },
          {
            id: "kimi-k2-thinking",
            name: "Kimi K2 Thinking",
            reasoning: true,
            input: ["text"],
            cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
            contextWindow: 262144,
            maxTokens: 262144,
          },
          {
            id: "kimi-k2-thinking-turbo",
            name: "Kimi K2 Thinking Turbo",
            reasoning: true,
            input: ["text"],
            cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
            contextWindow: 262144,
            maxTokens: 262144,
          },
          {
            id: "kimi-k2-turbo",
            name: "Kimi K2 Turbo",
            reasoning: false,
            input: ["text"],
            cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
            contextWindow: 256000,
            maxTokens: 16384,
          },
          // moonshot-kimi-k2-models:end
        ],
      },
    },
  },
}

Best for: code-focused tasks via the Kimi Coding endpoint.

Kimi Coding uses a different API key and provider prefix (kimi/...) than Moonshot (moonshot/...). Legacy model ref kimi/k2p5 remains accepted as a compatibility id.

Run onboarding

fluffbuzz onboard --auth-choice kimi-code-api-key

Set a default model

{
  agents: {
    defaults: {
      model: { primary: "kimi/kimi-code" },
    },
  },
}

Verify the model is available

fluffbuzz models list --provider kimi

Config example

{
  env: { KIMI_API_KEY: "sk-..." },
  agents: {
    defaults: {
      model: { primary: "kimi/kimi-code" },
      models: {
        "kimi/kimi-code": { alias: "Kimi" },
      },
    },
  },
}

Kimi web search

FluffBuzz also ships Kimi as a web_search provider, backed by Moonshot web search.

Run interactive web search setup

fluffbuzz configure --section web

Choose Kimi in the web-search section to store plugins.entries.moonshot.config.webSearch.*.

Configure the web search region and model

Interactive setup prompts for:

Setting	Options
API region	`https://api.moonshot.ai/v1` (international) or `https://api.moonshot.cn/v1` (China)
Web search model	Defaults to `kimi-k2.6`

Config lives under plugins.entries.moonshot.config.webSearch:

{
  plugins: {
    entries: {
      moonshot: {
        config: {
          webSearch: {
            apiKey: "sk-...", // or use KIMI_API_KEY / MOONSHOT_API_KEY
            baseUrl: "https://api.moonshot.ai/v1",
            model: "kimi-k2.6",
          },
        },
      },
    },
  },
  tools: {
    web: {
      search: {
        provider: "kimi",
      },
    },
  },
}

Advanced configuration

Native thinking mode

Moonshot Kimi supports binary native thinking:

thinking: { type: "enabled" }
thinking: { type: "disabled" }

Configure it per model via agents.defaults.models.<provider/model>.params:

{
  agents: {
    defaults: {
      models: {
        "moonshot/kimi-k2.6": {
          params: {
            thinking: { type: "disabled" },
          },
        },
      },
    },
  },
}

FluffBuzz also maps runtime /think levels for Moonshot:

`/think` level	Moonshot behavior
`/think off`	`thinking.type=disabled`
Any non-off level	`thinking.type=enabled`

When Moonshot thinking is enabled, tool_choice must be auto or none. FluffBuzz normalizes incompatible tool_choice values to auto for compatibility.

Kimi K2.6 also accepts an optional thinking.keep field that controls multi-turn retention of reasoning_content. Set it to "all" to keep full reasoning across turns; omit it (or leave it null) to use the server default strategy. FluffBuzz only forwards thinking.keep for moonshot/kimi-k2.6 and strips it from other models.

{
  agents: {
    defaults: {
      models: {
        "moonshot/kimi-k2.6": {
          params: {
            thinking: { type: "enabled", keep: "all" },
          },
        },
      },
    },
  },
}

Tool call id sanitization

Moonshot Kimi serves tool_call ids shaped like functions.<name>:<index>. FluffBuzz preserves them unchanged so multi-turn tool calls keep working.To force strict sanitization on a custom OpenAI-compatible provider, set sanitizeToolCallIds: true:

{
  models: {
    providers: {
      "my-kimi-proxy": {
        api: "openai-completions",
        sanitizeToolCallIds: true,
      },
    },
  },
}

Streaming usage compatibility

Native Moonshot endpoints (https://api.moonshot.ai/v1 and https://api.moonshot.cn/v1) advertise streaming usage compatibility on the shared openai-completions transport. FluffBuzz keys that off endpoint capabilities, so compatible custom provider ids targeting the same native Moonshot hosts inherit the same streaming-usage behavior.With the bundled K2.6 pricing, streamed usage that includes input, output, and cache-read tokens is also converted into local estimated USD cost for /status, /usage full, /usage cost, and transcript-backed session accounting.

Endpoint and model ref reference

Provider	Model ref prefix	Endpoint	Auth env var
Moonshot	`moonshot/`	`https://api.moonshot.ai/v1`	`MOONSHOT_API_KEY`
Moonshot CN	`moonshot/`	`https://api.moonshot.cn/v1`	`MOONSHOT_API_KEY`
Kimi Coding	`kimi/`	Kimi Coding endpoint	`KIMI_API_KEY`
Web search	N/A	Same as Moonshot API region	`KIMI_API_KEY` or `MOONSHOT_API_KEY`

Kimi web search uses KIMI_API_KEY or MOONSHOT_API_KEY, and defaults to https://api.moonshot.ai/v1 with model kimi-k2.6.
Override pricing and context metadata in models.providers if needed.
If Moonshot publishes different context limits for a model, adjust contextWindow accordingly.

Model selection

Choosing providers, model refs, and failover behavior.

Web search

Configuring web search providers including Kimi.

Configuration reference

Full config schema for providers, models, and plugins.

Moonshot Open Platform

Moonshot API key management and documentation.

Overview

Concepts and configuration

Providers

Moonshot AI

Moonshot AI (Kimi)

Built-in model catalog

Getting started

Config example

Config example

Kimi web search

Advanced configuration

Model selection

Web search

Configuration reference

Moonshot Open Platform

​Moonshot AI (Kimi)

​Built-in model catalog

​Getting started

​Config example

​Config example

​Kimi web search

​Advanced configuration

​Related

Model selection

Web search

Configuration reference

Moonshot Open Platform

Moonshot AI (Kimi)

Built-in model catalog

Getting started

Config example

Config example

Kimi web search

Advanced configuration

Related