Source: https://ailoot.ai/docs/integrations/kimi-cli/
Canonical: https://ailoot.ai/docs/en/integrations/kimi-cli/
Language: en

[Terminal agents](https://ailoot.ai/docs/en/integrations/#agents) 

# Kimi CLI

[Markdown](https://ailoot.ai/docs/en/integrations/kimi-cli/index.md)

Terminal agent · OpenAI Chat, OpenAI Responses, Anthropic Messages, Gemini

| Format | Where to set it up |
| --- | --- |
| OpenAI Chat, OpenAI Responses, Anthropic Messages, Gemini | ~/.kimi/config.toml (providers and models sections, default\_model); /login supports only Moonshot platforms, so set a custom URL manually in the file |

## [](https://ailoot.ai/docs/integrations/kimi-cli/#setup)Setup

Copy the configuration and replace `sk-...` with your key from the Ailoot Dashboard. Prefer storing the key in the environment variable `AILOOT_API_KEY`, if the application supports it.

Before starting, request GET /v1/models with your Ailoot key. Choose an exact model ID whose methods include POST /v1/chat/completions, POST /v1/responses, POST /v1/messages, POST /v1beta/models/{model}:generateContent, then use that ID in the configuration. For agents, also check tool support and the features required by your client version.

`~/.kimi/config.toml`

```toml
default_model = "ailoot-kimi"

[providers.ailoot]
type = "openai_legacy"
base_url = "https://api.ailoot.ai/v1"
api_key = "sk-..."

[providers.ailoot-claude]
type = "anthropic"
base_url = "https://api.ailoot.ai"
api_key = "sk-..."

[models.ailoot-kimi]
provider = "ailoot"
model = "kimi-k3"
max_context_size = 262144
capabilities = ["thinking"]

[models.ailoot-sonnet]
provider = "ailoot-claude"
model = "claude-sonnet-5-5"
max_context_size = 1000000
capabilities = ["thinking", "image_in"]
```

Example model: `kimi-k3`. Choose any other model from the [catalog](https://ailoot.ai/models/en/) — check that it supports the format you need.

## [](https://ailoot.ai/docs/integrations/kimi-cli/#notes)Good to know

Types: openai\_legacy (Chat Completions, base\_url with /v1), openai\_responses (Responses, with /v1), anthropic (without /v1), gemini (base\_url is Google's root URL; for us, https://api.ailoot.ai). SearchWeb works only with Moonshot's own platform; with a different API URL, FetchURL switches to local downloading.

## [](https://ailoot.ai/docs/integrations/kimi-cli/#check)Test

- For the OpenAI format, the URL is `https://api.ailoot.ai/v1` (or the full path if the application asks for a full URL).
- For the Anthropic format, the URL is `https://api.ailoot.ai` without `/v1`.
- For the Gemini format, the URL is `https://api.ailoot.ai` — the API origin. The example above does not show the full setup for this format; consult the client’s documentation for the path to use in the relevant field. The API route prefix is `/v1beta`.
- Ask a short question. If you get an error, check the code and Request ID, then consult [Errors and limits](https://ailoot.ai/docs/en/errors/).
- 404 immediately after setup almost always means the URL is wrong: an extra or missing `/v1`.
- 402 — insufficient balance for the reserve. Agents reserve more than chat: [why](https://ailoot.ai/docs/en/billing/reserve/).

Application documentation: [https://moonshotai.github.io/kimi-cli/en/configuration/providers.html](https://moonshotai.github.io/kimi-cli/en/configuration/providers.html)

Still have questions? Send your Request ID and a description — we'll help you troubleshoot.[Contact support](mailto:support@ailoot.ai)

## Ailoot · The company and its project portfolio





Ailoot combines established operating experience, a large client base, stable service and ongoing KPI control.





The company and its project portfolio: millions of customers; monthly sales in the billions.





Ailoot brings that operating experience to API access for AI features in customer products, agents, applications and automations.
