> ## Documentation Index
> Fetch the complete documentation index at: https://gomodel.enterpilot.io/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Kimi Code

> Configure Kimi Code in GoModel and understand its model alias, embeddings caveat, and quota behavior.

Kimi Code is an OpenAI-compatible coding assistant served at `https://api.kimi.com/coding/v1`.
GoModel routes chat, model listing, embeddings, and passthrough requests through the shared
OpenAI adapter. The `/v1/responses` endpoint is translated through chat completions, while
files and batches are not supported by the upstream endpoint.

## Configure

```bash theme={null}
KIMICODE_API_KEY=...
```

Or in `config.yaml`:

```yaml theme={null}
providers:
  kimicode:
    type: kimicode
    base_url: "https://api.kimi.com/coding/v1"
    api_key: "${KIMICODE_API_KEY}"
```

<Note>
  The provider `type` is `kimicode` (no hyphen). The config key (`kimicode` in
  the example above) is arbitrary and only identifies this entry inside your
  config; it may be changed.
</Note>

You can also override the base URL and model list with:

```bash theme={null}
KIMICODE_BASE_URL=https://api.kimi.com/coding/v1
KIMICODE_MODELS=kimi-for-coding,bge_m3_embed
```

## Models

The standard chat model alias is `kimi-for-coding`. You can reference it in a virtual
model or call it directly through the OpenAI-compatible `/v1/chat/completions` endpoint.

```yaml theme={null}
virtual_models:
  - source: kimi-coding
    target: kimicode/kimi-for-coding
```

## Embeddings

Kimi Code exposes `bge_m3_embed` for embeddings, but this model is not documented
upstream. Treat it as experimental: test availability and dimensionality in your account
before relying on it in production workflows.

## Pricing & quota

Kimi Code does not publish per-token pricing. Because GoModel's usage-cost tracking has
no price to multiply, it reports `cost` as zero for Kimi Code requests. The `cost` load-balancing
strategy cannot prefer or rank this provider by price, but it may still fall back to Kimi Code
when no priced provider is available.

Upstream quota works on a weekly refresh plus a rolling five-hour window. Plan for burst
limits and prefer conservative per-provider retry overrides:

```yaml theme={null}
providers:
  kimicode:
    type: kimicode
    base_url: "https://api.kimi.com/coding/v1"
    api_key: "${KIMICODE_API_KEY}"
    retries: 3
```