# kimi-k2.6 — API, Pricing & Context Window | Vivgrid

> Source: https://vivgrid.com/docs/models/kimi-k2.6

kimi-k2.6 on Vivgrid: Moonshot AI's coding model with a 262K context window, up to 256K output tokens, and function calling.

`kimi-k2.6` is Moonshot AI's capable coding model, notable for a **262K-token context window** paired with an exceptionally large **256K-token max output**. That combination suits agents that both read and generate large volumes of code.

Vivgrid serves `kimi-k2.6` through its unified, OpenAI-compatible API, letting you route Moonshot alongside other providers with a single key and billing surface.

## Specifications

| Field | Value |
| --- | --- |
| Provider | Moonshot AI |
| Model ID | `kimi-k2.6` |
| Best for | Coding |
| Available on | Vibe coding |
| Context window | 262,144 tokens |
| Max output | 256,000 tokens |
| Modalities | Text, Image |
| Tool / function calling | Yes |
| Knowledge cutoff | 2026-04 |
| Acceleration | Global (centralized) |

## Pricing

Pricing in USD per 1M tokens.

| Input | Cached input | Output |
| --- | --- | --- |
| $1.00 | $0.20 | $4.00 |

### What one request costs

The rates above applied to a 20K-token prompt with a 2K-token reply — a typical single agent turn, small enough that every request is billed at the base rate.

| Request | Cost |
| --- | --- |
| Cold prompt, nothing cached | $0.0280 |
| Warm prompt, 90% of the input served from cache | $0.0136 |


## API surfaces

The Vivgrid Console catalogs `kimi-k2.6` on one surface, all behind the same API key. The endpoint shown is the one the Console previews for that surface.

| Surface | Primary endpoint | Use it for |
| --- | --- | --- |
| Vibe coding | `/chat/completions` | Coding CLIs and IDE agents that drive the model themselves — point the tool at Vivgrid and keep your own loop. |

## Quick start

Get an API key from the Vivgrid Console (https://console.vivgrid.com), then call `kimi-k2.6` directly.

```bash
curl https://api.vivgrid.com/v1/chat/completions \
  -H "Authorization: Bearer $VIVGRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k2.6",
    "messages": [
      { "role": "user", "content": "Say hello in English, Chinese and Spanish." }
    ],
    "stream": true
  }'
```


## Ideal use cases

- Coding agents that produce large outputs
- Long-context engineering and refactoring tasks
- Tool-calling workflows on Chat Completions
- Cost-effective alternative to frontier coding models

## Related models

- [gpt-6-astra](/docs/models/gpt-6-astra) — OpenAI's frontier gpt-6 coding model
- [kimi-k3](/docs/models/kimi-k3) — the next-generation Moonshot coding model
- [kimi-k2.8-preview](/docs/models/kimi-k2.8-preview) — 1M context with adjustable thinking effort
- [minimax-m3](/docs/models/minimax-m3) — high-context coding option