# Kimi K2.6

> Moonshot AI Kimi-K2.6 — large MoE with agentic tool use, vision input, and long-context memory, served via Cloudflare Workers AI and SiliconFlow's free tier.

**ID**: `moonshotai/kimi-k2.6`  
**Creator**: Moonshot AI  
**Category**: multimodal  
**Context**: 256K tokens  
**Input**: $0.95/M  
**Output**: $4.00/M  
**Released**: 2026-07-08  
**Web page**: https://anyrouter.dev/model/moonshotai/kimi-k2.6

**Input modalities**: text, image  
**Output modalities**: text  

**Capabilities**: chat, reasoning, streaming, function-calling, vision

**Aliases**: `moonshotai/Kimi-K2.6`

## Usage

**Endpoint**: `POST https://anyrouter.dev/api/v1/chat/completions`

```bash
curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "moonshotai/kimi-k2.6",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'
```

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| aihubmix-byok | $0 | $0 |
| siliconflow-byok | $0 | $0 |
| cline-byok | $0 | $0 |
| nvidia | $0.95/M | $4.00/M |
| nvidia-byok | $0 | $0 |
| commandcode-byok | $0 | $0 |
| router-byok | $0 | $0 |
| vercel-byok | $0 | $0 |

## Benchmarks

- **GPQA Diamond**: 0.9
- **HLE**: 0.4
- **τ²-Bench Telecom**: 1.0
- **SciCode**: 0.5
- **OTIS Mock AIME**: 1.0
- **SimpleQA (verified)**: 0.4

Benchmark data from [Epoch AI](https://epoch.ai/benchmarks) (CC-BY 4.0).

## Source

- Upstream docs: https://developers.cloudflare.com/ai/models/@cf/moonshotai/kimi-k2.6/