# Kimi (latest)

> Always resolves to the newest live Kimi model — currently Kimi K3 (moonshotai/kimi-k3). Kimi K3 is an open-source multimodal reasoning model from Moonshot AI with a 1M-token context window and native visual understanding. It accepts text, image, and video inputs and is built for long-horizon software engineering, knowledge work, and deep reasoning, with particular strength where code meets visual and spatial reasoning — frontend, game development, and CAD workflows. Its architecture uses KDA and Attention Residuals for computational efficiency, and its thinking mode is always on.

**ID**: `moonshotai/kimi-latest`  
**Creator**: Moonshot AI  
**Category**: multimodal  
**Context**: 1M tokens  
**Family alias**: always resolves to the newest live family member — currently [`moonshotai/kimi-k3`](https://anyrouter.dev/model/moonshotai/kimi-k3). Specs below are moonshotai/kimi-k3's.  
**Fallback order**: `moonshotai/kimi-k3` → `moonshotai/kimi-k2.6`  
**Input**: $3.00/M  
**Output**: $15.00/M  
**Released**: 2026-07-16  
**Web page**: https://anyrouter.dev/model/moonshotai/kimi-latest

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

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

**Aliases**: `moonshotai/Kimi-K3`

## 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-latest",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'
```

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| aihubmix-byok | $0 | $0 |
| nvidia | $0 | $0 |
| nvidia-byok | $0 | $0 |
| moonshotai-byok | $0 | $0 |
| zenmux-byok | $0 | $0 |
| openrouter-byok | $0 | $0 |
| orcarouter-byok | $0 | $0 |
| cline-byok | $0 | $0 |
| novita-byok | $0 | $0 |
| fireworks-byok | $0 | $0 |
| baseten-byok | $0 | $0 |
| siliconflow-byok | $0 | $0 |
| gmicloud-byok | $0 | $0 |
| nousresearch-byok | $0 | $0 |
| venice-byok | $0 | $0 |
| commandcode-byok | $0 | $0 |
| opencode-go-byok | $0 | $0 |

## Benchmarks

- **GPQA Diamond**: 0.9
- **HLE**: 0.4
- **SciCode**: 0.6
- **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://platform.moonshot.cn/docs/kimi-k3