# Moonshot AI Kimi K2.5 API

> Kimi K2.5 is Moonshot AI's open-source native multimodal agentic model, built by continuing pretraining of Kimi K2 on about 15 trillion mixed visual and text tokens. It is a 1T-parameter mixture-of-experts model with 32B active parameters and a 256K-token context, offering instant and thinking modes. Moonshot highlights coding from visual specifications such as UI designs and an agent swarm mode that splits complex tasks across parallel sub-agents; Kimi K2.6 later succeeded it.

Source: https://www.sandbase.ai/models/moonshotai/kimi-k2.5
API reference: https://www.sandbase.ai/models/moonshotai/kimi-k2.5/docs

## Facts

- Provider: Moonshot AI
- Type: Language model
- Model ID: `moonshotai/kimi-k2.5`
- Price: $0.60 per 1M input tokens, $3 per 1M output tokens
- Context window: 262.1K tokens, up to 65.5K output tokens
- Capabilities: chat, vision, reasoning, structured output, function calling
- Billing: pay per use from one SandBase balance; no provider account or subscription needed

## Call it

- Chat Completions API: `POST https://api.sandbase.ai/v1/chat/completions`

```bash
curl -X POST https://api.sandbase.ai/v1/chat/completions \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "moonshotai/kimi-k2.5",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "max_tokens": 2048
}'
```

## FAQ

### How do I call Moonshot AI Kimi K2.5 through SandBase?

Create a SandBase API key, then send requests with the model ID "moonshotai/kimi-k2.5" to Chat Completions API (/v1/chat/completions) at https://api.sandbase.ai. The request examples on this page show the exact payload.

### How much does Moonshot AI Kimi K2.5 cost?

$0.60 per 1M input tokens and $3 per 1M output tokens, billed per request from your SandBase balance. Discounts, when available, are shown in the pricing on this page.

### What is the context window of Moonshot AI Kimi K2.5?

262.1K tokens of context, with up to 65.5K output tokens per response.

### How does Moonshot AI Kimi K2.5 score on benchmarks?

Moonshot AI Kimi K2.5 scores 23.5 on the Artificial Analysis Intelligence Index (v4.3), ranking #54 of 83 models on SandBase; Coding Index 46.8. Source: Artificial Analysis, measured as Kimi K2.5 (Reasoning).

### Which features does Moonshot AI Kimi K2.5 support?

Moonshot AI Kimi K2.5 supports vision (image input), reasoning, function calling, structured output. See Specifications above for the full list.

### Do I need a separate Moonshot AI account?

No. One SandBase API key and balance gives you access to Moonshot AI Kimi K2.5 and the other models in the catalog; you do not need to sign up with Moonshot AI separately.