# Kimi K2.5 Fp4 API Pricing

As of October 10, 2026, Kimi K2.5 Fp4 costs $0.50 per 1M input tokens and $2.80 per 1M output tokens on Together AI. It has a 262,144-token context window.

- Page: https://models.litellm.ai/models/kimi-k2.5-fp4
- Lab: Moonshot AI
- LiteLLM model name: `together_ai/moonshotai/Kimi-K2.5-fp4`
- Context window: 262,144 tokens
- Added to LiteLLM: September 11, 2026
- Prices updated: October 10, 2026

## Pricing by provider

Token prices in USD per 1M tokens.

| Provider | Model name | Input | Output | Cache read | Per image | Per second | Context |
|---|---|---|---|---|---|---|---|
| Together AI | `together_ai/moonshotai/Kimi-K2.5-fp4` | $0.50 | $2.80 | – | – | – | 256K |

## Cost examples

1,000 requests with 2,000 input and 500 output tokens each:

- Together AI: $2.40

100 long-document requests with 100,000 input and 2,000 output tokens each:

- Together AI: $5.56

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="together_ai/moonshotai/Kimi-K2.5-fp4",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Kimi K2.5 Fp4 cost?

Kimi K2.5 Fp4 costs $0.50 per 1M input tokens and $2.80 per 1M output tokens on Together AI.

### What is the context window of Kimi K2.5 Fp4?

Kimi K2.5 Fp4 has a 262,144-token context window.

### Which providers offer Kimi K2.5 Fp4?

Kimi K2.5 Fp4 is available from Together AI through LiteLLM, using the model name together_ai/moonshotai/Kimi-K2.5-fp4.

### How do I call Kimi K2.5 Fp4 with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="together_ai/moonshotai/Kimi-K2.5-fp4", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

### When did LiteLLM add Kimi K2.5 Fp4?

Kimi K2.5 Fp4 was added to LiteLLM's model price file on September 11, 2026.

Source: LiteLLM model price file, https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json
