# Kimi K2 Thinking 251104 API Pricing

As of October 10, 2026, Kimi K2 Thinking 251104 is free to use on Volcano Engine. It has a 229,376-token context window and returns up to 32,768 tokens per response.

- Page: https://models.litellm.ai/models/kimi-k2-thinking-251104
- Lab: Moonshot AI
- LiteLLM model name: `kimi-k2-thinking-251104`
- Context window: 229,376 tokens
- Max output: 32,768 tokens
- Added to LiteLLM: January 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 |
|---|---|---|---|---|---|---|---|
| Volcano Engine | `kimi-k2-thinking-251104` | $0 | $0 | – | – | – | 224K |

## Cost examples

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

- Volcano Engine: $0

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

- Volcano Engine: $0

## Features

Supported: Function calling, Reasoning, Prompt caching.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="kimi-k2-thinking-251104",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Kimi K2 Thinking 251104 cost?

Kimi K2 Thinking 251104 is free to use on Volcano Engine.

### What is the context window of Kimi K2 Thinking 251104?

Kimi K2 Thinking 251104 has a 229,376-token context window and returns up to 32,768 tokens per response.

### Which providers offer Kimi K2 Thinking 251104?

Kimi K2 Thinking 251104 is available from Volcano Engine through LiteLLM, using the model name kimi-k2-thinking-251104.

### How do I call Kimi K2 Thinking 251104 with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="kimi-k2-thinking-251104", 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.

### What features does Kimi K2 Thinking 251104 support?

Kimi K2 Thinking 251104 supports function calling, reasoning and prompt caching.

### When did LiteLLM add Kimi K2 Thinking 251104?

Kimi K2 Thinking 251104 was added to LiteLLM's model price file in January 2026.

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