# DeepSeek V4 Flash Thinking API Pricing

As of October 10, 2026, DeepSeek V4 Flash Thinking costs $0.25 per 1M input tokens and $1.75 per 1M output tokens on LibertAI. It has a 200,000-token context window and returns up to 200,000 tokens per response.

- Page: https://models.litellm.ai/models/deepseek-v4-flash-thinking
- Lab: DeepSeek
- LiteLLM model name: `libertai/deepseek-v4-flash-thinking`
- Context window: 200,000 tokens
- Max output: 200,000 tokens
- Added to LiteLLM: June 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 |
|---|---|---|---|---|---|---|---|
| LibertAI | `libertai/deepseek-v4-flash-thinking` | $0.25 | $1.75 | – | – | – | 200K |

## Cost examples

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

- LibertAI: $1.375

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

- LibertAI: $2.85

## Features

Supported: Function calling, Reasoning.
Not supported: Image input.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="libertai/deepseek-v4-flash-thinking",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does DeepSeek V4 Flash Thinking cost?

DeepSeek V4 Flash Thinking costs $0.25 per 1M input tokens and $1.75 per 1M output tokens on LibertAI.

### What is the context window of DeepSeek V4 Flash Thinking?

DeepSeek V4 Flash Thinking has a 200,000-token context window and returns up to 200,000 tokens per response.

### Which providers offer DeepSeek V4 Flash Thinking?

DeepSeek V4 Flash Thinking is available from LibertAI through LiteLLM, using the model name libertai/deepseek-v4-flash-thinking.

### How do I call DeepSeek V4 Flash Thinking with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="libertai/deepseek-v4-flash-thinking", 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 DeepSeek V4 Flash Thinking support?

DeepSeek V4 Flash Thinking supports function calling and reasoning. It does not support image input.

### When did LiteLLM add DeepSeek V4 Flash Thinking?

DeepSeek V4 Flash Thinking was added to LiteLLM's model price file in June 2026.

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