# Qwen3 Max Thinking API Pricing

As of October 10, 2026, Qwen3 Max Thinking costs $1.20 per 1M input tokens and $6.00 per 1M output tokens on DeepInfra, with cache reads at $0.24 per 1M tokens. It has a 256,000-token context window.

- Page: https://models.litellm.ai/models/qwen3-max-thinking
- Lab: Alibaba
- LiteLLM model name: `deepinfra/Qwen/Qwen3-Max-Thinking`
- Context window: 256,000 tokens
- Added to LiteLLM: August 27, 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 |
|---|---|---|---|---|---|---|---|
| DeepInfra | `deepinfra/Qwen/Qwen3-Max-Thinking` | $1.20 | $6.00 | $0.24 | – | – | 256K |

## Cost examples

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

- DeepInfra: $5.40

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

- DeepInfra: $13.20

## Features

Supported: Function calling, Structured output, Prompt caching.
Not supported: Image input.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="deepinfra/Qwen/Qwen3-Max-Thinking",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Qwen3 Max Thinking cost?

Qwen3 Max Thinking costs $1.20 per 1M input tokens and $6.00 per 1M output tokens on DeepInfra, with cache reads at $0.24 per 1M tokens.

### What is the context window of Qwen3 Max Thinking?

Qwen3 Max Thinking has a 256,000-token context window.

### Which providers offer Qwen3 Max Thinking?

Qwen3 Max Thinking is available from DeepInfra through LiteLLM, using the model name deepinfra/Qwen/Qwen3-Max-Thinking.

### How do I call Qwen3 Max Thinking with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="deepinfra/Qwen/Qwen3-Max-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 Qwen3 Max Thinking support?

Qwen3 Max Thinking supports function calling, structured output and prompt caching. It does not support image input.

### When did LiteLLM add Qwen3 Max Thinking?

Qwen3 Max Thinking was added to LiteLLM's model price file on August 27, 2026.

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