# Qwen3 Max Thinking

> Qwen3 Max Thinking is a language model from Alibaba (Qwen), released on 9 Feb 2026. It accepts text and generates text, with a 262K-token context window and up to 66K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $0.78 per million input tokens and $3.90 per million output tokens (OpenRouter), across 1 provider we track. It is scheduled for retirement on 9 Oct 2026.

Source page: https://www.aimodel.directory/models/qwen3-max-thinking
Last verified: 4 Oct 2026

## Specifications

- **Developer:** Alibaba (Qwen)
- **Release date:** 9 Feb 2026 (source: OpenRouter, https://openrouter.ai/qwen/qwen3-max-thinking)
- **Status:** Generally available
- **Context window:** 262K (262,144 tokens) (source: OpenRouter, https://openrouter.ai/qwen/qwen3-max-thinking)
- **Max output:** 66K tokens (source: OpenRouter, https://openrouter.ai/qwen/qwen3-max-thinking)
- **Input:** Text (source: OpenRouter, https://openrouter.ai/qwen/qwen3-max-thinking)
- **Output:** Text (source: OpenRouter, https://openrouter.ai/qwen/qwen3-max-thinking)
- **Reasoning mode:** Yes (source: OpenRouter, https://openrouter.ai/qwen/qwen3-max-thinking)
- **Tool calling:** Yes (source: OpenRouter, https://openrouter.ai/qwen/qwen3-max-thinking)
- **Structured output:** Yes (source: OpenRouter, https://openrouter.ai/qwen/qwen3-max-thinking)
- **Retirement date:** 9 Oct 2026 (source: OpenRouter, https://openrouter.ai/qwen/qwen3-max-thinking)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| OpenRouter | $0.78 | $3.90 | – | 262K |

## FAQ

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

Qwen3 Max Thinking has a context window of 262,144 tokens (262K) and can generate up to 65,536 tokens in a single response, according to OpenRouter.

### How much does the Qwen3 Max Thinking API cost?

Qwen3 Max Thinking is listed from $0.78 per million input tokens and $3.90 per million output tokens (OpenRouter). Prices last verified 4 Oct 2026.

### When was Qwen3 Max Thinking released?

Alibaba (Qwen) released Qwen3 Max Thinking on 9 Feb 2026, according to OpenRouter.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Qwen3 Max Thinking", https://www.aimodel.directory/models/qwen3-max-thinking