Qwen3 Max Thinking
Pick up to 3 models · pricing, context and capabilities · simulate your product cost
Data updated on September 30, 2026· 217 models
Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning.
- Reasoning estimated
- Speed estimated
- Input
- Output
- Context
- 262 K tokens
- Max output
- 66 K
- Input, $ per 1M tokens
- $0.780
- Output, $ per 1M tokens
- $3.90
- Cache read, $ per 1M
- —
- Batch (input / output)
- —
- Tool calling
- Yes
- Released
- 02/09/2026
- Knowledge cutoff
- —
- API id
- qwen/qwen3-max-thinking
Summary from the data
Qwen3 Max Thinking is a Qwen model available by API since 02/09/2026. It costs $0.780 per million input tokens and $3.90 per million output tokens, accepts 262 K tokens of context and generates up to 66 K tokens per response. Input: text; output: text. It has a reasoning mode. It supports tool calling. With 10,000 requests a month of 1,500 input and 400 output tokens it would cost about $27.30 a month.
Compare Qwen3 Max Thinking with…
- Qwen3 Max Thinking vs Qwen3.8 Max Prime
- Qwen3 Max Thinking vs Qwen3.8 Omni Flash
- Qwen3 Max Thinking vs Qwen3.8 Max (0902)
- Qwen3 Max Thinking vs Qwen3.8 Flash
- Qwen3 Max Thinking vs Claude Sonnet 5.5
- Qwen3 Max Thinking vs DeepSeek V4.1 Flash
- Qwen3 Max Thinking vs Gemini 3.8 Flash
- Qwen3 Max Thinking vs Mistral Medium 3.5
- Qwen3 Max Thinking vs Kimi K3
- Qwen3 Max Thinking vs GPT-6.1 Sol
What would your product cost?
Estimate the monthly cost with your app's real volume. List prices, no cache or batch discounts.
The 6 cheapest for this scenario (chat, last 12 months)
- 1Lyria 3 Pro Preview Google$0.00
- 2Lyria 3 Clip Preview Google$0.00
- 3Qwen3.7 Flash Qwen$0.97
- 4DeepSeek V4 Flash 0731 DeepSeek$1.55
- 5Ministral 3 3B 2512 Mistral$1.90
- 6Qwen3.5-Flash Qwen$2.02
Frequently asked questions
How much does Qwen3 Max Thinking cost per million tokens?
Qwen3 Max Thinking costs $0.780 per million input tokens and $3.90 per million output tokens (USD, list price). Cache read: not published. Batch tier: not published.
What context window does Qwen3 Max Thinking have?
Qwen3 Max Thinking accepts 262 K tokens of context per request and generates up to 66 K tokens per response.
Does Qwen3 Max Thinking accept images, audio or files?
Input: text. Output: text.
Does Qwen3 Max Thinking have a reasoning mode and tool calling?
It has a reasoning mode. It supports tool calling.
When was Qwen3 Max Thinking released and what is its knowledge cutoff?
Qwen3 Max Thinking has been available by API since 02/09/2026. Knowledge cutoff: not published.
What would an app built on Qwen3 Max Thinking cost?
With 10,000 requests a month of 1,500 input and 400 output tokens, Qwen3 Max Thinking would cost about $27.30 a month at list price, without cache or batch discounts.
What is the API id of Qwen3 Max Thinking?
The id is qwen/qwen3-max-thinking. It is the name passed in the model parameter of the API (or on OpenRouter).
Where do the prices come from and how often are they updated?
From the public catalogs of OpenRouter, models.dev and LiteLLM, which publish each provider's list prices. They sync once a day and the last update date is shown above the comparison.
What does price per million tokens mean?
It is what the provider charges per million tokens you send (input) or the model generates (output). A token is roughly 4 characters. Output almost always costs more than input.
Sources: OpenRouter, models.dev and LiteLLM. Prices in USD per million tokens, list price, no volume discounts. Prompt tokens are an estimate; each provider's tokenizer may differ.