Qwen 3 Max Thinking
Chat model by Qwen.
Qwen language model featuring a 256,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
Context window
Maximum input context length.
256K
Maker
Qwen
This model is deprecated
Qwen 3 Max Thinking has been deprecated since . It is still served on nRouter and can still be called.
Caller Notice: To help identify integrations still relying on this model, all API responses now include x-nr-model-deprecated: true and Warning: 299 - "Model deprecated" headers.
Specifications
Context window, ranked against other chat models
Proportional scale: 0 to 1.05M tokens. Not ranked, no published context window: qwen-plus-2025-09-11, voxtral-small-24b-2507, qwen3.6-plus-2026-04-02.
256.0K
tokens—
chat
Pricing
Rates are read live
Pricing for Qwen/Qwen3-Max-Thinking is fetched from the live catalogue on load, so it is never served from a cache that could outlive a repricing.
Availability
Not enough data yet
We have not collected enough health probes for this model to publish an uptime or latency figure. A percentage from a handful of samples is fabricated precision, so none is shown until the sample count supports one.
How Qwen 3 Max Thinking is billed
Billed at the provider's list price, with no per-token markup.
- Exact list price
- Tokens settle at the published rate of the model that served your call.
- Cache discounts passed through
- Provider prompt-caching discounts reach your balance with no added fee.
- Cost on every response
- Each response carries the
x-nr-request-costheader, so you can reconcile spend per request.
More from Qwen
Start building with Qwen/Qwen3-Max-Thinking
One API key, three steps. Choose your tool to begin.
Get a key
Create API keySet your API key
export NROUTER_API_KEY="<YOUR_API_KEY>"Configure Claude Code
Choose a tool, then copy its setup from the panel.
FAQs
What is Qwen 3 Max Thinking?
Qwen language model featuring a 256,000-token context window. Engineered for dialogue, instruction following, and versatile text generation.
How much does Qwen 3 Max Thinking cost?
Qwen 3 Max Thinking is billed at the provider's list price on nRouter with no per-token markup — tokens settle at the exact upstream rate. Input and output rates are read live, so see the pricing section above for the current figures.
What is the context length of Qwen 3 Max Thinking?
Qwen 3 Max Thinking supports a 256,000-token context window.
Does Qwen 3 Max Thinking support tool calling and structured outputs?
Yes. Qwen 3 Max Thinking supports tool calling (function calling), so it can invoke external tools and APIs during a conversation.
What inputs and outputs does Qwen 3 Max Thinking support?
Qwen 3 Max Thinking takes text as input and returns text as output.
How do I use Qwen 3 Max Thinking via nRouter?
Use any OpenAI-compatible client: point it at https://api.nrouter.ai/v1 with your nRouter API key and set the model to "deepinfra/Qwen/Qwen3-Max-Thinking". The quick-start panel above has a copy-paste curl command for this model.
When was Qwen 3 Max Thinking released?
Qwen 3 Max Thinking was released on October 7, 2026.
Where is the Qwen 3 Max Thinking documentation?
Start at nrouter.ai/docs. The quick-start guide (nrouter.ai/docs/getting-started/quick-start) covers API keys and your first request, and the API reference (nrouter.ai/docs/api-reference) lists every parameter.
What other text models does Qwen have?
Other Qwen text models on nRouter include Qwen Plus (nrouter.ai/models/qwen-plus-2025-09-11), Qwen 3.6 Plus (nrouter.ai/models/qwen3.6-plus-2026-04-02), Qwen 3.5 27B (nrouter.ai/models/qwen-qwen3.5-27b), Qwen Plus Latest (nrouter.ai/models/qwen-plus-latest).