Atlas / Models / Qwen / Qwen: Qwen3 Max Thinking

Qwen: Qwen3 Max Thinking✓ Catalog verified

qwen/qwen3-max-thinking

Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it delivers major gains in factual accuracy, complex reasoning, instruction following, alignment with human preferences, and agentic behavior.

Input price
$0.78 /1M
Output price
$3.90 /1M
Context
262K
Modalities
text
Released
Feb 9, 2026
Tool calling
✓ Yes
Atlas signal
88/100
01

Overview

Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it delivers major gains in factual accuracy, complex reasoning, instruction following, alignment with human preferences, and agentic behavior.

Access: available through the official Qwen API. Context window: 262K.

Pricing and metadata from the ModelsAtlas catalog.Last refreshed Aug 5, 2026
02

Specifications

API identifierqwen/qwen3-max-thinking
ProviderQwen
Model typeText LLM
Context window262K catalog
Input modalitiestext
Output modalitiestext
ReleasedFeb 9, 2026
TokenizerQwen
ModeratedNo
Architecture modalitytext->text
Supported parameters
include_reasoningmax_tokenspresence_penaltyreasoningresponse_formatseedstructured_outputstemperaturetool_choicetoolstop_p
Source: provider documentation + catalog feedMethodology →

API defaults

Default parameters
{
  "top_p": null,
  "temperature": null,
  "frequency_penalty": null
}
03

Pricing

Live pricing components for qwen/qwen3-max-thinking as published in the catalog.

$0.78
Input /1M
$3.90
Output /1M
Per request
Per image
Pricing componentRaw unit priceNormalizedUnit
Prompt tokens$7.8e-7$0.78 / 1MPer input token
Completion tokens$0.0000039$3.90 / 1MPer output token
Request feeN/AN/APer request
Image feeN/AN/APer image unit
Web search feeN/AN/APer search request
Source: catalog pricing feedCompare all pricing →Cheapest models →
04

Cost calculator

Estimate monthly spend from your own token volumes.

Scale / Volume

Estimated Total Cost

$1.17Calculated from current list pricing in the ModelsAtlas catalog.
05

Capabilities

CapabilityStatusWhat it means
Visual UnderstandingNot advertisedImage and document analysis support
Audio ProcessingNot advertisedSpeech and voice aligned flows
Tool Calling✓ SupportedSupports tools / function calling
Self-Hosting✓ SupportedDeploy outside managed APIs
Derived from catalog capability tags and supported parameters
06

Capability signals

Directional signals derived from model metadata and capability tags — not official benchmark submissions.

Qwen: Qwen3 Max Thinking
MMLU Signal (Reasoning)
97signal
Coding Signal (HumanEval proxy)
88signal
Math Signal (GSM8K proxy)
83signal
Science Signal (GPQA proxy)
83signal
Estimated from metadata — not an official benchmark runAll benchmarks →Methodology →
07

Quick start

Call Qwen: Qwen3 Max Thinking through an OpenAI-compatible client.

from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="qwen/qwen3-max-thinking",
    messages=[{"role": "user", "content": "Explain quantum physics."}]
)

print(response.choices[0].message.content)
08

Alternatives

Closest models by context window from a different provider.

09

Sources & attribution

Pricing and metadata are maintained in the ModelsAtlas catalog.

Capability bars use metadata tags — directional estimates onlyHow we source and verify data →
10

Frequently asked questions

How much does Qwen: Qwen3 Max Thinking cost?

$0.78 per 1M input tokens and $3.90 per 1M output tokens on the official Qwen API.

What is the context window of Qwen: Qwen3 Max Thinking?

Qwen: Qwen3 Max Thinking supports up to 262K tokens of context.

Does Qwen: Qwen3 Max Thinking support tool / function calling?

Yes, Qwen: Qwen3 Max Thinking supports tool / function calling — you can register tools and the model will emit structured tool calls.

How do I access Qwen: Qwen3 Max Thinking?

Use the official Qwen API with the model id `qwen/qwen3-max-thinking`. See the Quick start section above for code examples.