Qwen3 Max ThinkingDeprecated
Benchmarks
independent evaluations · source: Artificial Analysis| Benchmark | Best score | Effort | Cost / task | |
|---|---|---|---|---|
| CritPt | 2% | default | — | |
| GPQA Diamond | 86% | default | — | |
| Humanity's Last Exam | 28% | default | — | |
| IFBench | 71% | default | — | |
| Long-Context Reasoning | 74% | default | — | |
| Omniscience | -36.6 | default | — | |
| Omniscience Accuracy | 0.3 | default | — | |
| Omniscience Non Hallucination | 0.1 | default | — | |
| SciCodeArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | 43% | — | — | |
| TerminalBench Hard | 24% | default | — | |
| τ²-bench | 84% | default | — |
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $0.78 to $1.20 per 1M tokens across 3 providers, so the dearest route costs 54% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| OpenRouterRouted quote | $0.78 | $3.90 | 1 | |||||||||||||
Standardqwen/qwen3-max-thinking
| ||||||||||||||||
| DeepInfra | $1.20 | $6.00 | 1 | |||||||||||||
Standarddeepinfra/Qwen/Qwen3-Max-Thinking
| ||||||||||||||||
| VercelVercel reseller quote | $1.20 | $6.00 | 1 | |||||||||||||
Standardalibaba/qwen3-max-thinking
| ||||||||||||||||
| Vercel (long context, from 32K tokens)Vercel reseller quote | $2.40 | $12.00 | 1 | |||||||||||||
Long contextalibaba/qwen3-max-thinking
| ||||||||||||||||
Price history
OpenRouter routed quoteOpenRouter's price is a routed quote. It moves with whichever upstream route OpenRouter prefers that day, so we do not track it as a price history.
Cost calculator
estimate your monthly spend on this modelModel IDs
copy the exact identifier for your platformFrequently asked questions
Qwen3 Max Thinking pricing, context and availabilityIs Qwen3 Max Thinking still available?
Qwen3 Max Thinking was deprecated on 2026-10-09, but 3 serving providers still list it.
How much does Qwen3 Max Thinking cost?
Qwen3 Max Thinking costs $0.78 per 1M input tokens as an OpenRouter routed quote, and $3.90 per 1M output tokens as an OpenRouter routed quote. An OpenRouter routed quote is the price of whichever upstream provider OpenRouter prefers today, so it moves day to day. Across 3 serving providers, input prices range from $0.78 to $1.20 per 1M tokens.
What is the context window of Qwen3 Max Thinking?
Qwen3 Max Thinking accepts up to 256K tokens of context and can return up to 66K output tokens.
Which providers serve Qwen3 Max Thinking?
Qwen3 Max Thinking is available from 3 serving providers, each with its own pricing and model ID. OpenRouter is currently the cheapest, as a routed quote.
What can Qwen3 Max Thinking do?
Qwen3 Max Thinking supports tool use, prompt caching and structured output.
Other Alibaba models
compare pricing across the Alibaba lineupEvery weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI