Qwen3 Max Thinking
by Alibaba (Qwen) · qwen/qwen3-max-thinking · #211 cheapest of 325 paid models
Prices updated Jul 22, 2026, 1:31 AM UTC · refreshed hourly
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...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.78
per 1M tokens
Output
$3.90
per 1M tokens
Blended (3:1)
$1.56
3 input : 1 output
Cache read
—
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Qwen3 Max Thinking (no cache-read rate published — hits billed as normal input).
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $1.56 | $0.0835 | — |
| 50% | $1.56 | $0.0835 | −0% |
| 90% | $1.56 | $0.0835 | −0% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.00156 | $1.56 |
| Document summary | 8,000 | 1,000 | $0.0101 | $10.14 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0312 | $31.20 |
| Long-context analysis | 150,000 | 5,000 | $0.1365 | $136.50 |
Performance
Intelligence Index
31.7
AA composite quality
Coding Index
—
Math Index
—
Agentic Index
—
Output speed
0 tok/s
median
Time to first token
0s
median
Time to first answer
0s
after reasoning tokens
Artificial Analysis benchmarks
| Benchmark | Score |
|---|---|
| GPQA Diamond | 86.1% |
| Humanity's Last Exam | 26.2% |
| SciCode | 43.1% |
| IFBench | 70.7% |
| AA-LCR (Long Context Reasoning) | 66.0% |
| Terminal-Bench Hard | 24.2% |
| τ²-Bench (Telecom) | 83.6% |
Specs
Context window
262K
tokens
Max output
33K
tokens
Input modalities
text
Tokenizer
Qwen