Qwen3 Max
by Alibaba (Qwen) · qwen/qwen3-max · #212 cheapest of 325 paid models
Prices updated Jul 22, 2026, 1:41 AM UTC · refreshed hourly
Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version. 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
$0.156
per 1M cached tokens
Cache write
$0.975
per 1M tokens
Cache & batch economics
Effective prices for Qwen3 Max with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $1.56 | $0.0835 | — |
| 50% | $1.33 | $0.0523 | −37% |
| 90% | $1.14 | $0.0273 | −67% |
*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
24
AA composite quality
Coding Index
—
Math Index
80.7
Agentic Index
—
Output speed
60 tok/s
median
Time to first token
1.76s
median
Time to first answer
1.76s
after reasoning tokens
Artificial Analysis benchmarks
| Benchmark | Score |
|---|---|
| MMLU-Pro | 84.1% |
| GPQA Diamond | 76.4% |
| Humanity's Last Exam | 11.1% |
| LiveCodeBench | 76.7% |
| SciCode | 38.3% |
| AIME 2025 | 80.7% |
| IFBench | 44.1% |
| AA-LCR (Long Context Reasoning) | 46.7% |
| Terminal-Bench Hard | 20.5% |
| τ²-Bench (Telecom) | 74.3% |
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 1,146 |
| UI components | 1,119 |
| Data viz | 1,141 |
| SVG | 1,058 |
| 3D | 1,132 |
| Game dev | 1,153 |
| Code categories | 1,143 |
| ASCII art | 1,170 |
Specs
Context window
262K
tokens
Max output
33K
tokens
Input modalities
text
Tokenizer
Qwen3