Qwen3.7 Max
by Alibaba (Qwen) · qwen/qwen3.7-max · #230 cheapest of 325 paid models
Prices updated Jul 22, 2026, 1:31 AM UTC · refreshed hourly
Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$1.48
per 1M tokens
Output
$4.42
per 1M tokens
Blended (3:1)
$2.21
3 input : 1 output
Cache read
$0.295
per 1M cached tokens
Cache write
$1.84
per 1M tokens
Cache & batch economics
Effective prices for Qwen3.7 Max with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $2.21 | $0.1549 | — |
| 50% | $1.77 | $0.0959 | −38% |
| 90% | $1.42 | $0.0487 | −69% |
*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 | $0.002065 | $2.06 |
| Document summary | 8,000 | 1,000 | $0.0162 | $16.23 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0531 | $53.10 |
| Long-context analysis | 150,000 | 5,000 | $0.2434 | $243.38 |
Performance
Intelligence Index
46
AA composite quality
Coding Index
66
Math Index
—
Agentic Index
30.6
Output speed
207 tok/s
median
Time to first token
1.55s
median
Time to first answer
13.16s
after reasoning tokens
Artificial Analysis benchmarks
| Benchmark | Score |
|---|---|
| GPQA Diamond | 92.3% |
| Humanity's Last Exam | 38.1% |
| SciCode | 48.8% |
| IFBench | 80.5% |
| AA-LCR (Long Context Reasoning) | 69.0% |
| Terminal-Bench Hard | 50.8% |
| Terminal-Bench 2.1 | 74.5% |
| τ²-Bench (Telecom) | 94.7% |
| τ³-Bench Banking | 10.9% |
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 1,291 |
| Web apps | 1,253 |
| Full-stack | 1,225 |
| Mobile apps | 1,208 |
| Android native | 1,182 |
| UI components | 1,313 |
| Data viz | 1,304 |
| SVG | 1,267 |
| 3D | 1,310 |
| Game dev | 1,315 |
| Agentic game dev | 1,180 |
| Godot game dev | 1,248 |
| HTML slides | 1,191 |
| Python→PPTX slides | 1,229 |
| Code categories | 1,299 |
| ASCII art | 1,261 |
Specs
Context window
1M
tokens
Max output
66K
tokens
Input modalities
text
Tokenizer
Qwen