Qwen3.5 397B A17B
by Alibaba (Qwen) · qwen/qwen3.5-397b-a17b · #253 cheapest of 457 paid models
Prices updated Nov 18, 2026, 4:47 PM UTC · refreshed nightly
The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.45
per 1M tokens
Output
$3.00
per 1M tokens
Blended (3:1)
$1.09
3 input : 1 output
Cache read
$0.22
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Qwen3.5 397B A17B with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $1.09 | $0.0489 | — |
| 50% | $1.00 | $0.0374 | −24% |
| 90% | $0.932 | $0.0282 | −42% |
*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 | $0.001125 | $1.13 |
| Document summary | 8,000 | 1,000 | $0.0066 | $6.60 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0195 | $19.50 |
| Long-context analysis | 150,000 | 5,000 | $0.0825 | $82.50 |
Performance
Intelligence Index
—
AA composite quality
Coding Index
48.2
Math Index
—
Agentic Index
8.3
Output speed
—
median
Time to first token
—
median
Time to first answer
—
after reasoning tokens
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 1,182 |
| UI components | 1,152 |
| Data viz | 1,171 |
| SVG | 1,128 |
| 3D | 1,141 |
| Game dev | 1,129 |
| Code categories | 1,168 |
Specs
Context window
262K
tokens
Max output
82K
tokens
Input modalities
text, image, video
Tokenizer
Qwen3