Qwen3.6 35B A3B
by Alibaba (Qwen) · qwen/qwen3.6-35b-a3b · #112 cheapest of 422 paid models
Prices updated Sep 19, 2026, 6:21 PM UTC · refreshed hourly
Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.10
per 1M tokens
Output
$0.90
per 1M tokens
Blended (3:1)
$0.30
3 input : 1 output
Cache read
$0.05
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Qwen3.6 35B A3B with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.30 | $0.0111 | — |
| 50% | $0.281 | $0.0086 | −23% |
| 90% | $0.266 | $0.0066 | −41% |
*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 | $0.00032 | $0.32 |
| Document summary | 8,000 | 1,000 | $0.0017 | $1.70 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0048 | $4.80 |
| Long-context analysis | 150,000 | 5,000 | $0.0195 | $19.50 |
Performance
Intelligence Index
18.8
AA composite quality
Coding Index
41.9
Math Index
—
Agentic Index
15
Output speed
109 tok/s
median
Time to first token
1.08s
median
Time to first answer
50.59s
after reasoning tokens
Artificial Analysis benchmarks
| Benchmark | Score |
|---|---|
| GPQA Diamond | 84.1% |
| Humanity's Last Exam | 22.2% |
| SciCode | 36.6% |
| IFBench | 64.4% |
| AA-LCR (Long Context Reasoning) | 71.7% |
| Terminal-Bench Hard | 34.8% |
| Terminal-Bench 2.1 | 44.9% |
| τ²-Bench (Telecom) | 95.3% |
| τ³-Bench Banking | 9.3% |
Specs
Context window
262K
tokens
Max output
236K
tokens
Input modalities
text, image, video
Tokenizer
Qwen