Qwen3.6 35B A3B
by Alibaba (Qwen) · qwen/qwen3.6-35b-a3b · #94 cheapest of 325 paid models
Prices updated Jul 22, 2026, 1:31 AM 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
$0.14
per 1M tokens
Output
$1.00
per 1M tokens
Blended (3:1)
$0.355
3 input : 1 output
Cache read
—
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Qwen3.6 35B A3B (no cache-read rate published — hits billed as normal input).
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.355 | $0.0153 | — |
| 50% | $0.355 | $0.0153 | −0% |
| 90% | $0.355 | $0.0153 | −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 | $0.00037 | $0.37 |
| Document summary | 8,000 | 1,000 | $0.00212 | $2.12 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0062 | $6.20 |
| Long-context analysis | 150,000 | 5,000 | $0.026 | $26.00 |
Performance
Intelligence Index
31.6
AA composite quality
Coding Index
41.9
Math Index
—
Agentic Index
21.4
Output speed
152 tok/s
median
Time to first token
1.42s
median
Time to first answer
36.95s
after reasoning tokens
Artificial Analysis benchmarks
| Benchmark | Score |
|---|---|
| GPQA Diamond | 84.1% |
| Humanity's Last Exam | 20.2% |
| SciCode | 35.8% |
| IFBench | 64.4% |
| AA-LCR (Long Context Reasoning) | 63.7% |
| Terminal-Bench Hard | 34.8% |
| Terminal-Bench 2.1 | 44.9% |
| τ²-Bench (Telecom) | 95.3% |
| τ³-Bench Banking | 8.7% |
Specs
Context window
262K
tokens
Max output
262K
tokens
Input modalities
text, image, video
Tokenizer
Qwen