All models
Alibaba (Qwen)
Qwen3.5-35B-A3B fastruns locally
alibaba/qwen3-5-35b-a3b
The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...
Input / 1M
$0.14
USD per million tokens
Output / 1M
$1.00
USD per million tokens
Est. cost / token
$0.000000355
$0.35 per 1M, 3:1 mix
Context window
262K
max output 82K
Major features
VisionOpen weightsCachingReasoningJSON schemaTools
Task suitability (heuristic 1–5, not a benchmark)
- coding3
- reasoning3
- math3
- summarization4
- extraction4
- classification4
- chat3
- creative3
- translation4
- vision3
- long context3
- agentic3
Run it locally
Will it run on my machine? →| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 18.4 GB |
| Q3_K_M | fair | 21.1 GB |
| Q4_K_Mrecommended | good | 25.7 GB |
| Q5_K_M | very good | 29.5 GB |
| Q6_K | excellent | 33.6 GB |
| Q8_0 | near-lossless | 42.8 GB |
| F16 | lossless | 78.2 GB |
Estimates. Mixture-of-experts: memory covers all parameters; only the active ones are used per token, so it runs faster than its size suggests.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.14 | $1.00 | $0.050 | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.14
- Output
- $1.00
- Cached input
- $0.050
- Blended (3:1)
- $0.35
Details
- Company
- Alibaba (Qwen)
- Version
- 3.5
- Family
- Qwen
- Released
- 2026-02-25
- Parameters
- 36B (3B active)
- Max output
- 82K
- Open weights
- Yes
- Inputs
- image, text, video
- Last synced
- 25 min ago