Qwen3.5-35B-A3B
ModelOpen sourceActiveby Alibaba (Qwen) · family “qwen3b-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... (description from the OpenRouter listing)
in: textin: imagein: videoout: textReasoningTool useStructured output
Epoch Capabilities Index
142.5 #95 of 268
90% CI 140.0 – 144.8
Released
24 Feb 2026
Context window
262K tokens
Max output
66K tokens
Input $ / 1M tokens
$0.16
Output $ / 1M tokens
$1.30
Cached input $ / 1M
Unknown
Each benchmark shown separately with its own source
Benchmark results (5)
| Benchmark | Domain | Score | vs best recorded | Setting | Run | Source |
|---|---|---|---|---|---|---|
| LMCA | agents | 29.5% | 43% | — | — | External ↗ |
| DTBench | reasoning | 80.0% | 81% | — | — | External ↗ |
| Chess Puzzles | games | 10.0% ±3.0 | 14% | none | 30 Aug 2026 | Eval log ↗ |
| OTIS Mock AIME 2024-2025 | math | 70.0% ±6.0 | 70% | none | 30 Aug 2026 | Eval log ↗ |
| GPQA diamond | science | 83.5% ±2.2 | 87% | — | 28 Aug 2026 | Eval log ↗ |
Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.
API list price over time
Price history
$ per 1M tokens
9 recorded prices on 3 Mar 2026 (OpenRouter listing + Internet Archive snapshots); re-read on every data refresh, most recently 10h ago. Steps show when the price changed.
Events
- Price cut-48%Qwen3.5-35B-A3B API price cutOpenRouter models API
- BenchmarkEpoch AI evaluates Qwen3.5-35B-A3BEpoch AI Benchmarking Hub
- BenchmarkEpoch AI evaluates Qwen3.5-35B-A3BEpoch AI Benchmarking Hub
- Open releaseMajorQwen releases Qwen3.5-35B-A3BEpoch AI Benchmarking Hub