All models
Alibaba (Qwen)
Qwen3.5-Flash fast
alibaba/qwen3-5-flash-02-23
The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the...
Input / 1M
$0.065
USD per million tokens
Output / 1M
$0.26
USD per million tokens
Est. cost / token
$0.000000114
$0.11 per 1M, 3:1 mix
Context window
1M
max output 66K
Major features
VisionReasoningJSON schemaTools
Task suitability (heuristic 1–5, not a benchmark)
- coding3
- reasoning3
- math3
- summarization4
- extraction4
- classification4
- chat3
- creative3
- translation4
- vision3
- long context5
- agentic3
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.065 | $0.26 | — | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.065
- Output
- $0.26
- Blended (3:1)
- $0.11
Details
- Company
- Alibaba (Qwen)
- Version
- 3.5
- Family
- Qwen
- Released
- 2026-02-25
- Parameters
- Undisclosed
- Max output
- 66K
- Open weights
- No
- Inputs
- image, text, video
- Last synced
- 25 min ago