Qwen3.5 Flash
Qwen vision-language model for visual reasoning, documents, and agent tasks
Cheapest input
$0.09
$/MTok · models.dev
Cheapest output
$0.36
$/MTok
Context
1M
tokens
Offers
2
1 source
Offers
Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestqwen3.5-flash | NanoGPT | $0.09 | $0.36 | $0 | 992K |
| models.devqwen3.5-flash | Alibaba / Qwen | $0.172 | $1.72 | $0 | 1M |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Attachments
- In: text
- In: image
- In: video
- Out: text
Knowledge cutoff: 2025-04Released: 2026-02-23Family: qwen
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.
- AA intelligence50.2
- AA coding70.1
- AA agentic37.4
Sources: Arena AI, Artificial Analysis. See /benchmarks.