HASTATAgent stack guide Unknown
qwen3-vl-235b-a22b
Qwen3 VL 235B A22B is a 235B-parameter MoE vision-language flagship model (≈22B active) designed for frontier-level multimodal understanding across text, images, documents, and long videos.
Fresh · fetched 2026-08-17T02:11:57.739Z · Models.dev(opens in a new tab)
Minimum context256K
Output256K
Providers4
CapabilitiesTool calling, Reasoning, Image input
Provider offers
| Providers | Input / 1M | Output / 1M | Cache read / 1M | Context / output | Updated |
|---|---|---|---|---|---|
 Cortecsqwen3-vl-235b-a22b | $0.62 | $3.12 | $0.052 | 256K | 2026-01-13 |
 Alibaba (China)qwen3-vl-235b-a22b | $0.29 | $1.15 | Unavailable | 128K | 2025-04 |
 Alibabaqwen3-vl-235b-a22b | $0.70 | $2.80 | Unavailable | 128K | 2025-04 |
 Venice AIqwen3-vl-235b-a22b | $0.21 | $1.90 | $0.10 | 128K | 2026-06-11 |
Lowest reported provider price in USD per 1M tokens; unavailable is not free. Provider documentation remains authoritative. Catalogue presence is not an uptime, security, or quality endorsement.
Source metadata and limitations
Capabilities are source-reported. Tool calling does not prove quality in a particular harness. Prices and limits can change.
Modalities: text, image → text