HASTATAgent stack guide Unknown
Qwen 2.5 VL 72B Instruct
Qwen vision-language model for visual reasoning, documents, and agent tasks
Fresh · fetched 2026-08-17T02:11:57.739Z · Models.dev(opens in a new tab)
Minimum context128K
Output128K
Providers8
CapabilitiesTool calling, Reasoning, Image input
Provider offers
| Providers | Input / 1M | Output / 1M | Cache read / 1M | Context / output | Updated |
|---|---|---|---|---|---|
 Qiniuqwen2.5-vl-72b-instruct | Unavailable | Unavailable | Unavailable | 128K | 2025-08-05 |
 Cortecsqwen2.5-vl-72b-instruct | $0.25 | $0.75 | Unavailable | 32K | 2025-01-27 |
 NanoGPTTEE/qwen2.5-vl-72b-instruct | $0.70 | $0.70 | $0.35 | 64K | 2025-02-01 |
 OpenRouterqwen/qwen2.5-vl-72b-instruct | $0.80 | $1.00 | $0.40 | 128K | 2025-02-01 |
 Nebius Token FactoryQwen/Qwen2.5-VL-72B-Instruct | $0.25 | $0.75 | $0.025 | 128K | 2026-02-04 |
 OVHcloud AI Endpointsqwen2.5-vl-72b-instruct | $1.01 | $1.01 | Unavailable | 32K | 2025-03-31 |
 NovitaAIqwen/qwen2.5-vl-72b-instruct | $0.80 | $0.80 | Unavailable | 32K | 2025-03-25 |
 Kilo Gatewayqwen/qwen2.5-vl-72b-instruct | $0.80 | $1.00 | $0.40 | 128K | 2025-02-01 |
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, audio, video → text