HASTATAgent stack guide llama
Llama 4 Scout 17B 16E Instruct
Open Llama with long-context vision for efficient multimodal agents
Fresh · fetched 2026-08-17T02:11:57.739Z · Models.dev(opens in a new tab)
Minimum context320K
Output128K
Providers6
CapabilitiesTool calling, Image input
Provider offers
| Providers | Input / 1M | Output / 1M | Cache read / 1M | Context / output | Updated |
|---|---|---|---|---|---|
 Cloudflare Workers AI@cf/meta/llama-4-scout-17b-16e-instruct | $0.27 | $0.85 | Unavailable | 131K | 2025-04-05 |
 Deep Inframeta-llama/Llama-4-Scout-17B-16E-Instruct | $0.10 | $0.30 | Unavailable | 320K | 2025-04-05 |
 Cloudflare AI Gatewayworkers-ai/@cf/meta/llama-4-scout-17b-16e-instruct | $0.27 | $0.85 | Unavailable | 131K | 2025-04-05 |
 Azure Cognitive Servicesllama-4-scout-17b-16e-instruct | $0.20 | $0.78 | Unavailable | 128K | 2025-04-05 |
 Azurellama-4-scout-17b-16e-instruct | $0.20 | $0.78 | Unavailable | 128K | 2025-04-05 |
 NovitaAImeta-llama/llama-4-scout-17b-16e-instruct | $0.18 | $0.59 | Unavailable | 128K | 2025-04-06 |
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