HASTATAgent stack guide deepseek
DeepSeek: DeepSeek V4 Flash 0731
This DeepSeek V4 Flash endpoint provides the lowest cost for multi-turn conversations for this model. This is accomplished with an exceptionally low cache read price. By using this endpoint you agree prompts and completions may be retained by DeepSeek and used to train future models.
Fresh · fetched 2026-08-17T02:11:57.739Z · Models.dev(opens in a new tab)
Minimum context1.05M
Output384K
Providers1
CapabilitiesTool calling, Reasoning
Provider offers
| Providers | Input / 1M | Output / 1M | Cache read / 1M | Context / output | Updated |
|---|---|---|---|---|---|
 Kilo Gatewaydeepseek/deepseek-v4-flash:discounted | $0.14 | $0.28 | $0.003 | 1.05M | 2025-08-26 |
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 → text