HASTATAgent stack guide trinity
Trinity Large Thinking
Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use
Fresh · fetched 2026-08-17T02:11:57.739Z · Models.dev(opens in a new tab)
Minimum context256K
Output256K
Providers4
CapabilitiesTool calling, Reasoning
Provider offers
| Providers | Input / 1M | Output / 1M | Cache read / 1M | Context / output | Updated |
|---|---|---|---|---|---|
 NanoGPTarcee-ai/trinity-large-thinking | $0.25 | $0.90 | $0.13 | 256K | 2026-05-28 |
 OpenRouterarcee-ai/trinity-large-thinking | $0.22 | $0.85 | $0.060 | 256K | 2026-05-28 |
 Vercel AI Gatewayarcee-ai/trinity-large-thinking | $0.25 | $0.90 | Unavailable | 256K | 2026-04-03 |
 Kilo Gatewayarcee-ai/trinity-large-thinking | $0.22 | $0.85 | $0.060 | 256K | 2026-05-28 |
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