Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use
5 providers
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Reasoning-tuned 26B MoE model with 3B active parameters for agents, tools, and multi-step workloads
2 providers
| Model | Creator | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| Trinity Large Thinkingarcee-ai/trinity-large-thinking | 524.288K | $0.25 | $0.9 | 2026-04-01 | |||
| Trinity Miniarcee-ai/trinity-mini | 131.072K | $0.045 | $0.15 | 2025-12-01 |