Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use
Trinity Large Thinking by arcee-ai is offered by 5 providers on this page. Its official list price is $0.25 per 1M input tokens and $0.80 per 1M output tokens.
Artificial Analysis rates it 10.8 on the Intelligence Index, with 25.8 for coding and 1 for agentic tasks. Against its lowest blended price of $0.388 per 1M, that is roughly 28 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 342 tokens per second, with 1.26s to the first token. Running one task of the Artificial Analysis suite costs about $0.1188, which reflects how many tokens its reasoning consumes rather than the unit price alone.
The context window is 262,144 tokens at the reference host, but hosts report different limits, from 262,100 to 262,144, so the usable window depends on the provider you pick. It supports reasoning and tool use. The weights are open, so it can also be self-hosted or served through a gateway of your choice.
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Kilo Gateway | Gateway | $0.25 | $0.80 | $0.06 | — | 262,144 | 80,000 | |
| OpenRouter | Gateway | $0.25 | $0.80 | $0.06 | — | 262,144 | 80,000 | |
| ArceeOfficial | First-party | $0.25 | $0.80 | $0.06 | — | 262,144 | 262,144 | beta |
| NanoGPT | Gateway | $0.25 | $0.90 | $0.13 | — | 262,144 | 80,000 | |
| Vercel AI Gateway | Cloud | $0.25 | $0.90 | — | — | 262,100 ⚠ | 80,000 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Interleaved thinking (reasoning between tool calls) is declared by 1 of 5 providers.
3 / 5 providers expose no reasoning control (reasoning_options: []).
Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.