Arcee Ai
Trinity Large Thinking
Flagship model for demanding analysis, coding, and production agent workflows
Cheapest input
$0.22
$/MTok · models.dev
Cheapest output
$0.85
$/MTok
Context
262K
tokens
Offers
4
2 sources
Offers
Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestarcee-ai/trinity-large-thinking | Kilo Gateway | $0.22 | $0.85 | $0.06 | 262K |
| OpenRouterarcee-ai/trinity-large-thinking | OpenRouter | $0.22 | $0.85 | $0.06 | 262K |
| models.devarcee-ai/trinity-large-thinking | NanoGPT | $0.25 | $0.9 | $0 | 262K |
| models.devarcee-ai/trinity-large-thinking | Vercel AI Gateway | $0.25 | $0.9 | $0 | 262K |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Open weights
- In: text
- Out: text
Released: 2026-04-01Family: trinity
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.
- AA intelligence18.2
- AA coding25.8
- AA agentic3.7
Sources: Arena AI, Artificial Analysis. See /benchmarks.