Trinity Large Thinking
AI model by Arcee AI. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. Trinity Large Thinking is a budget-tier option from Arcee AI at $0.90/M output tokens. Despite the low price, it scores competitively on Coding Index (25.8) and Intelligence Index (18.7) — making it a candidate for high-volume production workloads where unit cost dominates.
Latency. On latency, Trinity Large Thinking reports 314 tok/s output speed and 1150ms time-to-first-token. Output speed is in the normal range — most chat and completion applications will be token-bound, not streaming-bound.
Cost model. For a workload of 1M input tokens + 100K output tokens, Trinity Large Thinking costs $0.34 per million input-equivalent requests. Multiply by your monthly request volume to project the bill, and compare against the speed/correctness profile above to decide if the trade-off is worth it for your workload.
Editorial summary generated from public pricing and benchmark data (Artificial Analysis API). All numbers are sourced — see the Artificial Analysis methodology for benchmark definitions. Last refreshed 2026-09-06.
Compare with similar models
| Model | Input | Output | Speed |
|---|---|---|---|
Trinity Large ThinkingCurrent | $0.25 | $0.90 | 314 tok/s |
| GLM-4.6V (Non-reasoning) | $0.30 | $0.90 | 72 tok/s |
| Agnes 2.5 Pro Alpha | $0.45 | $0.90 | 202 tok/s |
| GLM-4.6V (Reasoning) | $0.30 | $0.90 | 55 tok/s |
| DeepSeek V3 (Dec '24) | $0.36 | $0.89 | — |
| Llama 4 Maverick | $0.26 | $0.91 | 86 tok/s |