Arcee AI

Trinity Large Thinking

AI model by Arcee AI. Real-time pricing and benchmark data.

Pricing (per 1M tokens)

Input$0.23
Output$0.88
Blended (3:1)$0.39

Source: Artificial Analysis

Performance

Output Speed203 tok/s
Time to First Token1230ms

Median values from Artificial Analysis

Editorial Analysis

Profile. Trinity Large Thinking is a budget-tier option from Arcee AI at $0.88/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 203 tok/s output speed and 1230ms 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 $0.32 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 2026-08-15.

Compare with similar models

ModelInputOutputSpeed
Trinity Large ThinkingCurrent
$0.23$0.88203 tok/s
MiMo-V2.5-Pro
$0.43$0.8747 tok/s
DeepSeek V3 (Dec '24)
$0.36$0.89
MiMo-V2.5-Pro (Non-reasoning)
$0.43$0.8748 tok/s
DeepSeek V4 Pro (Reasoning, High Effort)
$0.43$0.8775 tok/s
DeepSeek V4 Pro (Non-reasoning)
$0.43$0.8782 tok/s

Example Costs

Single Request
$0.0007
1.0K in / 500 out
1K Requests/day
$0.6700
1.0M in / 500.0K out
10K Requests/day
$6.70
10.0M in / 5.0M out