NEWMEN
← back to all models

Arcee AI: Trinity Large Thinking

arcee-ai/trinity-large-thinking

Arceeopen-weight262K context3 providersIntelligence 50.0· est.

Cheapest provider

$0.22 / 1M

Parasail

Fastest provider (p95)

272 tok/s

Arcee AI

Intelligence (estimated)

50.0

Family + generation + popularity + price tier

Per-provider performance

Latency / throughput / uptime measured across providers over the last 30 minutes of live traffic. Atlas’s router weighs these per call (with the eval-gate signal) when picking a variant for Standard and Batch tiers.

ProviderQuantInput $/1MOutput $/1MLatency p50 / p95Throughput p50 / p95Uptime 30mSuccess
Parasailq8· fp8$0.2200$0.8500651ms / 2179ms75 / 118.5 tok/s100.00%97.4%
Arcee AIundisclosed$0.2500$0.8000548ms / 1159ms184 / 272.2 tok/s100.0%
Veniceq8· fp8$0.3125$1.1250690ms / 5533ms96 / 115.8 tok/s37.5%

“—” means live telemetry hasn’t accumulated enough recent traffic for that endpoint. “undisclosed” means the provider serves the model but doesn’t expose the quantization label (typically running fp8 / int8 internally).

Intelligence estimate

No public benchmark numbers indexed for this model yet, so the leaderboard score is derived from the catalogue data we sync: model family standing, generation, and live usage rank — applied identically to open- and closed-weight models. The heuristic ceiling sits below confirmed-benchmark frontier models so curated rankings stay clearly on top.

Want a curated score? File a benchmark report and we’ll add it to the next sync.

How Atlas routes Arcee AI: Trinity Large Thinking

  • Realtime tier — direct passthrough at the upstream’s native precision. Best for hard latency / quality guarantees.
  • Standard tier — Atlas picks the cheapest provider variant whose quantization has stayed green on your operation’s eval gates. For Arcee AI: Trinity Large Thinking that’s currently Parasail at $0.22/1M.
  • Batch tier — async, biggest discount. Roadmapped to use provider batch APIs (OpenAI / Anthropic) where available and queued spot capacity for open-weight workloads.