All AI models · LLM benchmarks · Methodology

Arcee AI

Trinity Large Thinking

Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use

Model facts

Context window
262K tokens
Maximum output
8K tokens
Cheapest paid input
$0.25 per 1M tokens
Cheapest paid output
$0.8 per 1M tokens
Open weights
yes
Providers
6

Capabilities and modalities

reasoning, tool calling, temperature control, open weights, text.

Artificial Analysis benchmarks

Compare this model on the full LLM benchmark leaderboard.

ConfigurationAAICodingMathOutput tokens/s
default18.725.8not measured320.4

Observed price history

  • 2026-08-24: $0.25 input / $0.8 output per 1M tokens
  • 2026-08-30: $0.25 input / $0.8 output per 1M tokens

API providers

  • OpenRouter — model id arcee-ai/trinity-large-thinking; $0.25 input / $0.8 output per 1M tokens; provider documentation
  • Arcee — model id trinity-large-thinking; $0.25 input / $0.8 output per 1M tokens; provider documentation
  • Kilo Gateway — model id arcee-ai/trinity-large-thinking; $0.25 input / $0.8 output per 1M tokens; provider documentation
  • NanoGPT — model id arcee-ai/trinity-large-thinking; $0.25 input / $0.9 output per 1M tokens; provider documentation
  • Vercel AI Gateway — model id arcee-ai/trinity-large-thinking; $0.25 input / $0.9 output per 1M tokens; provider documentation
  • Arena — model id trinity-large-thinking; not published input / not published output per 1M tokens; provider documentation