How much does Trinity Large Thinking cost?

Trinity Large Thinking costs $0.25/M input tokens and $0.80/M output tokens, with separate rates for Cache Read at $0.06/M tokens.

What is the context length of Trinity Large Thinking?

Trinity Large Thinking has a 262,144 token context window. It supports up to 80,000 completion tokens.

Does Trinity Large Thinking support tool calling and structured outputs?

Yes. Trinity Large Thinking accepts tools and tool_choice for function calling. It does not support response_format, so JSON output is not enforced.

When was Trinity Large Thinking released?

Trinity Large Thinking was released on April 1, 2026.

Arcee AI: Trinity Large Thinking

Name: Arcee AI: Trinity Large Thinking
Author: arcee-ai

arcee-ai/trinity-large-thinking

Model weights

Compare

Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks. Launch video: https://youtu.be/Gc82AXLa0Rg?si=4RLn6WBz33qT--B7

This model is optimized for agentic workflows and performs best when reasoning is preserved (aka interleaved thinking). Learn how to preserve reasoning in our docs: https://openrouter.ai/docs/guides/best-practices/reasoning-tokens#preserving-reasoning

Modalities

In / Out Price

$0.25 / $0.80per 1M

Context

262K

Released

Apr 1, 2026

Benchmarks

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows where this model lands among all models on OpenRouter.

Benchmark score summary for Arcee AI: Trinity Large Thinking (Artificial Analysis and Design Arena)
Source	Benchmark	Score
Artificial Analysis	Trinity Large Thinking Intelligence Index	10.8
Artificial Analysis	Trinity Large Thinking Coding Index	25.8
Artificial Analysis	Trinity Large Thinking Agentic Index	1.0
Artificial Analysis	Trinity Large Thinking GPQA Diamond	75.2%
Artificial Analysis	Trinity Large Thinking HLE	15.8%
Artificial Analysis	Trinity Large Thinking IFBench	56.3%
Artificial Analysis	Trinity Large Thinking τ²-Bench Telecom	90.1%
Artificial Analysis	Trinity Large Thinking AA-LCR	38.0%
Artificial Analysis	Trinity Large Thinking GDPval-AA	0.0%
Artificial Analysis	Trinity Large Thinking CritPt	0.9%
Artificial Analysis	Trinity Large Thinking SciCode	40.6%
Artificial Analysis	Trinity Large Thinking Terminal-Bench Hard	22.7%
Artificial Analysis	Trinity Large Thinking AA-Omniscience Accuracy	22.5%
Artificial Analysis	Trinity Large Thinking AA-Omniscience Non-Hallucination Rate	14.1%
Design Arena	Trinity Large Thinking Models Arena 3D Elo	1110
Design Arena	Trinity Large Thinking Models Arena Asciiart Elo	1060
Design Arena	Trinity Large Thinking Models Arena Code Categories Elo	1132
Design Arena	Trinity Large Thinking Models Arena Data Visualization Elo	1113
Design Arena	Trinity Large Thinking Models Arena Game Development Elo	1102
Design Arena	Trinity Large Thinking Models Arena SVG Elo	1040
Design Arena	Trinity Large Thinking Models Arena UI Component Elo	1061
Design Arena	Trinity Large Thinking Models Arena Website Elo	1149

Providers

This model is hosted by one provider. OpenRouter forwards every request to it directly — no routing decisions to make.

Latency / throughput


	$0.25	$0.80	$0.06	0.15s	82 tps	100.00%

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)

100.00%

Availability (3d)

99.50%

Availability over the last 3 days

Last 72 hours

Availability 99.50%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.31%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and customization options.

Benchmarks

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows where this model lands among all models on OpenRouter.

Benchmark score summary for Arcee AI: Trinity Large Thinking (Artificial Analysis and Design Arena)
Source	Benchmark	Score
Artificial Analysis	Trinity Large Thinking Intelligence Index	10.8
Artificial Analysis	Trinity Large Thinking Coding Index	25.8
Artificial Analysis	Trinity Large Thinking Agentic Index	1.0
Artificial Analysis	Trinity Large Thinking GPQA Diamond	75.2%
Artificial Analysis	Trinity Large Thinking HLE	15.8%
Artificial Analysis	Trinity Large Thinking IFBench	56.3%
Artificial Analysis	Trinity Large Thinking τ²-Bench Telecom	90.1%
Artificial Analysis	Trinity Large Thinking AA-LCR	38.0%
Artificial Analysis	Trinity Large Thinking GDPval-AA	0.0%
Artificial Analysis	Trinity Large Thinking CritPt	0.9%
Artificial Analysis	Trinity Large Thinking SciCode	40.6%
Artificial Analysis	Trinity Large Thinking Terminal-Bench Hard	22.7%
Artificial Analysis	Trinity Large Thinking AA-Omniscience Accuracy	22.5%
Artificial Analysis	Trinity Large Thinking AA-Omniscience Non-Hallucination Rate	14.1%
Design Arena	Trinity Large Thinking Models Arena 3D Elo	1110
Design Arena	Trinity Large Thinking Models Arena Asciiart Elo	1060
Design Arena	Trinity Large Thinking Models Arena Code Categories Elo	1132
Design Arena	Trinity Large Thinking Models Arena Data Visualization Elo	1113
Design Arena	Trinity Large Thinking Models Arena Game Development Elo	1102
Design Arena	Trinity Large Thinking Models Arena SVG Elo	1040
Design Arena	Trinity Large Thinking Models Arena UI Component Elo	1061
Design Arena	Trinity Large Thinking Models Arena Website Elo	1149

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

1.

OpenClaw

OpenClaw is an open-source AI agent that connects to your messaging apps and takes real actions on your behalf, from running commands and browsing the web to managing files and sending emails.

2.11Btokens

2.

Hermes Agent

Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.

568Mtokens

3.

TeXposit

new

29.4Mtokens

4.

omp

new

23.3Mtokens

5.

Codex

A coding agent that helps you build and ship with AI

21.6Mtokens