Trinity Large Thinking

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

arcee-ai/trinity-large-thinking

Organization: arcee-ai
Family: trinity
Providers: 6
Context: 524,288
Output limit: 262,144
Knowledge: —
Release: 2026-04-01
Updated: 2026-05-28
Weights: Open
Input: text
Output: text
Capabilities: Tools, Reasoning, Temperature

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

6 offers · USD per million tokens

Provider	Model ID	Context	Output	Input / output · 1M	Reasoning	Tools	Structured	Details
Arcee	trinity-large-thinking	262,144	262,144	$0.25 / $0.80	Yes	Yes	—	View
DigitalOcean	arcee-trinity-large-thinking	128,000	32,000	$0.25 / $0.90	Yes	Yes	—	View
Kilo Gateway	arcee-ai/trinity-large-thinking	262,144	80,000	$0.25 / $0.80	Yes	Yes	No	View
NanoGPT	arcee-ai/trinity-large-thinking	262,144	80,000	$0.25 / $0.90	Yes	Yes	No	View
Arcee AIvia OpenRouter	arcee-ai/trinity-large-thinking unknown	262,144	80,000	$0.25 / $0.80	Yes	Yes	No	View
Vercel AI Gateway	arcee-ai/trinity-large-thinking	262,100	80,000	$0.25 / $0.90	Yes	Yes	—	View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens

Input from$0.25Per 1M input tokens

Output from$0.80Per 1M output tokens

Available offers6Across 6 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 1 lowest-priced configuration

InputOutput

Arcee AIarcee-ai

$0.25$0.80

arcee-ai/trinity-large-thinkingObserved Oct 4, 2026, 11:31 AM UTC

Input: $0.25
Output: $0.80
Cache read: $0.06

Hosting prices through OpenRouter All endpoints and cache rates

Endpoint	Input / 1M	Output / 1M	Cache read / 1M	Cache write / 1M
Arcee AIarcee-ai	$0.25	$0.80	$0.06	—

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 1 endpoint

P50P75P90P99

Arcee AIarcee-ai

489–3,682.5 ms

All latency percentiles 1 endpoints

Endpoint	P50	P75	P90	P99
Arcee AIarcee-ai	489 ms	750.25 ms	1,487 ms	3,682.5 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 1 endpoint

P50P75P90P99

Arcee AIarcee-ai

193.5–316.5 t/s

All throughput percentiles 1 endpoints

Endpoint	P50	P75	P90	P99
Arcee AIarcee-ai	193.5 t/s	252.25 t/s	268 t/s	316.5 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window

Availability by endpointCurrent overlapping windows · 1 endpoint

Endpoint5 minutes30 minutes24 hours

Arcee AIarcee-aiObserved Oct 4, 2026, 11:31 AM UTC

—

100%

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Benchmarks

Review attributed evaluation results on each source's original scale.

External evaluations

arcee-ai/trinity-large-thinkingObserved Oct 4, 2026, 11:31 AM UTC

Benchmark profileArtificial Analysis · shared source scale from 0 to 30

Coding

25.8

Agentic

Intelligence

10.8

Design Arena	Category	Elo	Win rate	Rank
models	3d	1,097	41.3%	85
models	asciiart	1,052	37.1%	65
models	codecategories	1,123	40.1%	86
models	dataviz	1,106	39.3%	92
models	gamedev	1,092	38.4%	92
models	svg	1,015	35.2%	81
models	uicomponent	1,052	32.6%	98
models	website	1,144	41.3%	86

Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.

Detailed evaluations

Evaluation	Configuration	Source	Results	Details
Composite indices	Trinity Large Thinkingarcee-ai/trinity-large-thinking	Artificial Analysis	Intelligence 10.8 · Coding 25.8 · Agentic 1	Details
models · 3d	Trinity Large Thinkingarcee-ai/trinity-large-thinking	Design Arena	1,097 Elo	Details
models · dataviz	Trinity Large Thinkingarcee-ai/trinity-large-thinking	Design Arena	1,106 Elo	Details
models · asciiart	Trinity Large Thinkingarcee-ai/trinity-large-thinking	Design Arena	1,052 Elo	Details
models · gamedev	Trinity Large Thinkingarcee-ai/trinity-large-thinking	Design Arena	1,092 Elo	Details
models · svg	Trinity Large Thinkingarcee-ai/trinity-large-thinking	Design Arena	1,015 Elo	Details
models · codecategories	Trinity Large Thinkingarcee-ai/trinity-large-thinking	Design Arena	1,123 Elo	Details
models · website	Trinity Large Thinkingarcee-ai/trinity-large-thinking	Design Arena	1,144 Elo	Details
models · uicomponent	Trinity Large Thinkingarcee-ai/trinity-large-thinking	Design Arena	1,052 Elo	Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 4, 2026.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications

arcee-ai/trinity-large-thinkingObserved Oct 4, 2026, 11:31 AM UTC

Context: 262,144
Maximum output: 80,000
Tokenizer: Other
Input: text
Output: text
Moderation: No
Added to OpenRouter: 2026-04-01

Base URLhttps://openrouter.ai/api/v1

Model IDarcee-ai/trinity-large-thinking

Version IDarcee-ai/trinity-large-thinking

Weights IDarcee-ai/Trinity-Large-Thinking

Reasoning

Required: Yes
Enabled by default: Not reported
Default effort: —
Supported efforts: —

Supported parameters

include_reasoning
max_tokens
reasoning
temperature
tool_choice
tools
top_k
top_p

Default parameters

top p: 0.8
temperature: 0.3

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does Trinity Large Thinking cost?

Listed rates start at $0.25 per million input tokens and $0.80 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer Trinity Large Thinking?

There are 6 cataloged offers across 6 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 524,288 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: Yes. Structured output: Not reported. Support can vary by endpoint.

Resources

OpenMDW-1.1

Model card ↗Announcement ↗License ↗Hugging Face ↗

Catalog history · 2 recorded revisions

Metadata observations since this model was first cataloged. These are not model release versions.

Sep 14, 2026 · 2ab105d71911
Sep 12, 2026 · b37eff51bfe1