Trinity Mini

Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language model featuring 128 experts with 8 active per token. Engineered for efficient reasoning over long contexts (131k) with ro

Creator: Arcee AI
Lifecycle: Deprecated
Context: 131.1K
Max output: —
Released: Dec 1, 2025
Status: unknown

Input: $0.00 / 1M tokens
Output: $0.00 / 1M tokens
Cached read: — / 1M tokens
Cached write: — / 1M tokens
Batch discount: —%
Source: OpenRouter
Verified: Apr 5, 2026 (High)

Capabilities

Modalities: text→text
Capabilities: reasoningfunctionCallingstructuredOutputs

Official Links

Intro

https://openrouter.ai/arcee-ai/trinity-mini

Docs

https://openrouter.ai/arcee-ai/trinity-mini

Pricing

https://openrouter.ai/models

Benchmark Coverage

Benchmark	Version	Score	Date	Source	Notes

Release History

Release	Alias	Lifecycle	Release Date	Deprecation	Shutdown	Summary
Trinity Mini	arcee-ai-trinity-mini-free	Deprecated	Dec 1, 2025	Apr 10, 2026	—	Model available via OpenRouter.

Host Coverage

Host	Type	Context	Pricing Note	Differences
OpenRouter	aggregator	131.1K	$0.00/1M in · $0.00/1M out via OpenRouter	—

Migration Guidance

Change Events

Date	Type	Title	Description	Source
Dec 1, 2025	family_added	Trinity Mini published	Model made available via OpenRouter.	OpenRouter

Other models from Arcee AI

Coder Large, Maestro Reasoning, Spotlight, Trinity Large Preview, Trinity Large Thinking, Trinity Mini, Virtuoso Large