Trinity Mini

Fast and lightTools

Arcee AI · Released December 2025

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 robust function...

Facts and pricing

Provider
Arcee AI
Context window
131K tokens
Input price
0.50 credits / 1M tokens ($0.045 raw)
Output price
1.7 credits / 1M tokens ($0.15 raw)
Vision (image input)
No
Tool calling
Yes
Extended reasoning
No

Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.10x margin. Raw prices shown per 1M tokens.

Try Trinity Mini now

Ask Trinity Mini anything. Your prompt opens in the Zeplik app with this model selected.

Trinity Mini

What Trinity Mini is best for

Arcee AI family

ModelContextInput cr/MOutput cr/MReleased
Trinity Large Thinking262K2.88.8April 2026
Trinity Mini131K0.501.7December 2025
Virtuoso Large131K8.313.2May 2025
Coder Large33K5.58.8May 2025

Frequently asked questions

What is Trinity Mini?
Trinity Mini is an AI model by Arcee AI. 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 robust function...
How much does Trinity Mini cost on Zeplik?
Input tokens cost 0.50 credits per million and output tokens 1.7 credits per million (1 credit = $0.10; the raw provider rates are $0.045 and $0.15 per million). New accounts start with free credits.
How long can a conversation with Trinity Mini be?
Trinity Mini has a 131K-token context window (131,072 tokens), which covers the conversation plus any documents you attach.
Does Trinity Mini support images and tools?
Trinity Mini is text-only and supports tool calling.

Related models

Trinity Large ThinkingGeneral purpose

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...

262K ctx8.8 cr/M outApril 2026
Virtuoso LargeGeneral purpose

Virtuoso‑Large is Arcee's top‑tier general‑purpose LLM at 72 B parameters, tuned to tackle cross‑domain reasoning, creative writing and enterprise QA. Unlike many 70 B peers, it retains the 128 k...

131K ctx13.2 cr/M outMay 2025
Coder LargeCoding

Coder‑Large is a 32 B‑parameter offspring of Qwen 2.5‑Instruct that has been further trained on permissively‑licensed GitHub, CodeSearchNet and synthetic bug‑fix corpora. It supports a 32k context window, enabling multi‑file...

33K ctx8.8 cr/M outMay 2025
GPT-5.6 Luna ProFrontier

GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

1.1M ctx66.0 cr/M outJuly 2026
GPT-5.6 LunaFrontier

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...

1.1M ctx66.0 cr/M outJuly 2026
GPT-5.6 Terra ProFrontier

GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

1.1M ctx165 cr/M outJuly 2026
Trinity Mini - Arcee AI AI Model | Zeplik Chat