Trinity Mini pricing
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... This page tracks 1 listing in total. Highlighted lows are $0.045 per million input and $0.150 per million output (see table for which seller matches each).
Pricing across providers
All figures are list prices per million tokens unless a column says otherwise. 1 offer is listed for Trinity Mini. Best input in this view: Openrouter.
| Provider | Input / 1M | Output / 1M | Cached input | Batch |
|---|---|---|---|---|
O Openrouter | $0.045 | $0.150 | — | — |
Input vs output · 1M tokens
Cost calculator
The calculator uses the same dollars per million tokens as the table. Adjust sliders to see how Trinity Mini cost scales with traffic.
0.004500¢ / req
0.007500¢ / req
Model specifications
Quick spec sheet for Trinity Mini before you dive back into pricing. Reported under Arcee Ai.
- Context window
- 131,072 tokens
- Max output
- 131,072 tokens
- Vision (images)
- No
- Tool / function calling
- Yes
- Streaming
- Yes
- Released
- Dec 2025
- Primary provider
- Arcee Ai
- Model family
- N/A
Compare Trinity Mini
Jump into a comparison when you want one table for two models instead of two tabs. 6 curated matches for Trinity Mini.
Locked
Compare with
Pick a model on both sides.
Popular Trinity Mini comparisons
- Trinity Mini vs GPT-4o
Compare pricing side by side
- Trinity Mini vs GPT-4o mini
Compare pricing side by side
- Trinity Mini vs Claude Sonnet 4.6
Compare pricing side by side
- Trinity Mini vs Gemini 2.0 Flash
Compare pricing side by side
- Trinity Mini vs o3
Compare pricing side by side
- Trinity Mini vs Llama 3.1 70B
Compare pricing side by side
Frequently asked questions
Quick frequently asked items for Trinity Mini pricing and limits. The short model note from our index: 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...
Also from Arcee Ai
Other models by Arcee Ai with live pricing in our catalog.