Arcee AI · Released Dec 1, 2025Trinity Mini
Reasoning-tuned 26B MoE model with 3B active parameters for agents, tools, and multi-step workloads.
- Capability
- —No ECI score yet
- Input
- $0.045per 1M tokens
- Output
- $0.15per 1M tokens
- Context
- 131K131K max output
What it costs
- Input
- $0.045per million tokens
- Output
- $0.15per million tokens
- Blended (3:1)
- $0.071cheaper than 95% of priced models
Typical monthly bills
| Monthly usage | Estimated cost |
|---|---|
| Side project2M input + 0.5M output tokens | $0.165 |
| Team assistant25M input + 5M output tokens | $1.88 |
| Production app250M input + 50M output tokens | $18.75 |
Median of 1 paid API provider on models.dev.
Independent benchmarks
Epoch AI has not published a Capabilities Index score for Trinity Mini yet.
The details
- Lab
- Arcee AI
- Released
- Dec 1, 2025
- Context window
- 131,072 tokens
- Max output
- 131,072 tokens
- Inputs
- Text
- Output
- Text
- Reasoning
- Always on
- Tool calling
- Yes
- Structured output
- No
- Weights
- Open weights · OpenMDW-1.1
- Availability
- 1 API providerlisted on models.dev
More from Arcee AI
About Trinity Mini
How much does Trinity Mini cost?
Trinity Mini costs $0.045 input / $0.15 output per million tokens (median across 1 API provider). At a 3:1 input-to-output mix that is $0.071 per million tokens, cheaper than 95% of the 360 priced models we track.
What is the context window of Trinity Mini?
Trinity Mini accepts up to 131,072 tokens per request and can write up to 131,072 tokens in one response.
How good is Trinity Mini?
Epoch AI has not published a Capabilities Index score for Trinity Mini yet.
Is Trinity Mini open source?
Yes. Arcee AI publishes the weights under the OpenMDW-1.1 licence, so it can be downloaded and self-hosted.
What inputs does Trinity Mini support?
Trinity Mini accepts text and replies in text. It is a reasoning model, supports tool calling.
When was Trinity Mini released?
Arcee AI released Trinity Mini on Dec 1, 2025.
What are the best alternatives to Trinity Mini?
The closest current models from other labs on capability, price and release date are Seed 1.6 Flash (ByteDance Seed, $0.022 / $0.223), Ministral 3 3B (Mistral AI, $0.10 / $0.10), Sarvam 105B (Sarvam AI, $0.047 / $0.186) and Gemma 4 E2B IT (Google, $0.07 / $0.09).