modelgrep
A

Arcee AI: Trinity Mini

arcee-ai/trinity-mini

Cheaper than 96% of paidReasoningToolsJSON
Use via OpenRouter ↗
Intelligence
Design Elo
Speed
172
23rd fastest
Latency
328ms
first token
Input price
$0.045
13th cheapest
Context
131K
131K max out

How it compares

Faster than92%
of all ranked models
Cheaper than96%
of all ranked models

Overview

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...

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
Clarifaibf16$0.045$0.150

Specifications

Context window131K
Max output131K
Knowledge cutoff
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price
ModeratedNo

Trinity Mini FAQ

How much does Trinity Mini cost?

Trinity Mini costs $0.045 per million input tokens and $0.150 per million output tokens via OpenRouter, making it 13th cheapest of 298 paid models.

How fast is Trinity Mini?

Trinity Mini generates around 172 tokens per second with 328ms time-to-first-token (p50), the 23rd fastest tracked model.

What is Trinity Mini's context window?

Trinity Mini supports a 131K-token context window and can output up to 131K tokens. It accepts text input.

Compare head-to-head