RentGPU RentGPU
Encontrar GPU →
by Arcee Ai

Arcee AI: Trinity Mini.

text open weights 131K ctx
Cheapest input
$0.045/M
on Together AI
Cheapest output
$0.15/M
on Together AI
Fastest
154 tok/s
on OpenRouter
Hosted equiv.
~$0.05/hr
@ 100 tok/s on Together 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...

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
Together AI hosted inference $0.045 $0.15 Launch ↗
OpenRouter api aggregator $0.045 $0.15 Launch ↗
Performance

Speed across providers.

Tokens/sec and time-to-first-token measured against the same prompt template on each provider's API.

Provider Tokens/sec TTFT Total
OpenRouter 153.5 2492 ms 3257 ms
FAQ

Frequently asked.

How do I run Arcee AI: Trinity Mini?
Arcee AI: Trinity Mini is open-weight, so you can self-host on rented GPUs. See the Run It Yourself tab for GPU configurations + cost estimates, or use one of the hosted inference providers listed on this page.
Where can I access Arcee AI: Trinity Mini?
Arcee AI: Trinity Mini is available via Together AI, OpenRouter. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run Arcee AI: Trinity Mini?
API pricing starts at $0.045/M input tokens and $0.15/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is Arcee AI: Trinity Mini open-source or proprietary?
Arcee AI: Trinity Mini is open-weight under the license. You can download and self-host it.