Trinity Mini

by Arcee AIChat

Reasoning-tuned 26B MoE model with 3B active parameters for agents, tools, and multi-step workloads

Context
131K tokens
Max output
131,072 tokens
Parameters
26.1B total
Released
2025-12-01
Weights
Open
Licence
openmdw-1.1

Weights on Hugging Face

arcee-ai/trinity-mini · also seen as arcee_ai/AFM/models/trinity-mini

Specifications

Full facts as recorded, incl. what is unknown.

Released
2025-12-01
Weights
Opennot gated
License
openmdw-1.1
Input
Text
Output
Text
Context window
131,072 max across endpoints
Max output
131,072
Providers
2
Epoch Capabilities Index
not evaluated
Direct price range
$0.045 in · $0.15 out per 1M tokens · across all 2 providers
More details
Last updated
2026-02-25
Knowledge cutoff
2024-10
Weights link
Hugging Face · arcee-ai/Trinity-Mini
Parameters
26.1B total
Base model
arcee-ai/Trinity-Mini-Base

Capabilities

Across all endpoints: supported if any endpoint supports it.

  • Tool calling
  • Parallel toolsunknown
  • Structured outputunknown
  • Reasoning
  • Image input
  • PDF input
  • Audio input
  • Audio outputunknown
  • Video input
  • Prompt cachingunknown
  • Web searchunknown
  • Computer useunknown
  • System messagesunknown
  • Assistant prefillunknown
  • Temperature
  • Streamingunknown
  • Attachments

Endpoints

One row per provider and variant; gateways are listed separately.

Loading endpoints…

Price history

No change since 19 Oct 2026. The cheapest direct price has been $0.045 in / $0.15 out per 1M tokens at Together AI on every data refresh since then.

Tracked from 19 Oct 2026. Headline-eligible direct prices only, so a price the sanity check flags never draws a spike. Series as JSON

Cost calculator

Loading endpoints…

More from Arcee AI

Newest Arcee AI models in the catalogue. All Arcee AI models

ModelReleasedContextListed price
Trinity Large Thinking2026-04-01262Kfrom $0.25
Trinity Large Preview2026-01-27131Kunpriced
Heads up: prices are indicative list rates scraped from provider pricing pages; verify with the provider before relying on them. Report incorrect data for this model