Trinity Large Thinking

Tool callingReasoning

Hugging Face Launch post Website

Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use

Context: 262K
Released: 6mo ago
Parameters: —
Input / 1M tokens: $0.25
Output / 1M tokens: $0.80
Cached input / 1M tokens: $0.06

Sources:models.devOpenRouter

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

No benchmark results have been matched to this model yet.

Specifications

Developer: Arcee AI
Model family: Trinity
Type: Language model
Predecessor: —
Successor: —
Released: April 1, 2026
Model ID: arcee-ai/trinity-large-thinking
Openness: Open weights
License: OpenMDW-1.1
Parameters: —
Input modalities: text
Output modalities: text
Modality: text->text
Tokenizer: Other
Max output tokens: 80K
Hugging Face: arcee-ai/Trinity-Large-Thinking
Source freshness: Metadata synced Oct 8, 2026, 10:17 PM UTC

Additional source evidence

Source model: arcee-ai/trinity-large-thinking
Source family: trinity
Last updated: 2026-05-28
Model context: 524K
Model output limit: 262K
Open weights: Yes
File attachments: No
Reasoning: Yes
Tool calling: Yes
Temperature control: Yes

Downloadable weights

Hugging Facesafetensors

Official references

Complete source record (JSON)

{
  "id": "arcee-ai/trinity-large-thinking",
  "name": "Trinity Large Thinking",
  "description": "Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use",
  "family": "trinity",
  "last_updated": "2026-05-28",
  "attachment": false,
  "reasoning": true,
  "tool_call": true,
  "temperature": true,
  "modalities": {
    "input": [
      "text"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 524288,
    "output": 262144
  },
  "release_date": "2026-04-01",
  "open_weights": true,
  "license": "OpenMDW-1.1",
  "links": [
    {
      "url": "https://huggingface.co/arcee-ai/Trinity-Large-Thinking",
      "label": "Model card",
      "type": "model_card"
    },
    {
      "url": "https://www.arcee.ai/blog/trinity-large-thinking",
      "label": "Announcement",
      "type": "announcement"
    },
    {
      "url": "https://huggingface.co/arcee-ai/Trinity-Large-Thinking/blob/main/LICENSE",
      "label": "License",
      "type": "license"
    }
  ],
  "weights": [
    {
      "label": "Hugging Face",
      "url": "https://huggingface.co/arcee-ai/Trinity-Large-Thinking",
      "format": "safetensors"
    }
  ]
}

Infrastructure

Provider availability

All providers

Provider	Endpoint	Context	Input /M tokens	Output /M tokens	Cached input /M tokens	Cache write /M tokens	Uptime 1d	Data handling
Arcee AI	arcee-ai	262K	$0.25	$0.80	$0.06	—	100.00%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Checked 2026-10-15

Provider data:OpenRouter

Deployment graph

Can I run this?

Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.

Browse hardware