Trinity Models by Arcee AI
4 models2025–2026Up to 256k ctxFrom $0.045/1M input
Last refreshed 2026-06-29. Next refresh: weekly.
Details
ResearcherArcee AI
LicenseApache 2.0OSI-approved
Commercial useCommercial use: permitted
Models4
Released2025–2026
Max context256k
Capabilities
Reasoning1 of 4 models
JSON / Tool use3 of 4 models
Structured Outputs3 of 4 models
Links
WebsiteAbout
Arcee AI's open-source large language model family.
Decision facts
- Best fit
- reasoningJSON / Tool usestructured outputs
- Capability starting point
- Trinity-Large-Thinking with 256k context and reasoning, JSON / Tool use, and structured outputs
- Lowest tracked input
- Trinity Mini · $0.045/1M · OpenRouter
- Closest related family
- AFM
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
4 in view
Trinity-Large-ThinkingCurrent
Use when the workload needs reasoning, 256k context, and 400B parameters.
2026-04reasoning256k context400B parameters
Trinity-Large-PreviewCurrent
Use when the workload needs 128k context, 400B parameters, and JSON / Tool use.
2026-01128k context400B parametersJSON / Tool use
Trinity MiniCurrent
Use when the workload needs 128k context, 26B parameters, and JSON / Tool use.
2025-12128k context26B parametersJSON / Tool use
Trinity NanoCurrent
Use when the workload needs 128k context and 6B parameters.
2025-12128k context6B parameters
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Trinity-Large-Thinking | Use when the workload needs reasoning, 256k context, and 400B parameters. | 2026-04 | reasoning256k context400B parameters | Current |
| Trinity-Large-Preview | Use when the workload needs 128k context, 400B parameters, and JSON / Tool use. | 2026-01 | 128k context400B parametersJSON / Tool use | Current |
| Trinity Mini | Use when the workload needs 128k context, 26B parameters, and JSON / Tool use. | 2025-12 | 128k context26B parametersJSON / Tool use | Current |
| Trinity Nano | Use when the workload needs 128k context and 6B parameters. | 2025-12 | 128k context6B parameters | Current |
Release Timeline
3 release groups2026-04
1 current
Trinity-Large-Thinking
Currentreasoning256k context400B parameters
2026-01
1 current
Trinity-Large-Preview
Current128k context400B parametersJSON / Tool use
2025-12
2 current
Trinity Mini
Current128k context26B parametersJSON / Tool use
Trinity Nano
Current128k context6B parameters
Specifications(4 models)
| Model | Released | Context | Parameters | Reasoning | JSON / Tool use | Structured Outputs |
|---|---|---|---|---|---|---|
| Trinity-Large-Thinking | 2026-04 | 256k | 400B | Yes | Yes | Yes |
| Trinity-Large-Preview | 2026-01 | 128k | 400B | No | Yes | Yes |
| Trinity Mini | 2025-12 | 128k | 26B | No | Yes | Yes |
| Trinity Nano | 2025-12 | 128k | 6B | No | No | No |
Available From(3 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| Trinity Mini | OpenRouter | $0.045 | $0.15 | Serverless |
| Trinity Mini | Vercel AI Gateway | $0.045 | $0.15 | Serverless |
| Trinity-Large-Preview | OpenRouter | $0.15 | $0.45 | Serverless |
| Trinity-Large-Thinking | OpenRouter | $0.22 | $0.85 | Serverless |
| Trinity-Large-Preview | Vercel AI Gateway | $0.25 | $1 | Serverless |
| Trinity-Large-Thinking | Vercel AI Gateway | $0.25 | $0.9 | Serverless |
Popular comparisons in this family
- DeepSeek V4 Pro vs Trinity-Large-Thinking178
- DeepSeek V4 Flash vs Trinity-Large-Thinking160
- Aleph Alpha Luminous Base vs Trinity-Large-Preview124
- Grok 4 vs Trinity-Large-Thinking120
- GPT-5.5 vs Trinity-Large-Thinking116
- Grok 4.3 vs Trinity-Large-Thinking116
- Claude Opus 4.7 vs Trinity-Large-Thinking85
- DeepSeek R1 vs Trinity-Large-Thinking82
- Grok 4.20 vs Trinity-Large-Thinking81
- DeepSeek V3 vs Trinity-Large-Thinking81
