Trinity-Large-Thinking
Trinity-Large-Thinking is worth evaluating for rag, agents, and long context when its provider route and context window match the workload.
Use it for
- Teams evaluating rag, agents, and long context
- Workloads that can use a 256k context window
- Buyers comparing 3 tracked provider routes
Do not use it for
- Vision or document-understanding workloads
- Family
- Trinity
- Released
- 2026-04-01
- Context
- 256k
- Parameters
- 400B
- Architecture
- Mixture of Experts
- Specialization
- reasoning
- Openness
- Open source
- License
- Apache 2.0OSI-approvedCommercial use: permitted
- Weights
- Available
- Code
- Unknown
- Training
- Fine-tuned
Cheapest of 3 routes · OpenRouter
About
Arcee AI's flagship 400B sparse MoE reasoning model with 13B active parameters per token. Trained on 20T tokens with a STEM-focused curriculum. Designed for agentic workflows, chain-of-thought reasoning, and long-context tasks up to 256K tokens (BF16 API). Open-source under Apache 2.0. Available via Arcee AI API.
Trinity-Large-Thinking is an open-source model in the Trinity family. The structured metadata tracks a 256k-token context window, reasoning, function calling, tool use, and structured outputs. This page tracks provider routes through Arcee AI, OpenRouter, and Vercel AI Gateway, with the cheapest tracked route listed at $0.22 input and $0.85 output per 1M tokens. Headline tracked benchmarks include Google-Proof Q&A 89.2.
Top use-case fit: coding, agents, and build tasks
RAG
Included by capability and metadata signals in the decision map.
Agents
Included by capability and metadata signals in the decision map.
Long context
Included by capability and metadata signals in the decision map.
Provider price ladder
Compare all 3Compare API pricing across 3 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| OpenRouter | $0.220 | $0.850 | Serverless |
| Vercel AI Gateway | $0.250 | $0.900 | Serverless |
| Arcee AI | - | - | Partial |
Capabilities
Benchmark peer barsfor RAG
No task-mapped benchmark peers are available for this model yet.
Benchmark scores(1)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| Google-Proof Q&A | 89.2 | diamond | https://docs.arcee.ai/language-models/trinity-large-thinking |
Migration checks
No linked migration route is available for this model yet.
Rankings & picks(1)
Compare Trinity-Large-Thinking with other models
- Trinity-Large-Thinking vs DeepSeek V4 Pro178
- Trinity-Large-Thinking vs DeepSeek V4 Flash160
- Trinity-Large-Thinking vs Grok 4120
- Trinity-Large-Thinking vs GPT-5.5116
- Trinity-Large-Thinking vs Grok 4.3116
- Trinity-Large-Thinking vs Claude Opus 4.785
- Trinity-Large-Thinking vs DeepSeek R182
- Trinity-Large-Thinking vs Grok 4.2081
Comparison and alternatives
Browse all comparisons →Show all 33 popular comparisonssorted by 7-day search impressions
Frequently asked questions
What is the context window of Trinity-Large-Thinking?
Trinity-Large-Thinking has a context window of 256k tokens.
How much does Trinity-Large-Thinking cost?
Trinity-Large-Thinking pricing ranges from $0.22/1M to $0.25/1M input tokens depending on the provider.
When was Trinity-Large-Thinking released?
Trinity-Large-Thinking was released on 2026-04-01.
Which providers offer Trinity-Large-Thinking?
Trinity-Large-Thinking is available from 3 providers: Arcee AI, OpenRouter, Vercel AI Gateway.
What benchmarks has Trinity-Large-Thinking been tested on?
Trinity-Large-Thinking has been evaluated on 1 benchmark, including Google-Proof Q&A.
Cheapest of 3 routes · OpenRouter