Trinity Large Thinking
Arcee AI · released Apr 1, 2026 · arcee-ai/Trinity-Large-Thinking
- Type
- Open weightsCustom licence
- Params
- 399B
- Context
- 262K
active per word not recorded by us · about 197K words of context · download allowed, licence restricts use
Our take
Written Sep 30, 2026Trinity Large Thinking is a downloadable text model with a very large request capacity, built for long documents rather than for topping leaderboards. Its measured quality sits mid-field on the Arena boards, and its custom licence puts conditions on commercial use and redistribution.
Reach for it when you have long documents to work through in a single request and you can judge the output yourself, or when you want the option of running the model on your own hardware. Read the custom licence before you build anything commercial on it. Skip it if you need a model that places well on coding or web-app building, or if you want licence terms that need no reading.
The case for it
- A request capacity of 262144 tokens means long documents need not be split up first, though whether it recalls details across all of that is unverified in our data.
- You can download it and run it yourself, so a host is an option rather than the only route.
The case against it
- Mid-field on the boards we hold: 114th of 168 on Arena Text (overall) via Thinking as of 25 Sep 2026, and 119th of 168 on Arena Coding via Thinking as of 25 Sep 2026.
- The custom licence puts conditions on commercial use and redistribution, so it needs reading before you build on it.
- 398.6 billion parameters in total, with no figure supplied for how many work on any one token, so memory in use cannot be estimated from the facts we hold.
How good is it?
EverydayGeneral questions and everyday reasoning
Arena Text (overall)114th of 168 · 1368
CodingWriting and fixing code on its own
Arena Coding119th of 168 · 1413
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent.
WritingDrafting and rewriting prose
Arena Creative Writing112th of 168 · 1332
Arena Creative Writing is the only board that has scored it for this.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done.
Every published score for this model7 scoresEvery figure we hold, from 7 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Can you run it yourself?
GeForce RTX 4090 · 24 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Apple M1 Pro (16-core GPU) · 32 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Comfortable fit
Apple M3 Ultra (80-core GPU) · 512 GB
Room to spare. 123.4 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first.
Check against your own machine → · Where to rent it hosted →
Or rent it from someone else
Prices checked 2 hours ago — each listing carries its own date.
- per 1M tokens
- $0.25 in / $0.80 out
- Context served
- 262K
- Throughput
- ~86 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.25 / $0.80checked 2 hours ago | 262K | not measured | Unknown | Unknown | Unknown |
| Arcee AIThrough OpenRouter | $0.25 / $0.80checked 2 hours ago | 262K80K max reply | 86 tok/s | No | Yesunknown period | Unknown |
OpenRouterAcross the 2 listings we hold: 1 says it does not train on prompts, 0 say they do and 1 does not say. 0 appear in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✗ | ✗ |
| Arcee AIThrough OpenRouter | ✓ | ✗ | ✗ |
Tool calling: 2 of 2 listings say yes. JSON output: 0 of 2 listings say yes, 2 say no. Strict schema: 0 of 2 listings say yes, 2 say no.
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- We do not hold the active parameter count for it, so how much of it runs on any one token is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings does not say whether it trains on prompts.
- We hold no batch or off-peak rate for any of its listings.
- We hold a decode speed for it, but no prompt-processing (prefill) figure, so how long the input side of a job takes is unknown to us.
Licence and identifiers
What the licence allowsCustom licence, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Custom licence
This model ships custom license terms that don't map to a known template. We haven't parsed them, so commercial use, redistribution and derivatives are unverified — review the original terms before shipping.
Identifiers
- Hugging Face
- arcee-ai/Trinity-Large-Thinking
- Architecture
- Mixture of experts
- Takes in, gives back
- Text in, text out
- Catalogue slug
- arcee-ai-trinity-large-thinking