Trinity Large Thinking
Arcee AI · released Apr 1, 2026 · arcee-ai/Trinity-Large-Thinking
- Type
- Open weightsCustom licence
- Params
- 399B
- Context
- 262K
about 197K words of context · download allowed, licence restricts use
Our take
Written Aug 3, 2026Trinity Large Thinking is a 399-billion-parameter reasoning model from Arcee AI that excels at coding and hard-prompt tasks, with weights available under a custom restricted licence. It is text-only and served by three providers, though the cheapest option is measurably slower.
Pick this for code-heavy workloads where its Arena Coding score is the headline strength, or for hard-prompt reasoning tasks. Choose OpenRouter or Parasail if input cost matters most. Skip it if you need image or video input, if creative writing quality is critical, or if web development coding is your main use.
The case for it
- Strongest measured skill is coding, with an Arena Coding Elo 45.4 points above its overall text score.
- Competitive on hard prompts and math, with Arena Hard Prompts Elo 1385.6948 and Arena Maths Elo 1384.1305.
- Cheapest access via OpenRouter or Parasail, with input 12% cheaper than Arcee AI direct.
The case against it
- Web development coding lags general coding ability by 175.4 points on the Arena Code (WebDev) leaderboard.
- Creative writing is its weakest measured skill, 80.1 points below hard prompts and 34.8 points below overall text.
- Throughput gap between providers: the cheapest option is roughly a quarter slower than Arcee AI direct.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)92nd of 143 · 1368.9via Thinking
CodingWriting and fixing code on its own
Arena Coding96th of 143 · 1414.3via Thinking
AgenticPlanning, calling tools, staying on task
Nobody we watch has scored Trinity Large Thinking for this. We would take the rating from Arena Agent (IPS).
WritingWe do not rate this
Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage. So we show where Trinity Large Thinking placed and give it no mark out of five.
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, which is why they get no rating.
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?
- Fits in memory
- weights load entirely on the card
- Spills to system RAM
- some weights offload; much slower
- Too large
- will not load even with offload
- est
- size is calculated; the verdict could change by 10%
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.
All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.
Check against your own machine → · All 71 devices, with every size →
Or rent it from someone else
Cheapest of 3 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.
- per 1M tokens
- $0.25 in / $0.80 out
- Context served
- 262K
- Throughput
- ~191 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| Arcee AI | $0.25 / $0.80 | 262K | 191 tok/s | No | Yesunknown period | Unknown |
| OpenRouter | $0.22 / $0.85 | 262K | not measured | Unknown | Unknown | Unknown |
| Parasailfp4 | $0.22 / $0.85 | 262K | 153 tok/s | No | No | Confirmed |
OpenRouterAcross the 3 listings we hold: 2 say they do not train on prompts, 0 say they do and 1 do not say. 1 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| Arcee AI | ✓ | ✗ | ✗ |
| OpenRouter | ✓ | ✓ | ✓ |
| Parasailfp4 | ✓ | ✓ | ✓ |
Tool calling: 3 of 3 listings say yes. JSON output: 2 of 3 listings say yes, 1 says no. Strict schema: 2 of 3 listings say yes, 1 says no.
When we formed this view
Dates behind this page
Prices last checked 5h ago
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.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 3 listings do not say whether they train on prompts.
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
- Modality record
- text->text
- Catalogue slug
- arcee-ai-trinity-large-thinking