arcee-ai › Trinity Large Thinking › Pricing
aBenchmarks and alternatives →
Trinity Large Thinking pricing
API list price by arcee-ai · same on Arcee AI, Featherless · checked Oct 23, 2026
$0.25 / $0.80per 1M tokens in / out
$0.06cache read · −76%
$0.12per task at thinking?
#315on OpenRouter by tokens · 1.3B / week
Price sheetper 1M tokens
| Input | $0.25 | list |
| Output | $0.80 | |
| Cache read | $0.06 | −76% vs input |
| Context · max output | 262K · 80K | tokens |
Where to buy2 providers · per 1M tokens
| Provider | Input | Output | Context |
|---|---|---|---|
| Arcee AI | $0.25 | $0.80 | 262K |
| Featherless | $0.25 | $0.80 | — |
Cheaper for the same workvs Trinity Large Thinking
| GPT-6 Luna max | -43% | score ×3.5 | $0.068 |
| MiMo v2.6 Flash thinkingOpen | -48% | score ×3.5 | $0.062 |
| Claude Haiku 5.5 high | -33% | score ×3.5 | $0.079 |
| Agnes 2.5 Pro Beta | -61% | score ×3.3 | $0.10 / $0.30 |
| GPT-5.6 Luna xhigh | -28% | score ×3.2 | $0.085 |
Pricing questions
How much does Trinity Large Thinking cost?›
$0.25 per 1M input tokens and $0.80 per 1M output tokens on arcee-ai's API and Arcee AI, Featherless. Cached input is $0.06. One Intelligence Index task costs about $0.12 at the default effort.
Is Trinity Large Thinking free to use?›
There is no free API tier, but the weights are open: you can run it on your own hardware for the cost of compute.
How much does prompt caching save?›
Cache reads cost $0.06 per 1M, 76% below the input price.
What is a cheaper alternative to Trinity Large Thinking?›
GPT-6 Luna at max effort costs -43% per task with a score ×3.5 on Humanity's Last Exam.