Trinity Large Thinking
trinity-large-thinking
Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use
Specification
most-agreed values
Context
262K
Max output
80K
Released
2026-04-01
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.25
Output
$0.80
Cache read
$0.06
Available from 2 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| arcee | $0.25 | $0.80 | $0.06 | — | 262K | 80K | — |
| nano-gpt · arcee-ai | $0.25 | $0.90 | $0.125 | — | 262K | 80K | — |
Price history
append-only observations · a listing writes a row only when its price moves
| Date | Host | Field | $/M |
|---|---|---|---|
| 2026-09-02 | vercel · arcee-ai | Output | $0.90 |
| 2026-10-06 | vercel · arcee-ai | Output | $0.80 |