Models / Arcee AI / Trinity Large Thinking

Arcee AI · trinity

Trinity Large Thinking

Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use

$0.25 in · $0.80 out

per 1M tokens · provider rate closest to the median. No first-party Arcee AI price was listed. The reference price is Arcee's rate, the provider closest to the median.

Provider input prices run from $0.25 to $0.25 per 1M tokens. Output prices run from $0.80 to $0.90.

Context
524,288
Max output
262,144
Cache read
$0.06
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Unknown
Vision
No
Open weights
Yes
License
OpenMDW-1.1
Released
Apr 1, 2026
Updated in source
May 28, 2026
Knowledge
—
Providers
6

Hugging Face weights · Model card · Announcement · License

What this model costs per month

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Providers

Base rates from Models.dev. One row per provider.
ProviderInputOutputCache readCache writeStatus
Arceereference$0.25$0.80$0.06—beta
DigitalOcean$0.25$0.90$0.06——
Kilo Gateway$0.25$0.80$0.06——
NanoGPT$0.25$0.90$0.13——
OpenRouter$0.25$0.80$0.06——
Vercel AI Gateway$0.25$0.80———