LLM Pricing
PricingLeaderboardsToolsProvidersReleasesGuides

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list
ar

Trinity Large Thinking

arcee-ai·arcee-ai/trinity-large-thinking·BETA·Open weights·trinity series
Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use

Trinity Large Thinking by arcee-ai is offered by 5 providers on this page. Its reference price is $0.25 per 1M input tokens and $0.90 per 1M output tokens.

Artificial Analysis rates it 18.7 on the Intelligence Index, with 25.8 for coding and 3.7 for agentic tasks. Against its lowest blended price of $0.388 per 1M, that is roughly 48 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 309 tokens per second, with 1.39s to the first token. Running one task of the Artificial Analysis suite costs about $0.1996, which reflects how many tokens its reasoning consumes rather than the unit price alone.

The context window is 262,100 tokens at the reference host, but hosts report different limits, from 262,100 to 262,144, so the usable window depends on the provider you pick. It supports reasoning and tool use. The weights are open, so it can also be self-hosted or served through a gateway of your choice.

Specs & pricing

Input / output per 1M tokens
Reference price·Vercel AI Gateway
$0.25 / $0.90
Blended $0.412 · Cache read —
Lowest paid·Kilo GatewayGateway
$0.25 / $0.80
Blended $0.388 · 1× spread
Context
262,100
Output limit
80,000
Knowledge cutoff
—
Released / updated
2026-04-01 / 2026-05-28
Capabilities
✓ Reasoning✓ Tool useStructured output✓ TemperatureAttachments
Modalities
Text

Quality & performanceArtificial Analysis · Intelligence Index v4.1

Intelligence18.7
Value48
Coding25.8
Agentic3.7
Output speed309 tok/s
TTFT1.39 s
Cost per task$0.1996
Value formulaIQ 18.7 ÷ min blended $0.388 = 48

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 5 providers5 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Kilo GatewayGateway$0.25$0.80$0.06—262,144 ⚠80,000
OpenRouterGateway$0.25$0.80$0.06—262,144 ⚠80,000
ArceeGateway$0.25$0.80$0.06—262,144 ⚠262,144beta
NanoGPTGateway$0.25$0.90$0.125—262,144 ⚠80,000
Vercel AI GatewayCloud$0.25$0.90——262,10080,000

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

1Kilo Gateway$67.20
2OpenRouter$67.20
3Arcee$67.20
4NanoGPT$80.00
5Vercel AI Gateway$95.00
The cheapest paid channel is the only channel.

Reasoning control

effort = high

4 / 5 providers expose no reasoning control (reasoning_options: []).

Related models

arTrinity Minisame series$0.045 / $0.15miArcee Trinity Large Thinking (Public Preview)same series$0.25 / $0.90DeepSeek V4 Flashcheaper alternative$0.14 / $0.28GLM-5.3-Flashcheaper alternative$0.075 / $0.25GPT-5 Nanocheaper alternative$0.05 / $0.40MiMo-V2.5cheaper alternative$0.14 / $0.28

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.90$02026-08-052026-09-012026-08-05 · Input list $0.252026-08-06 · Input list $0.252026-08-07 · Input list $0.252026-08-08 · Input list $0.252026-08-09 · Input list $0.252026-08-10 · Input list $0.252026-08-11 · Input list $0.252026-08-12 · Input list $0.252026-08-13 · Input list $0.252026-09-01 · Input list $0.252026-08-05 · Output list $0.902026-08-06 · Output list $0.902026-08-07 · Output list $0.902026-08-08 · Output list $0.902026-08-09 · Output list $0.902026-08-10 · Output list $0.902026-08-11 · Output list $0.902026-08-12 · Output list $0.902026-08-13 · Output list $0.902026-09-01 · Output list $0.902026-08-05 · Min blended $0.3782026-08-06 · Min blended $0.3782026-08-07 · Min blended $0.3782026-08-08 · Min blended $0.3782026-08-09 · Min blended $0.3782026-08-10 · Min blended $0.3782026-08-11 · Min blended $0.3782026-08-12 · Min blended $0.3782026-08-13 · Min blended $0.3782026-09-01 · Min blended $0.388
Data partly from models.dev (MIT) · Vercel AI Gateway official docs ↗