Model
Trinity Large Thinking
Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use
Compare providers (sorted by listed input price)
5 providers list Trinity Large Thinking. The cheapest full-context option is Kilo Gateway at $0.25/$0.8 per M.
Best price history
Daily lowest published price across live providers. A lower line is better for the buyer.
- Best input /M
- $0.25▲ 13.6%
- Best output /M
- $0.8▼ 5.9%
- Provider coverage
- 5
- 5 at the start · 24 snapshots
Price badge
https://www.vaanalytics.in/badge/arcee-ai/trinity-large-thinking.svgLive SVG, regenerated on every hourly sync — paste it into a README to always show the current cheapest listed price. Updates when prices change; no build step needed on your side.
Recent changes
Changelog →- capabilityvia openrouter · Aug 31, 2026
- structured_output: true → false
- repricedvia kilo · Aug 31, 2026
- structured_output: true → false
- input: $0.22 → $0.25
- output: $0.85 → $0.8
- repricedvia openrouter · Aug 30, 2026
- output: 236K → 80K tokens
- input: $0.22 → $0.25
- output: $0.85 → $0.8
- contextvia kilo · Aug 30, 2026
- output: 236K → 80K tokens
- contextvia openrouter · Aug 25, 2026
- output: 262K → 236K tokens
- contextvia kilo · Aug 25, 2026
- output: 262K → 236K tokens
Weights
No machine-readable licence on the model card. Check it before you rely on this. Weights download without an access request.
Derived from arcee-ai/Trinity-Large-Base.
licence and gating from the Hugging Face model card ↗ — the card is authoritative, this is a summary
Prices are per million tokens (USD). “—” means the provider does not publicly list a price for this model. Data from models.dev; verify with the provider before purchasing.