Trinity Large Thinking
by Arcee AIChat
Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use
- Context
- 262K tokens
- Max output
- 262,144 tokens
- Parameters
- 399B total
- Released
- 2026-04-01
- Weights
- Open
- Licence
- openmdw-1.1
arcee-ai/trinity-large-thinking · also seen as arcee-trinity-large-thinking
Specifications
Full facts as recorded, incl. what is unknown.
- Released
- 2026-04-01
- Weights
- Opennot gated
- License
- openmdw-1.1
- Input
- Text
- Output
- Text
- Context window
- 262,144 max across endpoints
- Max output
- 262,144
- Providers
- 2 + 4 gateways, not counted as providers
- Epoch Capabilities Index
- not evaluated
- Direct price range
- $0.25 in · $0.80–$0.90 out per 1M tokens · across all 2 providers
More details
- Last updated
- 2026-05-28
- Knowledge cutoff
- Weights link
- Hugging Face · arcee-ai/Trinity-Large-Thinking
- Parameters
- 399B total
- Base model
- arcee-ai/Trinity-Large-Base
Capabilities
Across all endpoints: supported if any endpoint supports it.
- Tool calling
- Parallel toolsunknown
- Structured output
- Reasoning
- Image input
- PDF input
- Audio input
- Audio outputunknown
- Video input
- Prompt caching
- Web searchunknown
- Computer useunknown
- System messagesunknown
- Assistant prefillunknown
- Temperature
- Streamingunknown
- Attachments
Endpoints
One row per provider and variant; gateways are listed separately.
Loading endpoints…
Price history
No change since 19 Oct 2026. The cheapest direct price has been $0.25 in / $0.80 out per 1M tokens at Arcee on every data refresh since then.
Tracked from 19 Oct 2026. Headline-eligible direct prices only, so a price the sanity check flags never draws a spike. Series as JSON
Cost calculator
Loading endpoints…
Similarly priced models
Blended rate per 1M tokens, each at its own cheapest provider (10M input : 2M output mix).
| Model | Blended/1M | In/1M | Out/1M | Context | vs Trinity Large Thinking |
|---|---|---|---|---|---|
| Qwen3-VL PlusAlibaba (Qwen) | $0.343 | $0.137 | $1.37 | 262K | +0% |
| Qwen3 VL 8B InstructAlibaba (Qwen) | $0.333 | $0.25 | $0.75 | 262K | −2% cheaper |
| Mercury 2Inception | $0.333 | $0.25 | $0.75 | 128K | −2% cheaper |
| Cydonia 24B V4.1TheDrummer | $0.333 | $0.30 | $0.50 | 131K | −2% cheaper |
| Grok 3 MinixAI | $0.333 | $0.30 | $0.50 | 131K | −2% cheaper |
| MiniMax Text 01MiniMax | $0.35 | $0.20 | $1.10 | 1M | +2% |
| MiniMax LatestMiniMax | $0.352 | $0.23 | $0.96 | 1M | +3% |
| MiniMax-M3MiniMax | $0.352 | $0.23 | $0.96 | 1M | +3% |
More from Arcee AI
Newest Arcee AI models in the catalogue. All Arcee AI models
| Model | Released | Context | Listed price |
|---|---|---|---|
| Trinity Large Preview | 2026-01-27 | 131K | unpriced |
| Trinity Mini | 2025-12-01 | 131K | from $0.045 |