Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use
Context
262K
262,144 tokens
Max output
80K
80,000 tokens
Input
$0.25
per 1M tokens
Output
$0.90
per 1M tokens
Providers
4
4 listings
Intelligence
—
Not yet scored
Pricing
USD per 1M tokens · listed by NanoGPT
| Token type | Standard |
|---|---|
| Input | $0.25 |
| Output | $0.90 |
| Cache read | $0.13 |
Lowest input price across providers: $0.25.
Capabilities
ReasoningYes
Effort: none, low, medium, high
Tool callYes
Structured outputNo
TemperatureYes
AttachmentsNo
Interleaved reasoningYes
Field: reasoning_content
Open weightsYes
ModeratedUnknown
Input
Text
Output
Text
Benchmarks
Published scores and Design Arena Elo
No published benchmark scores for this model yet.
Rankings
Position on each OneAtlas leaderboard
Providers · 4
4 listings
| Provider | Model ID | Context | Input limit | Output | Input $ | Output $ | Reasoning $ | Cache read | Cache write | Audio in | Audio out | Reasoning | Tools | Structured | Temp. | Updated |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| trinity-large-thinking | 262K | — | 80K | $0.25 | $0.80 | — | $0.06 | — | — | — | Yes | Yes | Unknown | Yes | May 28, 2026 | |
| arcee-trinity-large-thinking | 128K | — | 32K | $0.25 | $0.90 | — | $0.06 | — | — | — | Yes | Yes | Unknown | Yes | May 28, 2026 | |
| arcee-ai/trinity-large-thinking | 262K | 262K | 80K | $0.25 | $0.90 | — | $0.13 | — | — | — | Yes | Yes | No | Yes | May 28, 2026 | |
| arcee-ai/trinity-large-thinking | 262K | — | 80K | $0.25 | $0.80 | — | $0.06 | — | — | — | Yes | Yes | Unknown | Yes | May 28, 2026 |