Models10in catalog
Largest context262KTrinity Large Thinking
Avg context
147K
Cheapest input
—
Largest output
262K
Trinity Large Thinking
Speed tiers
deep 7balanced 1fast 2
Capabilities
What Arcee Ai models support across the catalog.
Vision
1 / 10
10% of models
Tool use
7 / 10
70% of models
Function calling
7 / 10
70% of models
Extended thinking
4 / 10
40% of models
Streaming
10 / 10
100% of models
All Arcee Ai models
Sorted by context window, largest first. Tap a row for full specs.
| Model | Context | Max output | Input $/M | Speed |
|---|---|---|---|---|
| Trinity Large Thinking | 262K | 262K | — | deep |
| Trinity Large Thinking (free) | 262K | 80K | — | deep |
| Maestro Reasoning | 131K | 32K | — | deep |
| Spotlight | 131K | 66K | — | balanced |
| Trinity Mini | 131K | 131K | — | fast |
| Trinity Mini (free) | 131K | — | — | fast |
| Virtuoso Large | 131K | 64K | — | deep |
| Trinity Large Preview | 131K | — | — | deep |
| Trinity Large Preview (free) | 131K | — | — | deep |
| Coder Large | 33K | — | — | deep |
See rankings
How Arcee Ai models rank against the full catalog.