Maestro Reasoning
Maestro Reasoning is Arcee AI's language model with a 131K context window and up to 32K output tokens, starting at $0.900 / 1M input and $3.30 / 1M output. A 32B-parameter reasoning-focused LLM derived from Qwen 2.5-32B, tuned with DPO and chain-of-thought RL for step-by-step logical analysis.
Arcee AI's language model with a 131K context window and up to 32K output tokens, starting at $0.900 / 1M input and $3.30 / 1M output. A 32B-parameter reasoning-focused LLM derived from Qwen 2.5-32B, tuned with DPO and chain-of-thought RL for step-by-step logical analysis.Capabilities
Input1/5
✓
·
·
·
·
Output1/5
✓
·
·
·
·
Capabilities0/13
·
·
·
·
·
·
·
·
·
·
·
·
·
Pricing by Provider
| Provider | Standard | |
|---|---|---|
| Input $ / 1M | Output $ / 1M | |
 OpenRouter | $0.900 | $3.30 |
Cost Calculator
Preset:
Compares every provider & tier in USD
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Trinity Large Preview | 131K | $0.250 | $1.00 | Deprecating | |
| Trinity Mini | 131K | $0.045 | $0.150 | Available | |
| Maestro Reasoning | 131K | $0.900 | $3.30 | Current | |
| Coder Large | 33K | $0.500 | $0.800 | Available | |
| Spotlight | 131K | $0.180 | $0.180 | Available | |
| Virtuoso Large | 131K | $0.750 | $1.20 | Available | |
| Arcee Lite | — | — | — | — | Available |
| Arcee Llama 3.1 SuperNova Lite | — | — | — | — | Available |
| Arcee Llama Spark | — | — | — | — | Available |
| Arcee SuperNova | — | — | — | — | Available |
| Arcee Virtuoso Small | — | — | — | — | Available |