arcee-ai
Arcee AI: Maestro Reasoning
arcee-ai/maestro-reasoning
For $1, you can send approximately:
~34.0messages
How do we get this number?
One message = ~7,000 input tokens + ~7,000 output tokens
Input cost per message7,000 x $0.90/M = $0.006300
Output cost per message7,000 x $3.30/M = $0.023100
Total cost per message$0.029400
Messages for $134.01
Context window
131k
tokens
Max response
32k
tokens
Input price
$0.90
per million tokens
Output price
$3.30
per million tokens
Modalities
Input:textOutput:text
Description
Maestro Reasoning is Arcee's flagship analysis model: a 32 B‑parameter derivative of Qwen 2.5‑32 B tuned with DPO and chain‑of‑thought RL for step‑by‑step logic. Compared to the earlier 7 B...