Back to all models
arcee-ai
arcee-aiArcee AI: Maestro Reasoning
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...
arcee-ai/maestro-reasoning
Context Size
131.072K
Input Price
5,535 Ks/M
Output Price
20,295 Ks/M
Architecture
Text
Supported Parameters
frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltystoptemperaturetop_ktop_p
Details
TokenizerOther
Max Completion32,000 tokens
Provider Context131.072K tokens
ModeratedNo