AI Observatory / Model Radar
Arcee Ai / arcee-ai/maestro-reasoning
Arcee 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...
131,072
Context
32,000
Max output
$0.90 / 1M
Prompt price
2025-05-05
Created
01 / Snapshot
Pricing, context, modalities, and parameters.
Model Radar detail pages stay neutral and operator-readable: core metadata first, then workflow fit.
| Provider | Arcee Ai | Input modalities | text |
|---|---|---|---|
| Output modalities | text | Prompt price | $0.90 / 1M |
| Completion price | $3.30 / 1M | Request price | N/A |
| Context length | 131,072 | Max completion tokens | 32,000 |
| Supported parameters | frequency_penalty, logit_bias, max_tokens, min_p, presence_penalty, repetition_penalty, stop, temperature, top_k, top_p | ||
Best for
arcee-ai/maestro-reasoning
Arcee 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...
Deep analysis
High-volume usage
low-cost
03 / Colophon
Routes and exits.
Each model page stays simple: overview, compare, related models, then back to the public hub.