This is the batch-processing variant of gpt-oss-20b, OpenAI's open-weight mixture-of-experts model (21B total parameters, 3.6B active, Apache 2.0 license, 128K-token context, released August 5, 2025), offering the same configurable reasoning effort at a lower cost via OpenRouter's asynchronous batch endpoint. It suits high-volume, non-latency-sensitive workloads like bulk summarization or classification rather than interactive tool-calling use.
Fascia di costo
0.1x
Contesto
131K
Rilasciato
5 ago 2025
Input
Text
Output
Text
Supporto
RagionamentoChiamata di strumentiOutput strutturati
In cosa eccelle
Le categorie in cui questo modello ottiene i risultati migliori.
Matematica
#235 · top 58%
Medicina e sanità
#236 · top 60%
Business, gestione e finanza
#248 · top 60%
Software e servizi IT
#250 · top 59%