Hi! What is the default reasoning effort for openai/gpt-oss-120b served over NIM? I don’t see it specified in the model card and I don’t think this is configurable through the python api call example.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Request for NVIDIA NIM API Rate Limit Increase for Academic Study Project | 0 | 136 | May 8, 2026 | |
| Request for NIM API rate limit increase (40 → 200 RPM) — getting started with multi-model exploration | 0 | 49 | May 25, 2026 | |
| Request for Rate Limit Increase for NIM API | 1 | 170 | April 16, 2026 | |
| Request for NVIDIA NIM API Rate Limit Increase (40 -> 200 RPM) for OpenCode Integration | 1 | 114 | July 16, 2026 | |
| Standardize reasoning controls across AI APIs | 1 | 102 | June 20, 2026 | |
| Rpm increase to 200 request | 0 | 39 | July 3, 2026 | |
|
NIM API Rate Limit Upgrade Request 40 - 200 rpm
Access/Accounts
ai-training
,
ai
,
generative_ai
,
nim
,
ai-model-training
,
llama
,
agentic-ai
,
nemotron
,
nemoclaw
|
0 | 86 | May 22, 2026 | |
| Model returns "<|return|>" and missing reasoning_content with openai/gpt-oss-120b | 0 | 291 | October 4, 2025 | |
| Request for NVIDIA NIM API Rate Limit Increase (40 → 200 RPM) - [glm-5.2] | 1 | 48 | August 2, 2026 | |
| Rate limit increase request (40→200 RPM) for open-model batch evaluation | 1 | 58 | July 17, 2026 |