The deepseek-v4.1-flash, glm-5.3-flash, and Nemotron models have been throwing a “READ TIMEOUT” error (HTTPSConnectionPool(host=‘integrate.api.nvidia.com’, port=443): Read timed out. (read timeout=90)) since this morning, and there is no solution for it. pleasea
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Deepseek-ai/deepseek-v4.1-flash fails even in official Playground — "Retries exhausted: 3/3" | 4 | 643 | September 26, 2026 | |
| CRITICAL: NVIDIA NIM Chat Completions Timeout — DeepSeek V4.1 Flash | 3 | 584 | November 6, 2026 | |
| NVIDIA NIM — DeepSeek V4.1 Flash API Timeout / Playground HTTP 200 / Developer API HTTP 401 | 1 | 161 | November 5, 2026 | |
| Deepseek-V4.1-flash + glm-5.3-flash extreme loss of speed | 3 | 411 | October 29, 2026 | |
| NVIDIA NIM GLM-5.3 chat completions time out while /v1/models returns HTTP 200 | 2 | 333 | October 15, 2026 | |
| NVIDIA API endpoint | 1 | 711 | May 15, 2026 | |
| NVIDIA API: Models Endpoint Works, but Chat Completions Time Out | 0 | 125 | October 30, 2026 | |
| Nvidia Nim is too slow via API for DeepSeek Models | 1 | 2361 | May 23, 2026 | |
| Request to Add DeepSeek-V4.1-Flash-1017 to NVIDIA NIM | 7 | 670 | October 22, 2026 | |
| Unknown Error 504 Gateway Timeout Error | 0 | 50 | November 7, 2026 |