Third-party model endpoints cannot be configured
Connecting to third-party or local OpenAI-compatible model servers needs per-provider URLs, keys and model names that the config cannot hold.
Tier II · Emerging Problems that are still building up.
3 public reports · first reported 18 April 2024 · last reported 10 February 2025
What's going wrong
People who run this project against several model providers, such as SiliconFlow, Tencent Cloud, Alibaba, DeepSeek's own site, or a local LM Studio server, struggle with its configuration.
AI-assisted: written with the help of AI from the reports. The idea report has the full summary.
In the idea report
- The full summary.
- The products the 3 reports are about, and how many came each month.
- Related problems.
No business has been found with this problem yet, so the report has no contacts. All sales are final — no refunds. Pricing.