You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Currently, dstack Models work with Chat Completions API, but since March OpenAI has introduced the Responses API (migration guide). OpenAI says that the Chat Completions API will not be deprecated, but Responses API is the recommended default, with new features and improved efficiency. Ecosystem projects (vLLM, Ollama, etc.) are actively adding Responses API support, mainly because Codex does not work with Chat Completions.
In our docs, chat model is said to have OpenAI-compatible endpoint, which is confusing since there are different OpenAI formats with Responses API being the new default.
Since we migrated from the deprecated gateway.-prefixed endpoint to the service endpoint (#3560), we now rely on the serving framework directly, which seems to already support the Responses API.
Tested with an SGLang-based service (deepseek-ai/DeepSeek-R1-Distill-Qwen-32B on H100 NVL):
Activity
github-actions commentedon Sep 19, 2025
This issue is stale because it has been open for 30 days with no activity.
peterschmidt85 commentedon Feb 12, 2026
Since we migrated from the deprecated
gateway.-prefixed endpoint to the service endpoint (#3560), we now rely on the serving framework directly, which seems to already support the Responses API.Tested with an SGLang-based service (
deepseek-ai/DeepSeek-R1-Distill-Qwen-32Bon H100 NVL):The response comes back with the proper
responseobject format (id,output,status, etc.).