Unverified50% confidenceFactExact time
vLLM, SGLang, llama.cpp, and Ollama all expose an OpenAI-compatible /v1/chat/completions endpoint by default.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedOllama's interface design is highly compatible with OpenAI's /v1/chat/completions specification.80% similarUnverifiedOpenAI兼容协议定义了标准化HTTP REST接口，包括/v1/chat/completions、/v1/completions等端点，切换模型提供商只需更换Base URL和API Key72% similarUnverifiedWhen configuring an OpenAI-compatible interface in SillyTavern, /v1 must be appended to the request URL; otherwise the connection will fail.72% similarUnverifiedWhen configuring a custom service provider, the address must be verified as accurate and the correct protocol selected; most providers support the OpenAI-compatible interface (with /v1 appended to the address).69% similarUnverifiedChatbox supports multiple backends—in addition to Ollama, it can also connect to cloud services such as OpenAI, Claude, and Azure, allowing users to switch between local and cloud models within the same interface.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1002850API
curl https://kongchang.com/api/v1/knowledge/claims/1002850MCP
get_claim(id=1002850)