OpenAI Chat Completions
A conversational completion API interface provided by OpenAI that supports both streaming and non-streaming responses. Usage data in streaming mode must be enabled through stream_options.
Timeline (last 90 days)
The strict sequence requirement of the tool-calling API is that every tool_call must be immediately followed by a tool message with a matching id, otherwise the server may return a 400 error or behave undefinedly.
For the same MiniMax M3.1 Flash model, the effort field is named reasoning_effort, output_config.effort, and reasoning.effort under the OpenAI Chat Completions, Anthropic Messages, and OpenAI Responses protocols respectively; all three accept the five values low/medium/high/xhigh/max, and all default to max.
Qwen Code is a terminal coding agent launched by the Tongyi team, originally forked from Gemini CLI and switched to the OpenAI Chat Completions protocol.
Using the three environment variables OPENAI_API_KEY, OPENAI_BASE_URL and OPENAI_MODEL, Qwen Code can be configured to connect to a custom OpenAI-compatible API without a configuration file.
The OpenAI Chat Completions protocol is currently the de facto standard for LLM inference access; mainstream self-hosted frameworks such as vLLM, Ollama and LiteLLM all implement it, and their common trait is exposing a /v1/chat/completions endpoint and accepting Bearer authentication.
Strata is compatible with the OpenAI Chat Completions interface specification; point the base URL to local port 8080 and fill in any key to use it.
GLM (glm-4.5-air) is Zhipu AI's large language model series, called via the OpenAI-compatible API provided by Z.ai, with interface paths, request bodies, and response formats largely consistent with the OpenAI Chat Completions specification.
In traditional interfaces such as OpenAI Chat Completions, messages with the system role are usually conventionally placed at the very front of the message array, as the global setting for the entire session.
NowRouter是一个运行在本地（localhost）的模型路由网关，负责统一管理多个模型提供商并对外暴露一个兼容OpenAI Chat Completions格式的标准化API端点
All Facts (10)
Claude使用Anthropic Messages API格式，而GPT系列使用OpenAI Chat Completions格式，两者接口规范存在本质差异
95%UnverifiedThe strict sequence requirement of the tool-calling API is that every tool_call must be immediately followed by a tool message with a matching id, otherwise the server may return a 400 error or behave undefinedly.
50%UnverifiedFor the same MiniMax M3.1 Flash model, the effort field is named reasoning_effort, output_config.effort, and reasoning.effort under the OpenAI Chat Completions, Anthropic Messages, and OpenAI Responses protocols respectively; all three accept the five values low/medium/high/xhigh/max, and all default to max.
50%UnverifiedQwen Code is a terminal coding agent launched by the Tongyi team, originally forked from Gemini CLI and switched to the OpenAI Chat Completions protocol.
50%UnverifiedUsing the three environment variables OPENAI_API_KEY, OPENAI_BASE_URL and OPENAI_MODEL, Qwen Code can be configured to connect to a custom OpenAI-compatible API without a configuration file.
50%UnverifiedThe OpenAI Chat Completions protocol is currently the de facto standard for LLM inference access; mainstream self-hosted frameworks such as vLLM, Ollama and LiteLLM all implement it, and their common trait is exposing a /v1/chat/completions endpoint and accepting Bearer authentication.
50%UnverifiedStrata is compatible with the OpenAI Chat Completions interface specification; point the base URL to local port 8080 and fill in any key to use it.
50%UnverifiedGLM (glm-4.5-air) is Zhipu AI's large language model series, called via the OpenAI-compatible API provided by Z.ai, with interface paths, request bodies, and response formats largely consistent with the OpenAI Chat Completions specification.
50%UnverifiedIn traditional interfaces such as OpenAI Chat Completions, messages with the system role are usually conventionally placed at the very front of the message array, as the global setting for the entire session.
50%UnverifiedNowRouter是一个运行在本地（localhost）的模型路由网关，负责统一管理多个模型提供商并对外暴露一个兼容OpenAI Chat Completions格式的标准化API端点
50%