inference-apis plugin
Inference-API compatibility suite — the three open LLM serving protocols as third-party surfaces: OpenAI Chat Completions + legacy /v1/completions (7 local servers, gateways, 10 cloud compat endpoints, reasoning-field schism, client wire behavior), OpenAI Responses (spec, streaming events, store/previous_response_id semantics, translation), and Anthropic Messages (7 native server implementations, thinking-signature seam, stop_reason divergences, Claude Code/opencode integration). Source-examined at pinned commits with live-verification logs.
How to install the inference-apis plugin
Run both commands inside Claude Code. The first adds the marketplace once; the second installs the plugin.
/plugin marketplace add air-gapped/skills
/plugin install inference-apis@air-gapped-marketplaceWhat's inside inference-apis
3 parts read from the plugin's own files.
Skills 3
Claude loads it when the task matches- chat-completions-api
Reference for the OpenAI Chat Completions API (/v1/chat/completions) and legacy /v1/completions as the lingua-franca compatibility protocol — the official spec incl. deprecation timeline and Responses-only feature delta, how 7 local servers (vLLM, SGLang, llama.cpp, Ollama, mistral.rs, Llama Stack/OGX, Lemonade) actually implement it, gateways (LiteLLM, Bifrost), 10 cloud providers' CC-compat endpoints (Anthropic, Gemini, DeepSeek, xAI, Groq, OpenRouter, Azure...), the reasoning_content/reasoning field schism, finish_reason divergences, and client wire behavior (opencode, Vercel AI SDK). NOT for the Responses API (responses-api skill) or Anthropic Messages protocol (messages-api skill).
- messages-api
Provides a compatibility reference for implementing or using the Messages API protocol across third-party inference servers, gateways, and clients.
- responses-api
Provides a reference for the Responses API, OpenResponses standard, and Codex CLI for managing agentic workloads and tool-calling workflows.
Using inference-apis in Claude Code
Skills need no command. Claude reads them when your request matches what they describe.
Update, turn off or remove
- Update the plugin (shell)
- claude plugin update inference-apis@air-gapped-marketplace
- Refresh the marketplace
- /plugin marketplace update air-gapped-marketplace
- Turn it off for now
- /plugin disable inference-apis@air-gapped-marketplace
- Remove it
- /plugin uninstall inference-apis@air-gapped-marketplace
Skills in inference-apis
- chat-completions-apiair-gapped/skills
Reference for the OpenAI Chat Completions API (/v1/chat/completions) and legacy /v1/completions as the lingua-franca compatibility protocol — the official spec incl. deprecation timeline and Responses-only feature delta, how 7 local servers (vLLM, SGLang, llama.cpp, Ollama, mistral.rs, Llama Stack/OGX, Lemonade) actually implement it, gateways (LiteLLM, Bifrost), 10 cloud providers' CC-compat endpoints (Anthropic, Gemini, DeepSeek, xAI, Groq, OpenRouter, Azure...), the reasoning_content/reasoning field schism, finish_reason divergences, and client wire behavior (opencode, Vercel AI SDK). NOT for the Responses API (responses-api skill) or Anthropic Messages protocol (messages-api skill).
9 files6stars - messages-apiair-gapped/skills
Provides a compatibility reference for implementing or using the Messages API protocol across third-party inference servers, gateways, and clients.
8 files6stars - responses-apiair-gapped/skills
Provides a reference for the Responses API, OpenResponses standard, and Codex CLI for managing agentic workloads and tool-calling workflows.
9 files6stars
inference-apis plugin questions
How do I install the inference-apis plugin?
In Claude Code run /plugin marketplace add air-gapped/skills, then /plugin install inference-apis@air-gapped-marketplace.
What does the inference-apis plugin include?
inference-apis bundles 3 skills.
How do I update or remove the inference-apis plugin?
Update it with claude plugin update inference-apis@air-gapped-marketplace in your shell, or from the Installed tab of /plugin. Remove it with /plugin uninstall inference-apis@air-gapped-marketplace.
What license is the inference-apis plugin under?
MIT, as stated in the plugin's manifest.