Status: [UNTESTED] Endpoints found: http://localhost:8080/v1/chat/completions http://localhost:8080/v1/models http://localhost:8080/v1/responses http://localhost:8080/v1/messages http://localhost:8080/v1/systemone Source: https://github.com/jasonxu114514/opencode2api # opencode2api [English](README.md) | [简体中文](README.zh-CN.md) | [Tiếng Việt](README.vi.md) | [Italiano](README.it.md) A Go gateway for **OpenCode Zen and Zen Go**. It exposes Chat Completions, Responses, and Anthropic Messages endpoints, translates between their native protocols, and manages upstream keys and proxies. The executable includes the WebUI. Running the service requires no Node.js runtime or database. ## Capabilities - JSON and SSE responses across all three inference protocols. - Text, images, reasoning, function tools, tool calls, and tool results; file content where the target protocol can represent it. - Separate Zen and Go key pools, configurable tier preference, retries, and session affinity. - Opt-in anonymous Zen access with the OpenCode `public` credential; disabled by default because upstream blocking can make it unavailable. - Optional userspace Cloudflare WARP egress for free-model traffic, without TUN or root. - Direct, HTTP, HTTPS, SOCKS5, and SOCKS5H connections, including a proxy file. - Dynamic model discovery, native protocol metadata, and disk caches. - A separate management port with configuration editing, a Playground, diagnostics, token statistics, and live logs. - Configuration hot reload with validation before switching new requests to a replacement gateway. - Go subscription quota dashboard with remaining percentages, reset times, and available models. - Local API key creation, naming, enabling, disabling, and deletion with immediate updates. - Sticky `sota` / `sweet` model groups with ordering, failure fallback, streaming protection, and persisted state. See the [management console guide (Chinese)](docs/management.zh-CN.md) for the new pages and configuration. ## Sponsors
IPWO