--- title: "Use my Nexus access" description: "Make a first request with the Gateway Base URL and Inference Key your application supplied." --- > Documentation Index > Fetch the complete documentation index at: https://nexus.microvoid.io/llms.txt > Use this file to discover all available pages before exploring further. # Use my Nexus access ## Goal 保留你已有的 OpenAI-compatible SDK 或 OpenCode，只替换 Base URL 和 API Key，完成首次 Nexus Gateway 请求。 ## Outcome 请求使用应用分配给你的 Access 和 Quota，并由明确的 `providerConnectionId` UUID 选择 Workspace 内的一条 ProviderConnection；模型名和 Provider Payload 保持原样。 ## Who this is for 已经从应用安全收到 Nexus 访问信息的最终用户、用户 Agent 或集成工程师。 ## Prerequisites 你需要三项值： 1. `NEXUS_BASE_URL`：形如 `https://gateway.nexus.microvoid.io/providers/`。 2. `NEXUS_API_KEY`：Nexus Inference Key，不是 Provider Key 或 Management Key。 3. `NEXUS_MODEL`：该 ProviderConnection 上游接受的原始模型名。 平台方应通过私密渠道交付 Key。不要把 Key 写入源码、URL、浏览器持久化存储、Analytics 或日志。 ## 1. Replace Base URL and Key E2E Fixture 固定了唯一需要变化的客户端字段： ### JavaScript ```diff title="OpenAI JavaScript client" const client = new OpenAI({ - baseURL: "https://openrouter.ai/api/v1", - apiKey: process.env.PROVIDER_API_KEY, + baseURL: "https://gateway.nexus.microvoid.io/providers/00000000-0000-0000-0000-000000000141", + apiKey: process.env.NEXUS_API_KEY, }); ``` ### Python ```diff title="OpenAI Python client" client = OpenAI( - base_url="https://openrouter.ai/api/v1", - api_key=os.environ["PROVIDER_API_KEY"], + base_url="https://gateway.nexus.microvoid.io/providers/00000000-0000-0000-0000-000000000141", + api_key=os.environ["NEXUS_API_KEY"], ) ``` ## 2. Choose a client ### JavaScript ```sh title="Terminal" npm install openai@6.48.0 ``` ```js title="openai-javascript.mjs" import OpenAI from 'openai'; function requiredEnvironment(name) { const value = process.env[name]?.trim(); if (!value) throw new Error(`${name} is required`); return value; } const client = new OpenAI({ baseURL: requiredEnvironment('NEXUS_BASE_URL'), apiKey: requiredEnvironment('NEXUS_API_KEY'), maxRetries: 0, }); const completion = await client.chat.completions.create({ model: requiredEnvironment('NEXUS_MODEL'), messages: [{ role: 'user', content: 'Keep this request unchanged.' }], temperature: 0.37, }); console.log( JSON.stringify({ model: completion.model, content: completion.choices[0]?.message.content, }), ); ``` ```sh title="Terminal" node openai-javascript.mjs ``` ### Python ```sh title="Terminal" python3 -m venv .venv . .venv/bin/activate pip install openai==2.46.0 ``` ```python title="openai-python.py" """Public OpenAI Python SDK quickstart executed by the Nexus compatibility E2E suite.""" import json import os import openai from openai import OpenAI def required_environment(name: str) -> str: value = os.environ.get(name, "").strip() if not value: raise RuntimeError(f"{name} is required") return value client = OpenAI( base_url=required_environment("NEXUS_BASE_URL"), api_key=required_environment("NEXUS_API_KEY"), max_retries=0, timeout=10.0, ) model = required_environment("NEXUS_MODEL") messages = [{"role": "user", "content": "Keep this Python request unchanged."}] completion = client.chat.completions.create(model=model, messages=messages) stream = client.chat.completions.create( model=model, messages=messages, stream=True, stream_options={"include_usage": True}, ) stream_text = "" stream_usage = None for chunk in stream: if chunk.choices and chunk.choices[0].delta.content: stream_text += chunk.choices[0].delta.content if chunk.usage is not None: stream_usage = chunk.usage.total_tokens print( json.dumps( { "sdk_version": openai.__version__, "model": completion.model, "content": completion.choices[0].message.content, "stream_text": stream_text, "stream_usage": stream_usage, } ) ) ``` ```sh title="Terminal" python openai-python.py ``` ### OpenCode 把下面的受测 Fixture 保存为项目根目录的 `opencode.json`： ```json title="opencode.json" { "$schema": "https://opencode.ai/config.json", "model": "nexus-openrouter/provider/opaque-model-v9", "provider": { "nexus-openrouter": { "npm": "@ai-sdk/openai-compatible", "name": "Nexus OpenRouter", "options": { "baseURL": "https://gateway.nexus.microvoid.io/providers/00000000-0000-0000-0000-000000000141", "apiKey": "{env:NEXUS_API_KEY}" }, "models": { "provider/opaque-model-v9": { "name": "Provider opaque model" } } } } } ``` ```sh title="Terminal" export NEXUS_API_KEY="" opencode ``` 启动后，配置中的 `nexus-openrouter/provider/opaque-model-v9` 会选择该 OpenCode Provider 配置及其原始模型 ID。OpenCode 的自定义 Provider 格式可参阅其[官方 Provider 文档](https://opencode.ai/docs/providers)。 JavaScript/Python 使用这些环境变量；示例 UUID 和模型名是无 Secret 的兼容性 Fixture，请替换为应用交付的值： ```sh title="Terminal" export NEXUS_BASE_URL="https://gateway.nexus.microvoid.io/providers/00000000-0000-0000-0000-000000000141" export NEXUS_API_KEY="" export NEXUS_MODEL="provider/opaque-model-v9" ``` ## 3. Check the response 成功响应应保留上游响应格式和原始模型名。记录 `x-nexus-request-id`，并检查 `x-nexus-metering-status`、`x-nexus-quota-remaining` 与 `x-nexus-quota-reset`。 Python 示例同时执行普通与 Streaming 请求，并读取末尾 Usage；JavaScript 和 OpenCode Fixture 也由同一套 Node/Cloudflare E2E Gateway 行为验证。 ## Check your work - 代码只改了 Base URL 和 Key；没有增加 Nexus 专用请求字段。 - Gateway Base URL 包含完整 UUID，后面由 SDK 添加 Provider path。 - `model` 是所选上游 Provider 接受的原始值。 - 应用方能用 Request ID 在 Usage/Activity 中找到你的请求。 ## What Nexus stored 请求归因、Quota Reservation/Settlement、Usage 与 Audit 元数据。Nexus MVP 默认不把 Prompt/Response 正文作为授权事实保存。 ## What the user received 你只需要 Gateway Base URL、Inference Key 和原始模型名。Provider Key 留在平台方的加密 ProviderConnection 中。 ## Troubleshooting - `401`：确认环境变量使用 Inference Key，且 Key 未撤销或到期。 - `404`：确认 Base URL 的 UUID 完整并属于该 Key 解析出的 Workspace。 - `429`：联系应用方检查 Access 的当前 QuotaPeriod。 - Streaming 无 Usage：确认上游协议支持受测的 Usage Inspector 路径，并保留 Request ID。 ## Next steps 查看独立的 [OpenAI JavaScript](/docs/make-model-requests/openai-javascript)、[OpenAI Python](/docs/make-model-requests/openai-python) 或 [OpenCode](/docs/make-model-requests/opencode) 页面以复制单一客户端版本。 Source: https://nexus.microvoid.io/docs/quickstarts/use-my-nexus-access/index.mdx