From caa85ec11c6911a01ee2b660905963b64008d7b0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?S=C3=A9bastien=20Conejo?= Date: Thu, 20 Aug 2026 14:19:13 +0200 Subject: [PATCH] docs: Google Vertex AI rows, key prefix, and the choice against the plain Google entry (issue #85) --- providers/api-key-providers.mdx | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/providers/api-key-providers.mdx b/providers/api-key-providers.mdx index df5c61e..48d0308 100644 --- a/providers/api-key-providers.mdx +++ b/providers/api-key-providers.mdx @@ -1,10 +1,10 @@ --- title: "API key providers" sidebarTitle: "API keys" -description: "Bring your own API key for OpenAI, Anthropic, Google, xAI, DeepSeek, Mistral, Groq, Cerebras, AWS Bedrock, NVIDIA NIM, OpenRouter, Hugging Face, and more." +description: "Bring your own API key for OpenAI, Anthropic, Google, Google Vertex AI, xAI, DeepSeek, Mistral, Groq, Cerebras, AWS Bedrock, NVIDIA NIM, OpenRouter, Hugging Face, and more." icon: "key" keywords: - ["OpenAI", "Anthropic", "Google Gemini", "xAI", "DeepSeek", "Mistral", "Qwen", "Moonshot", "MiniMax", "Z.ai", "OpenRouter", "Groq", "Cerebras", "Fireworks", "AWS Bedrock", "NVIDIA NIM", "Xiaomi MiMo", "Hugging Face", "Gemini Free", "API key"] + ["OpenAI", "Anthropic", "Google Gemini", "Google Vertex AI", "xAI", "DeepSeek", "Mistral", "Qwen", "Moonshot", "MiniMax", "Z.ai", "OpenRouter", "Groq", "Cerebras", "Fireworks", "AWS Bedrock", "NVIDIA NIM", "Xiaomi MiMo", "Hugging Face", "Gemini Free", "API key"] --- Most providers work the standard way: sign up, generate an API key, paste it into Manifest. Routed requests go out with that key as the credential. @@ -16,6 +16,7 @@ Most providers work the standard way: sign up, generate an API key, paste it int | [OpenAI](https://platform.openai.com) | [platform.openai.com](https://platform.openai.com) | | [Anthropic](https://www.anthropic.com) | [console.anthropic.com](https://console.anthropic.com) | | [Google](https://ai.google.dev) | [ai.google.dev](https://ai.google.dev) | +| Google Vertex AI | [cloud.google.com/vertex-ai](https://cloud.google.com/vertex-ai/generative-ai/docs/start/express-mode/overview) | | [xAI](https://x.ai) | [x.ai/api](https://x.ai/api) | | [Meta](https://dev.meta.ai) | [dev.meta.ai](https://dev.meta.ai) | | [DeepSeek](https://www.deepseek.com) | [platform.deepseek.com](https://platform.deepseek.com) | @@ -42,6 +43,10 @@ New providers are added often, so **Providers → Usage-based** in the dashboard Gemini Free is a managed tile. Manifest provisions the credential through its own gateway, so there's no key to fetch from Google first: add the tile and you have a free model to route to. It behaves like any other provider once connected. +### Google Vertex AI + +Google Vertex AI serves Gemini models through Google Cloud, and it takes an express mode API key. The connect form refuses a key that does not start with `AQ.`, and it refuses a key shorter than 40 characters. The **Google** entry above takes a Google AI Studio key instead, and Manifest enforces no prefix on that one. + BytePlus, NousResearch, Command Code, ClinePass, Kiro, GitHub Copilot, Ollama Cloud, and OpenCode Go connect through a plan rather than an API key, so they @@ -92,6 +97,7 @@ Each provider issues keys with a recognizable prefix. Useful for catching paste | Qwen | `sk-` | `sk-...` | | OpenRouter | `sk-or-` | `sk-or-...` | | Google | none | API key | +| Google Vertex AI | `AQ.` | `AQ...` | | Mistral | none | API key | | Z.ai | none | API key | | Fireworks | `fw_` | `fw_...` |