RelaySwitch is answering right now. Last checked 10 min ago. It exposes 15 tools.
Every major chat, image and video model on one prepaid key. OpenAI, Anthropic and Gemini formats.
Uptime history
20 hours of history
20 hours agonow
100.0%
Uptime 24h
72 of 72 checks
15
Tools
read from the server
139 ms
Response time
average over 24h
open, no key
Access
streamable-http
Nothing serious here today
Today is the operative word: we check RelaySwitch every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 10 min ago.
run in your terminal
claude mcp add gateway --transport http https://api.relayswitch.io/mcpSettings → Connectors → Add custom connector, then paste this address
https://api.relayswitch.io/mcp~/.codex/config.toml
[mcp_servers.gateway]
url = "https://api.relayswitch.io/mcp".cursor/mcp.json
{
"mcpServers": {
"gateway": {
"url": "https://api.relayswitch.io/mcp"
}
}
}.vscode/mcp.json
{
"servers": {
"gateway": {
"type": "http",
"url": "https://api.relayswitch.io/mcp"
}
}
}Available tools 15
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
media
list_media_models
Every media model on RelaySwitch with its id, kind, endpoint, unit and price per image, second, generation or minute at each setting, next to the developer's price where recorded. No key needed. Live from GET /v1/catalog/media.
media_model
Everything generate needs to call one image, video, speech, music or 3D model: each setting under params with its type, the values it takes, its range and its default, and the price per unit at each setting under pricing. No key needed. Live from GET /v1/catalog/media.
media_quote
What generate would charge for exactly these settings, at the key's own rates: the units billed, the charge, and the developer's own price for the same request where one is on record. The settings are checked as a real request's would be, so a wrong value fails here, not at the model. Nothing runs and nothing is charged. Needs the key. Live from POST /v1/generations/quote.
chat
chat
Sends messages to any chat model id through POST /v1/chat/completions and returns the answer, the token usage and what the request cost. system adds instructions, image_urls lets a model that sees images look at them (a file generate made works), web_search lets the model search while it answers. Billed to the key in the MCP request's Authorization header (Bearer sk-relay-live-...); without one it fails.
compare
compare
Sends the same conversation (or one prompt) to 2 to 5 chat model ids at once through POST /v1/chat/completions and returns every answer side by side with its token usage, cost and time, plus the total. For a second opinion from another model, or to pick the model that answers a kind of question best. Completions are capped at max_tokens each (default 1024). Each model is billed to the key in the MCP request's Authorization header; a model that fails is reported and not charged.
embed
embed
Embeds one text or up to 64 through POST /v1/embeddings with an embedding model id from list_models (type embedding) and returns one vector per text, in order, with the token usage and the charge. Billed to the key in the MCP request's Authorization header.
estimate
estimate
The cost of a request on every chat model (or the ids given), cheapest first, with the developer's list cost and the saving. Give input_tokens, or a prompt / messages to count from. With the caller's key, prices are the key's own (price locks included). Live from POST /v1/estimate.
generate
generate
Runs any media model id from list_media_models with its settings (see media_model) through POST /v1/generations, waits up to wait_seconds for the files, and returns the generation: a link per file (kept 30 days), a finished image inline, and the charge. A video that is still running when the wait ends is returned as it stands; call generation with its id to keep waiting. Charged to the key in the MCP request's Authorization header when the model accepts the task; a failed generation is refunded in full. To go from an image to a video or an edit, pass the image's URL in image_urls.
generation
generation
One generation by id: its status, progress, files and charge, waiting up to wait_seconds for it to finish first. Use it after generate answers with a video still running. Needs the key the generation was made with. Live from GET /v1/generations/{id}.
generations
generations
The organization's generations, newest first, each with its status, model, files and charge: the asset library behind generate. Filter by kind, model or status; page with before. Files are kept 30 days. Needs the key. Live from GET /v1/generations.
models
list_models
Every chat, embedding, rerank and transcription model on RelaySwitch with its id, type, the routes and tools that take it, our price (per million tokens, or per audio minute for transcription), the developer's list price where recorded, the wire formats it answers (openai, anthropic, gemini) and its specs. Image, video, speech, music and 3D models are in list_media_models. No key needed. Live from GET /v1/catalog.
proof
proof
Whether each model is still the model it says it is: every day one fixed prompt goes to every model and the verdict per model is stable, changed, failed or unchecked, with the time of the last check and how long the answer has been unchanged. No key needed. Live from GET /v1/proof.
rerank
rerank
Orders up to 100 documents by relevance to a query through POST /v1/rerank with a rerank model id from list_models (type rerank): each result's index into documents, its score and its text, best first. Billed per input token to the key in the MCP request's Authorization header.
search
search
One web search through POST /v1/search: titles, URLs, snippets and publish dates, up to 10 results, optionally only from the last day, week, month or year. Billed as one search to the key in the MCP request's Authorization header (the price in GET /v1/catalog server_tools); a search that fails is not charged.
transcribe
transcribe
Turns the speech in an audio or video file at an https URL (25 MB at most; a file generate made works) into text through POST /v1/audio/transcriptions, or into English with translate. Use a transcription model id from list_models (type transcription). Billed per second of audio to the key in the MCP request's Authorization header; a request that fails is not charged.
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://api.relayswitch.io/mcp | streamable-http | answering | 118 ms | 10 min ago |
Alternatives to RelaySwitch
same job, measured the same wayMediaEngine
by tr1ckymag1ca1
AI image, video, and audio generation for MCP — one API key, every model, wiring never changes.
K
Korpi API
by reksely
MCP server for the Korpi API: every top AI video, image and text model behind one key and one bill.
Pixel Surgeon
by j-east
AI image and video generation, editing, and region repair via Gemini, OpenAI, and Grok.
Pixfaro
by pixfaro
Generate images with any major model — one API key, one prepaid balance, one MCP.
PZERO
by pzero
Prepaid inference for agents over hosted MCP. Chat, image, and video.
OneOver
by oneover
Chat, image, video, and audio models from many vendors behind one remote MCP server and one key.
Unifically
by unifically
One API for 100+ AI video, image, music and speech models.
MCP Gemini
by crunchtools
MCP server for Google Gemini AI - text, image, video, research, and more
RelaySwitch — questions
Answers built from our own checks of this server.
What can RelaySwitch do?
It exposes 15 tools, read directly from the server on our last check. Among them: chat, compare, embed, estimate, generate, generation and 9 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README.
How MCP servers expose tools in the first place →
Is RelaySwitch working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 72 of 72 checks got a reply (100.0%), average response time 139 ms. The bar chart above shows every period we have measured.
How do I connect RelaySwitch?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does RelaySwitch need an API key?
No. RelaySwitch completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 15 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is RelaySwitch?
It answers our handshake in 139 ms on average, which is faster than 84% of all working MCP servers we measure. That puts it in the quick quarter of the ecosystem. The comparison comes from our own checks across the whole registry, every 15 minutes.