RelaySwitch

io.relayswitchPublished by relayswitch.ioOfficial publisherv1.0.0Updated Nov 8, 2026

Every major chat, image and video model on one prepaid key. OpenAI, Anthropic and Gemini formats.

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingMedia & DesignAI & ML

Overview

AI-generated overview

RelaySwitch is a remote gateway that lets an assistant call many chat, embedding, rerank, transcription and media models on one prepaid API key.

What you can do
  • List and price models: browse chat, embedding, rerank and transcription models, media models and their settings, and estimate or quote request costs before sending.
  • Send and compare conversations: chat with any model id, or send the same prompt to 2 to 5 models side by side with cost and time.
  • Search the web: run one web search returning titles, URLs, snippets and publish dates.
  • Work with text and audio: embed text, rerank documents by relevance, and transcribe audio or video files from a URL.
  • Generate and track media: run image, video, speech, music or 3D models, poll a running generation, and list the organization's past generations.
  • Check model integrity: see a daily per-model verdict…
When to use it
Useful when you want one key and one endpoint for many providers' models, when you need to compare answers across models or price a request before sending it, or when you want image, video and audio generation alongside chat in the same assistant.
Requirements
A remote streamable HTTP endpoint; no local package. A RelaySwitch API key sent as a bearer token in the Authorization header, obtained from the provider's console. Some catalog and proof tools work without a key; chat, compare, search, embed, rerank, transcribe, media_quote, generate, generation and generations require it. Prepaid account credit and network access.
Before you install
Most tools bill the prepaid key per token, per search, per audio second or per media unit, so usage spends real money; use estimate and media_quote first. The key is a secret passed in the Authorization header. Prompts, documents, audio and media inputs are sent to a third-party API. Generations are stored and listed per organization, and files are kept only 30 days. The service advertises abliterated and uncensored models, so outputs may be unfiltered.

Installation

In SourceWeft

  1. Open RelaySwitch in the dashboard and add it to a workspace.
  2. Connect Authorization token credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.relayswitch%2Fgateway/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "relayswitch": {
      "type": "http",
      "url": "https://api.relayswitch.io/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

Tools

15

list_models

List every text model and price

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.

Parameterstypesearchdeveloper

list_media_models

List image, video, speech and 3D models and prices

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.

Parameterskindsearch

media_model

One media model's settings and prices

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.

Parametersmodelrequired

estimate

Estimate what a request costs

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.

Parametersmodelspromptmessagesinput_tokensoutput_tokens

media_quote

Price a generation before running it

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.

Parametersinputrequiredmodelrequired

proof

Daily real-model check

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.

Parametersmodel

chat

Send a chat request

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.

Parametersmodelrequiredsystemmessagesrequiredimage_urlsmax_tokensweb_searchtemperature

compare

Ask several models the same thing

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.

Parametersmodelsrequiredpromptsystemmessagesimage_urlsmax_tokenstemperature

embed

Turn text into vectors

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.

Parametersinputrequiredmodelrequired

rerank

Rank documents by relevance

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.

Parametersmodelrequiredqueryrequiredtop_ndocumentsrequired

transcribe

Transcribe audio or video

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.

Parametersmodelrequiredpromptlanguageaudio_urlrequiredtranslate

generate

Generate an image, video, speech, music or 3D file

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.

Parametersinputrequiredmodelrequiredpreviewwait_seconds

generation

A generation's status and files

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}.

Parametersidrequiredpreviewwait_seconds

generations

List the generations made on this key's organization

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.

Parameterskindlimitmodelbeforestatus

Version history

1
  1. v1.0.0LatestNov 8, 2026

Score

83% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.