OmniProvider

tech.omnidevPublished by omnidev.techOfficial publisherv1.0.0Updated Oct 24, 2026

Pay-per-call LLM API for agents: model catalog, pricing, unpaid x402/MPP quotes, how-to-pay.

VerifiedStreamable HTTPWeb executableFinanceAI & ML

Overview

AI-generated overview

Remote MCP server exposing a pay-per-call LLM API's model catalog, pricing, unpaid x402/MPP quotes and payment instructions to an assistant.

What you can do
  • List the public model catalog with context windows, output limits, per-million token prices, payment rails and prepaid packs
  • Get fixed per-call prices for the nano, small and brief routes and per-token prices, plus estimated cost and minimum charge for a model and token counts
  • Request an unpaid quote: one request to a paid route returns the 402 payment requirements (amount, currency, network, payee, protocol) without paying
  • Look up the payment flow for a rail, including endpoint, required headers, client nonce format and client commands
When to use it
Useful when an assistant needs to compare models and prices for a pay-per-call LLM API, estimate the cost of a request, or find out what a specific call would cost and how to pay before any money moves.
Requirements
A remote streamable HTTP endpoint; no package, environment variables or headers are declared. Payment itself is done with the caller's own wallet tooling, outside this server.
Before you install
The server returns payment requirements and instructions but holds no keys and makes no payment; any actual payment happens through your own wallet tooling, so review amounts, network and payee before paying. Quotes are generated by sending an unpaid request to a paid route.

Installation

In SourceWeft

  1. Open OmniProvider in the dashboard and add it to a workspace.
  2. 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/tech.omnidev%2Fomniprovider/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": {
    "omniprovider": {
      "type": "http",
      "url": "https://mcp.omnidev.tech/mcp"
    }
  }
}

Tools

4

omniprovider_list_models

List OmniProvider models

Returns the public catalog: model ids, context windows, maximum output tokens, price per million input and output tokens, accepted payment rails and prepaid packs that can be bought now.

Parameterstier

omniprovider_get_pricing

OmniProvider pricing

Returns prices: fixed per-call prices of the nano, small and brief routes, and per-token prices of the catalog. With a model and token counts it also returns an estimated cost and the minimum charge per rail.

Parametersmodelinput_tokensoutput_tokens

omniprovider_get_quote

OmniProvider price quote

Sends one unpaid request to a paid route and returns the 402 payment requirements (amount, currency, network, payee, protocol). No payment is made and no credential is sent; the response is the quote for that exact request body.

Parametersbodyrequiredrouterequired

omniprovider_how_to_pay

How to pay OmniProvider

Returns the payment flow for a rail: endpoint URL, required headers, the client nonce format, and client commands. Payment is produced by the caller's own wallet tooling; this server holds no keys.

Parametersrail

Version history

1
  1. v1.0.0LatestOct 16, 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.