Where to Find the Complete List of FreeLLMAPI Supported Models and Rate Limits

The authoritative, always-up-to-date catalog of FreeLLMAPI supported models and their rate limits is hosted at freellmapi.co/models.html, with programmatic access available via the /v1/models REST endpoint and the freellmapi models list CLI command.

The tashfeenahmed/freellmapi repository provides an open-source routing layer that aggregates multiple LLM providers behind a unified interface. To manage capacity and avoid throttling, you need accurate metadata for each model, including RPM (Requests Per Minute), RPD (Requests Per Day), TPM (Tokens Per Minute), and TPD (Tokens Per Day) limits, plus context window sizes and any free-token allowances.

Official Model Catalog Location

The single source of truth for FreeLLMAPI supported models resides on the project website at https://freellmapi.co/models.html. This page displays the complete set of routable models and is dynamically generated from live provider feeds, ensuring the rate limits and availability status are current.

According to the repository documentation, both the root README.md and docs/install.md explicitly direct users to this URL for the "full, always-current list" of models. Because the catalog is built dynamically rather than hard-coded, the website supersedes any static documentation for determining current support and limits.

Accessing Models Programmatically

While the website provides a human-readable interface, the codebase exposes the same data through machine-readable interfaces implemented in server/src/services/model-listing.ts and cli/src/models.ts.

Via the HTTP API

The server implementation in server/src/services/model-listing.ts exposes a REST endpoint at /v1/models that returns a JSON array of all supported models. Each object includes the rateLimits, contextWindow, and freeTokenBudget fields.

To fetch the entire catalog from a locally running instance:

curl http://localhost:3001/v1/models | jq .

To inspect a specific model’s limits, append the model ID to the endpoint:

curl http://localhost:3001/v1/models/<model-id> | jq .

This returns granular details including per-minute and per-day token allowances.

Via the CLI

The command-line interface, implemented in cli/src/models.ts, provides a convenient wrapper for the same data. After installing the CLI, list all available models with:

freellmapi models list

This command queries the local or remote API and formats the output for terminal viewing, displaying the same rate limit metadata available through the HTTP interface.

Understanding Rate Limit Metadata

When you query the model list—whether through the website, API, or CLI—you encounter several standardized limit fields:

• RPM: Requests allowed per minute.
• RPD: Requests allowed per day.
• TPM: Tokens processed per minute.
• TPD: Tokens processed per day.

Additionally, the response includes contextWindow, indicating the maximum token length for the model’s context, and freeTokenBudget, which specifies any no-cost token allocations for eligible models. These values are sourced directly from provider feeds and updated dynamically.

Summary

• The definitive list of FreeLLMAPI supported models and rate limits lives at freellmapi.co/models.html.
• The HTTP endpoint /v1/models (implemented in server/src/services/model-listing.ts) serves this data as JSON.
• The CLI command freellmapi models list (implemented in cli/src/models.ts) provides terminal access to the same catalog.
• Rate limit fields include RPM, RPD, TPM, TPD, plus contextWindow and freeTokenBudget for capacity planning.

Frequently Asked Questions

Where is the official FreeLLMAPI model catalog hosted?

The authoritative catalog is hosted at https://freellmapi.co/models.html. This URL is referenced in the repository README.md and docs/install.md as the single source of truth for model support, rate limits, and capabilities, and it is updated dynamically from live provider feeds.

How can I retrieve model rate limits using the API?

Send a GET request to the /v1/models endpoint to retrieve the full catalog, or query /v1/models/<model-id> for specific details. The JSON response includes rateLimits, contextWindow, and freeTokenBudget fields.

What do RPM and TPM mean in the rate limit definitions?

RPM stands for Requests Per Minute, while TPM stands for Tokens Per Minute. The catalog also lists RPD (Requests Per Day) and TPD (Tokens Per Day) limits to help you manage daily quotas and throughput.

Which source files handle model listing in the FreeLLMAPI codebase?

The server-side routing logic resides in server/src/services/model-listing.ts, which implements the /v1/models endpoint. The CLI implementation is located in cli/src/models.ts, handling the models list command and related interactions.

{
  "mcpServers": {
    "instagit": {
      "command": "npx",
      "args": ["-y", "instagit@latest"]
    }
  }
}