Featherless ACTION

List Models

List the models available on Featherless (GET /v1/models). Returns model objects each containing an id field to pass as the model prop in Create Chat Completion and Create Text Completion. The catalog is very large (~22k models), so results are paged (100 per page by default) and each model is trimmed to key fields (id, name, model_class, context_length, max_completion_tokens, available_on_current_plan); use q to search, page to page through, or fields to change which fields are returned. Example: q=Qwen returns Qwen-family models with ids like Qwen/Qwen3-8B (pass that id as the model prop in a completion). Results are paged (100 per page); increment page to fetch more. Because a page size is always sent, the response also includes pagination (current_page, total_pages, total_items) and a total count. See the documentation.

Action
Read only
API key
SDK
MCP

Start building

IMPLEMENTATION

Call this tool

Connect a user's Featherless account once, then configure and run List Models from your backend or agent.

Pipedream Connect

import { PipedreamClient } from "@pipedream/sdk"

const pd = new PipedreamClient({
  projectId: process.env.PIPEDREAM_PROJECT_ID!,
  clientId: process.env.PIPEDREAM_CLIENT_ID!,
  clientSecret: process.env.PIPEDREAM_CLIENT_SECRET!,
  projectEnvironment: "production",
})

const result = await pd.actions.run({
  id: "featherless-list-models",
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  configuredProps: {
    featherless: { authProvisionId: "apn_xxxxxxx" },
    q: "Search Query",
    availableOnCurrentPlan: true,
  },
})

console.log(result)

curl -X POST https://api.pipedream.com/v1/connect/{project_id}/actions/run \
  -H "Content-Type: application/json" \
  -H "X-PD-Environment: production" \
  -H "Authorization: Bearer {access_token}" \
  -d '{
    "external_user_id": "{external_user_id}",
    "id": "featherless-list-models",
    "configured_props": {
      "featherless": { "authProvisionId": "apn_xxxxxxx" },
      "q": "Search Query",
      "availableOnCurrentPlan": true
    }
  }'

// accessToken: mint a short-lived token with the Connect SDK — see the MCP guide
const transport = new StreamableHTTPClientTransport(
  new URL("https://remote.mcp.pipedream.net/v3"),
  {
    requestInit: {
      headers: {
        Authorization: `Bearer ${accessToken}`,
        "x-pd-project-id": "{project_id}",
        "x-pd-environment": "production",
        "x-pd-external-user-id": "{external_user_id}", // any stable ID for this user in your system
        "x-pd-app-slug": "featherless",
      },
    },
  },
)

const mcp = new Client({ name: "my-agent", version: "1.0.0" })
await mcp.connect(transport)

const { tools } = await mcp.listTools()

// listTools() hands your model this tool's input schema, so it can
// fill the arguments itself:
const result = await mcp.callTool({
  name: "featherless-list-models",
  arguments: {
    q: "Search Query",
    availableOnCurrentPlan: true,
  },
})

SCHEMA

Inputs

Pipedream supplies the connected account. Your application provides the operation-specific values below. Dynamic inputs are resolved against that user's account.

List Models inputs
Property	Type	Description
`q` Search Query	`string`	Optional free-text search query to filter models by name or id. Optional
`availableOnCurrentPlan` Available on Current Plan	`boolean`	When true, only return models available on the connected account's current plan (maps to `available_on_current_plan`). Optional
`tags` Tags	`string`	Optional comma-separated tags to filter by, e.g. `chat,instruct`. Optional
`page` Page	`integer`	Page number of results to fetch (1-based). Optional
`perPage` Per Page	`integer`	Number of models to return per page. Min 1, max 1000 (maps to `per_page`). Defaults to 100. Note the API floors values below 100 at 100 per page. Optional
`fields` Fields	`string[]`	An array of field names to keep on each returned model, e.g. `["id", "is_gated"]`. Omit to use the compact default (id, name, model_class, context_length, max_completion_tokens, available_on_current_plan). Available keys also include `is_gated` and other model metadata. Optional

REFERENCE

Tool details

Behavior hints are published with the component in the Pipedream registry and surface as MCP tool annotations, so an agent can reason about a tool before it calls it.

Registry key: featherless-list-models
Version: 0.0.2
App: Featherless
Authentication: API key
Read-only: Yes
Destructive: No
Open world: Yes
Source: View on GitHub ↗

Call this tool #

Inputs #

Tool details #

Call this tool

Inputs

Tool details