Featherless AI

Access 11,900+ open-source models through Featherless AI and Portkey.

Quick Start

Get started with Featherless AI in under 2 minutes:

Python

from portkey_ai import Portkey

# 1. Install: pip install portkey-ai
# 2. Add @featherless-ai provider in model catalog
# 3. Use it:

portkey = Portkey(api_key="PORTKEY_API_KEY")

response = portkey.chat.completions.create(
    model="@featherless-ai/google/gemma-3-4b-it",
    messages=[{"role": "user", "content": "Hello!"}]
)

print(response.choices[0].message.content)

import Portkey from 'portkey-ai'

// 1. Install: npm install portkey-ai
// 2. Add @featherless-ai provider in model catalog
// 3. Use it:

const portkey = new Portkey({
    apiKey: "PORTKEY_API_KEY"
})

const response = await portkey.chat.completions.create({
    model: "@featherless-ai/google/gemma-3-4b-it",
    messages: [{ role: "user", content: "Hello!" }]
})

console.log(response.choices[0].message.content)

from openai import OpenAI
from portkey_ai import PORTKEY_GATEWAY_URL

# 1. Install: pip install openai portkey-ai
# 2. Add @featherless-ai provider in model catalog
# 3. Use it:

client = OpenAI(
    api_key="PORTKEY_API_KEY",  # Portkey API key
    base_url=PORTKEY_GATEWAY_URL
)

response = client.chat.completions.create(
    model="@featherless-ai/google/gemma-3-4b-it",
    messages=[{"role": "user", "content": "Hello!"}]
)

print(response.choices[0].message.content)

import OpenAI from "openai"
import { PORTKEY_GATEWAY_URL } from "portkey-ai"

// 1. Install: npm install openai portkey-ai
// 2. Add @featherless-ai provider in model catalog
// 3. Use it:

const client = new OpenAI({
    apiKey: "PORTKEY_API_KEY",  // Portkey API key
    baseURL: PORTKEY_GATEWAY_URL
})

const response = await client.chat.completions.create({
    model: "@featherless-ai/google/gemma-3-4b-it",
    messages: [{ role: "user", content: "Hello!" }]
})

console.log(response.choices[0].message.content)

# 1. Add @featherless-ai provider in model catalog
# 2. Use it:

curl https://api.portkey.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "x-portkey-api-key: $PORTKEY_API_KEY" \
  -d '{
    "model": "@featherless-ai/google/gemma-3-4b-it",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Add Provider in Model Catalog

Before making requests, add Featherless AI to your Model Catalog:

1. Go to Model Catalog → Add Provider
2. Select Featherless AI
3. Enter your Featherless AI API key
4. Name your provider (e.g., featherless-ai)

Complete Setup Guide

See all setup options and detailed configuration instructions

---

Supported Models

Featherless AI provides access to 11,900+ open-source models with unlimited tokens:

Check Featherless AI’s documentation for the complete model catalog.

---

Next Steps

Gateway Configs

Add fallbacks, load balancing, and more

Observability

Monitor and trace your Featherless requests

Prompt Library

Manage and version your prompts

Metadata

Add custom metadata to requests

For complete SDK documentation:

SDK Reference

Complete Portkey SDK documentation