Integrations

Works with your existing stack

InferAll exposes OpenAI-compatible and Anthropic-compatible endpoints. Any tool that accepts a custom base URL works with InferAll — usually two environment variables, no code changes.

Get a key at inferall.ai/keys — no credit card required.

AI coding assistants

Claude Code

Guide →

Anthropic's terminal-native coding agent. Set ANTHROPIC_BASE_URL and cheap turns route through free open-source models; hard tasks use premium Claude.

export ANTHROPIC_BASE_URL=https://api.inferall.ai
export ANTHROPIC_API_KEY=ifu_your_key_here

Cline

VS Code extension for agentic coding. Supports ANTHROPIC_BASE_URL natively — set it in Cline's settings or environment.

export ANTHROPIC_BASE_URL=https://api.inferall.ai
export ANTHROPIC_API_KEY=ifu_your_key_here

Cursor

AI code editor. Uses the OpenAI API under the hood for its custom models.

export OPENAI_BASE_URL=https://api.inferall.ai/v1
export OPENAI_API_KEY=ifu_your_key_here

Continue

Open-source coding assistant for VS Code and JetBrains. Configure the OpenAI provider URL in Continue's settings.

export OPENAI_BASE_URL=https://api.inferall.ai/v1
export OPENAI_API_KEY=ifu_your_key_here

Aider

Terminal-based AI pair programming. Set OPENAI_API_BASE and OPENAI_API_KEY environment variables.

export OPENAI_API_BASE=https://api.inferall.ai/v1
export OPENAI_API_KEY=ifu_your_key_here

Python frameworks

LangChain

Guide →

Point ChatOpenAI at InferAll with base_url and api_key parameters.

from langchain_openai import ChatOpenAI
llm = ChatOpenAI(
    model="meta/llama-3.3-70b-instruct",
    base_url="https://api.inferall.ai/v1",
    api_key="ifu_your_key_here",
)

LlamaIndex

Guide →

Configure the OpenAI LLM with a custom API base.

from llama_index.llms.openai import OpenAI
from llama_index.core import Settings
Settings.llm = OpenAI(
    model="meta/llama-3.3-70b-instruct",
    api_base="https://api.inferall.ai/v1",
    api_key="ifu_your_key_here",
)

LiteLLM

Guide →

InferAll is OpenAI-compatible — use the openai/ provider prefix and set api_base.

import litellm
response = litellm.completion(
    model="openai/meta/llama-3.3-70b-instruct",
    messages=[{"role": "user", "content": "Hello"}],
    api_base="https://api.inferall.ai/v1",
    api_key="ifu_your_key_here",
)

Direct SDK

OpenAI Python SDK

Pass base_url and api_key to the OpenAI constructor.

from openai import OpenAI
client = OpenAI(
    base_url="https://api.inferall.ai/v1",
    api_key="ifu_your_key_here",
)

OpenAI Node.js SDK

Pass baseURL and apiKey to the OpenAI constructor.

import OpenAI from "openai";
const client = new OpenAI({
  baseURL: "https://api.inferall.ai/v1",
  apiKey: process.env.INFERALL_API_KEY,
});

Anthropic Python SDK

Pass base_url to the Anthropic constructor.

import anthropic
client = anthropic.Anthropic(
    base_url="https://api.inferall.ai",
    api_key="ifu_your_key_here",
)

Agent frameworks

CrewAI

Guide →

Set OPENAI_API_BASE and OPENAI_API_KEY environment variables — CrewAI uses them via its OpenAI dependency.

export OPENAI_BASE_URL=https://api.inferall.ai/v1
export OPENAI_API_KEY=ifu_your_key_here

AutoGPT

Guide →

Override the OPENAI_API_BASE in AutoGPT's configuration.

export OPENAI_BASE_URL=https://api.inferall.ai/v1
export OPENAI_API_KEY=ifu_your_key_here

Open Interpreter

Set the OPENAI_BASE_URL environment variable before running.

export OPENAI_BASE_URL=https://api.inferall.ai/v1
export OPENAI_API_KEY=ifu_your_key_here
interpreter

If your tool accepts a custom OpenAI API base URL or Anthropic base URL, InferAll works. See the docs for full API reference.