Universal Compatibility

Works with Every AI Framework

Drop-in OpenAI-compatible API that works with LangChain, LlamaIndex, CrewAI, AutoGen, Vercel AI SDK, and 14+ other frameworks. Change two lines of code. Keep everything else.

Two-Line Migration

Forge exposes a fully OpenAI-compatible API at https://api.optima-forge.com/v1. Any SDK, framework, or tool that supports OpenAI works with Forge by changing the base URL and API key. Your prompts, tools, streaming logic, function calling, and structured output all work identically. Behind the scenes, Forge adds intelligent routing, persistent memory, security scanning, and full observability to every request.

Integration Examples

Integrating with Forge takes under a minute. Here are examples for the most popular SDKs and frameworks.

Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    base_url="https://api.optima-forge.com/v1",
    api_key="forge_sk_..."
)

response = client.chat.completions.create(
    model="auto",
    messages=[{"role": "user", "content": "Hello"}],
    extra_body={"forge": {"cache": True}}
)

TypeScript (Vercel AI SDK)

import { openai } from "@ai-sdk/openai";
import { generateText } from "ai";

const { text } = await generateText({
  model: openai("auto", {
    baseURL: "https://api.optima-forge.com/v1",
    apiKey: "forge_sk_..."
  }),
  prompt: "Explain quantum computing"
});

Python (LangChain)

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    base_url="https://api.optima-forge.com/v1",
    api_key="forge_sk_...",
    model="auto"
)

response = llm.invoke("Summarize this document")

14+ Supported Frameworks

Every framework that supports OpenAI-compatible APIs works with Forge. Here is a non-exhaustive list of frameworks we actively test against and support.

LangChain

Orchestration

Use ChatOpenAI with Forge's base URL. All chains, agents, and retrieval pipelines work without modification. Memory, tools, and callbacks pass through transparently.

LlamaIndex

Data Framework

Configure the OpenAI LLM class with Forge credentials. Query engines, chat engines, and data agents run against Forge's routing layer with full memory and security.

CrewAI

Multi-Agent

Set Forge as the LLM provider for all crew agents. Role-based agent orchestration works natively, with Forge adding cross-provider routing and persistent memory.

AutoGen

Multi-Agent

Point AutoGen's model client at Forge. Multi-agent conversations, code execution, and group chats route through Forge with automatic failover and cost tracking.

Semantic Kernel

Orchestration

Use the OpenAI connector with Forge's endpoint. Planners, plugins, and memory connectors work out of the box. Microsoft Copilot-style applications benefit from Forge's security pipeline.

Vercel AI SDK

Frontend

Use the OpenAI provider with a custom base URL. Streaming, tool calling, and structured output generation work identically through Forge's gateway.

OpenAI Agents SDK

Multi-Agent

Route OpenAI Agents through Forge for multi-provider failover, cost optimization, and security scanning. Agent handoffs and tool calls are fully supported.

Haystack

Data Framework

Configure the OpenAIChatGenerator with Forge's API URL. Pipelines, retrievers, and generators route through Forge with tracing and memory enabled.

LiteLLM

Gateway

Forge can serve as a backend for LiteLLM or replace it entirely. Both expose OpenAI-compatible APIs, so migration is a base URL change.

Instructor

Structured Output

Structured output extraction with Pydantic models works through Forge. The gateway preserves function calling and JSON mode for all supported providers.

DSPy

Programming

Configure DSPy's language model to use Forge's endpoint. Signature-based programming, optimizers, and assertions run through Forge with cost tracking.

Mastra

Orchestration

Use Forge as the LLM backend for Mastra agents, workflows, and tool integrations. The OpenAI-compatible API ensures full compatibility.

Pydantic AI

Structured Output

Configure the OpenAI model with Forge's base URL. Structured responses, tool calls, and streaming all work natively through the gateway.

Spring AI

Enterprise

Java and Kotlin applications use Spring AI's OpenAI auto-configuration with Forge's endpoint URL. Chat clients, embedding clients, and function calling are supported.

All Major LLM Providers

Forge routes to 14+ LLM providers through a unified interface. Add providers to your account via the dashboard, and Forge handles authentication, rate limiting, and failover automatically.

OpenAI

GPT-4o, GPT-4o-mini, o1, o3

Anthropic

Claude Opus 4, Sonnet 4, Haiku

Google

Gemini 2.5 Pro, Flash, Ultra

Mistral

Large, Medium, Small, Codestral

Meta (via providers)

Llama 4 Scout, Maverick

Cohere

Command R+, Command R

Perplexity

Sonar Pro, Sonar

Groq

Llama, Mixtral (ultra-fast inference)

Together AI

Open-source models at scale

Fireworks AI

Optimized open-source serving

DeepSeek

DeepSeek V3, Coder

xAI

Grok 3, Grok 3 Mini

Amazon Bedrock

Claude, Llama, Titan

Azure OpenAI

GPT-4o, GPT-4o-mini (Azure-hosted)

Switch in under a minute

Replace your OpenAI base URL with Forge's endpoint. Your existing code, prompts, and integrations work immediately. Gain routing, memory, security, and observability with zero refactoring.

Get API Key Quickstart Guide