API ManyNew models: Qwen 3.8 Max, Claude Haiku 5.5, Claude Opus 5.5, Claude Sonnet 5.5

Integrations

API Many works anywhere you can set an OpenAI or Anthropic base URL. Pick your tool for the exact settings.

OpenAI-compatible base URLhttps://apimany.com/v1
Anthropic base URLhttps://apimany.com
Get an API key

Claude Code

Coding agents
  1. Point Claude Code at API Many with two environment variables, then pick any Claude model.
export ANTHROPIC_BASE_URL=https://apimany.com
export ANTHROPIC_AUTH_TOKEN=YOUR_API_KEY
export ANTHROPIC_MODEL=claude-opus-5-5
claude

Codex CLI

Coding agents
  1. Add API Many as a model provider in ~/.codex/config.toml.
model = "gpt-6.1-sol"
model_provider = "apimany"

[model_providers.apimany]
name = "API Many"
base_url = "https://apimany.com/v1"
env_key = "APIMANY_API_KEY"
wire_api = "chat"

Cline / Roo Code

Coding agents
  1. Open the provider settings and choose "OpenAI Compatible".
  2. Base URL: https://apimany.com/v1, API key: your key, Model ID: any model id such as claude-sonnet-5-5.

Continue

Coding agents
  1. Add a model to ~/.continue/config.yaml:
models:
  - name: Claude Sonnet 5.5 (API Many)
    provider: openai
    model: claude-sonnet-5-5
    apiBase: https://apimany.com/v1
    apiKey: YOUR_API_KEY

Aider

Coding agents
  1. Use the OpenAI-compatible settings:
export OPENAI_API_BASE=https://apimany.com/v1
export OPENAI_API_KEY=YOUR_API_KEY
aider --model openai/deepseek-v4.1-flash

Cherry Studio

Chat apps
  1. Settings → Model Provider → Add, type "OpenAI".
  2. API host https://apimany.com, your key, then "Manage" to add model ids.

LobeChat

Chat apps
  1. Settings → Language Model → OpenAI.
  2. API proxy URL https://apimany.com/v1, your key, then add custom model ids.

Open WebUI

Chat apps
  1. Admin Settings → Connections → OpenAI API.
  2. URL https://apimany.com/v1 and your key; models are listed automatically.

NextChat

Chat apps
  1. Settings → Custom Endpoint.
  2. Endpoint https://apimany.com, your key, and custom models such as gpt-6.1-sol,claude-opus-5-5.

Chatbox

Chat apps
  1. Settings → Model Provider → Add custom provider (OpenAI API compatible).
  2. API host https://apimany.com/v1 and your key.

OpenAI SDK

SDKs & frameworks
  1. Set base_url and api_key; everything else stays the same.
from openai import OpenAI
client = OpenAI(base_url="https://apimany.com/v1", api_key="YOUR_API_KEY")

Anthropic SDK

SDKs & frameworks
  1. Use the base URL without /v1 for Claude models.
import Anthropic from '@anthropic-ai/sdk'
const client = new Anthropic({ baseURL: 'https://apimany.com', apiKey: process.env.APIMANY_API_KEY })

Vercel AI SDK

SDKs & frameworks
  1. Create an OpenAI-compatible provider.
import { createOpenAICompatible } from '@ai-sdk/openai-compatible'
import { generateText } from 'ai'

const apimany = createOpenAICompatible({ name: 'apimany', baseURL: 'https://apimany.com/v1', apiKey: process.env.APIMANY_API_KEY })
const { text } = await generateText({ model: apimany('gemini-4-argon'), prompt: 'Hello' })

LangChain

SDKs & frameworks
  1. Use ChatOpenAI with a custom base URL.
from langchain_openai import ChatOpenAI
llm = ChatOpenAI(model="claude-sonnet-5-5", base_url="https://apimany.com/v1", api_key="YOUR_API_KEY")
print(llm.invoke("Hello").content)

LlamaIndex

SDKs & frameworks
  1. Use OpenAILike with your key.
from llama_index.llms.openai_like import OpenAILike
llm = OpenAILike(model="deepseek-v4.1-flash", api_base="https://apimany.com/v1", api_key="YOUR_API_KEY", is_chat_model=True)

Dify

Workflows
  1. Settings → Model Provider → OpenAI-API-compatible → Add model.
  2. API endpoint https://apimany.com/v1, your key, and the model id.

n8n

Workflows
  1. Create an OpenAI credential with Base URL https://apimany.com/v1 and your key.
  2. Use the OpenAI Chat Model node, or an HTTP Request node for image and video tasks.

MCP clients

Workflows
  1. Claude Desktop, Cursor, VS Code and Windsurf can use API Many tools over MCP.
MCP setup guide →