One API for 1000+ AI models

Fastest gateway to Chat, Reasoning, Image, Video, Audio, Voice, Search, and World models under one bill. Compatible with all popular agents.

AI/ML API MCP

1Copy the MCP URL
2Open Settings → Connectors

Add a custom connector, name it AIMLAPI, and paste the URL.

3Connect and sign in

Click Add, then click Connect and sign in with your AIMLAPI account. (Same steps in Claude Desktop and on claude.ai.) You're all set.

1Open Cursor Settings → Tools & MCPs

Click New MCP ServerAdd a Custom MCP Server. This opens ~/.cursor/mcp.json — paste:

{ "mcpServers": { "aimlapi": { "url": "https://mcp.aimlapi.com/mcp" } } }
2Enable and log in

Back in Tools & MCPs, find aimlapi (it appears Disabled). Click ···Enable, then Login.

3Sign in

A browser opens; sign in with your AIMLAPI account and click Allow. The server turns green — you're all set.

1Add the server
claude mcp add --transport http aimlapi https://mcp.aimlapi.com/mcp
2Open the MCP menu

In a Claude Code session, run /mcp, select aimlapi, and choose Authenticate.

3Sign in

A browser opens; sign in with your AIMLAPI account. You're connected.

1Copy the MCP URL
2Point your client at it

Use Streamable HTTP transport with no API key. OAuth 2.1 + PKCE with dynamic client registration handles authentication.

3Sign in

On first connect, your browser opens to sign in with your AIMLAPI account. Approve access and it connects.

1

Copy MCP URL

https://mcp.aimlapi.com/mcp
2

Configure your client

claude mcp add --transport http aimlapi https://mcp.aimlapi.com/mcp --header "Authorization: Bearer YOUR_AIMLAPI_KEY"
Add to ~/.cursor/mcp.json:
{
  "mcpServers": {
    "aimlapi": {
      "url": "https://mcp.aimlapi.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_AIMLAPI_KEY"
      }
    }
  }
}
  1. Open Settings → Connectors.
  2. Click Add custom connector.
  3. Paste the MCP URL above.
  4. Add an Authorization header with value Bearer YOUR_AIMLAPI_KEY.
  5. Save and enable the connector.
Point your client at the MCP URL above using Streamable HTTP transport, and send an Authorization: Bearer YOUR_AIMLAPI_KEY header with every request.
3

Connect and start building

Grab your key from aimlapi.com/app/keys, plug it in, and ask your agent to list models, run a chat completion, or check your balance.
View MCP docs →
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
Trusted by

Meet GPT-5.6 Sol

OpenAI's GPT-5.6 Sol, available through a single AI/ML API endpoint. Same OpenAI-compatible schema you already use — reasoning effort control, tool calling, structured outputs, image and PDF input. Switch models by changing one string.

Top-tier serverless infrastructure reduces deployment and maintenance costs.

Fastest Inference

1000+
AI Models
#1
Data Security
99.9%
Uptime SLA
24/7
Support
Advanced AI features for easy integration into your products.

Feature Packed

desktop

AI Playground

Test all API models in the sandbox environment before you integrate. We provide more than 1000 models to integrate into your app.
Settings

Simple Integration

Simply change the endpoints in your existing setup, and you're ready to go. OpenAI & Anthropic compatible.
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.aimlapi.com/v1",
    api_key="<YOUR_API_KEY>",    
)

response = client.chat.completions.create(
    model="openai/gpt-5.6-sol",
    messages=[
        {
            "role": "system",
            "content": "You are an AI assistant who knows everything.",
        },
        {
            "role": "user",
            "content": "Tell me, why is the sky blue?"
        },
    ],
)

message = response.choices[0].message.content

print(f"Assistant: {message}")
Top

Infinite Scalability

Experience low latency with our AI API, deploy instantly, and surpass rate limits without impact.
Chart

AI Plans That Grow With You

Seamlessly scale your AI capabilities
from proof-of-concept  to production and beyond.
Pay As You Go
$20
Top up
Best for:
  • Production projects
  • Fast iteration & scaling
  • Startups & indie devs
What’s included
  • Access to all models
  • No usage limits
  • Access to Playground
  • Crypto payments available
  • Pay only for what you use
  • Priority human support

Enterprise

Contact us
Best for:
  • High-volume production workloads
  • Custom infrastructure
  • Enterprise & regulated use
What is included:
  • Dedicated servers
  • Custom / private models
  • Unlimited  RPM & TPM
  • Extended  data storage
  • Shared Slack channel
  • Full staff training & integration

The Best Growth Choice
for Enterprise

Get API Key