AIMLAPI
AIMLAPI is a unified AI model API gateway providing access to 400+ state-of-the-art AI models from OpenAI, Anthropic, Google, Meta, DeepSeek, Mistral, Stability AI, and 40+ other providers through a single OpenAI-compatible API. Supported modalities include text/chat LLMs, image generation, video generation, music generation, speech-to-text, text-to-speech, vision/OCR, embeddings, and 3D generation.
APIs
AIMLAPI
Access 400+ AI models from 40+ providers via a single OpenAI-compatible REST API. Supports chat completions, image generation, video generation, speech models, embeddings, music...
Collections
GraphQL
AIMLAPI GraphQL API
AIMLAPI is an AI model aggregation API providing access to 200+ AI models including GPT-4, Claude, Llama, Stable Diffusion, Midjourney, and more through a single OpenAI-compatib...
GRAPHQLPricing Plans
Rate Limits
FinOps
Aimlapi Finops
FINOPSFeatures
Access to 400+ models from OpenAI, Anthropic, Google, Meta, DeepSeek, Mistral, Stability AI, and 40+ providers.
Drop-in replacement for OpenAI API — use existing OpenAI client libraries with AIMLAPI endpoint.
Chat completions, completion, function calling, streaming, reasoning, and code generation.
Generate images via DALL-E, Flux, Stable Diffusion, and other image generation models.
Generate video via Sora 2, Runway, and other video generation models.
Text-to-speech and speech-to-text transcription via Whisper and other speech models.
AI music generation via dedicated music models.
Image understanding, visual question answering, and OCR via vision-capable LLMs.
Generate vector embeddings for semantic search and RAG applications.
Online playground for experimenting with all available models without writing code.
Use Cases
Build conversational AI chatbots and virtual assistants using leading LLMs.
Automate text, image, video, and music content generation for media and marketing.
Build retrieval-augmented generation applications using embeddings and LLMs.
Integrate AI code generation and review capabilities into developer tools.
Extract information and summarize documents using vision and LLM models.
Add speech-to-text transcription and text-to-speech synthesis to applications.
Integrations
Use the official OpenAI Python and Node.js SDKs with AIMLAPI base URL.
Integrate AIMLAPI models with LangChain for agentic AI workflows.
Use AIMLAPI with LlamaIndex for RAG and document intelligence pipelines.
Build AI-powered web apps using Vercel AI SDK with AIMLAPI as backend.
Native Python integration via requests library or OpenAI client.
Node.js integration via OpenAI npm package pointed at AIMLAPI endpoint.