One API for every AI model & agent.

78+ image, video, speech & LLM models via REST or MCP. Pay only for what you run.

One command palette for every model

Generate images, clone voices, and run verified skills from a single API or MCP tool call.

> lumoz image · clone voice · load verified skill
Native MCP Protocol

One hub for every agent & creative engine

Connecting Claude Code, Cursor, Antigravity, Windsurf & Lumoz Desk to 78+ AI models.

Serverless Inference

Featured AI models & microservices

Every model runs behind one unified REST API and native MCP tool interface.

Lumoz Image Text to Image

Lumoz Image

Autonomous flagship visual synthesis engine. Intelligently analyzes prompt semantics in real time to generate images with optimal photorealism, typography, multilingual script, and creative variations.

Lumoz LLM LLM

Lumoz LLM

Lumoz LLM is our flagship multimodal intelligence model combining frontier language reasoning with high-resolution visual comprehension and OpenAI-compatible API access.

Lumoz Vision Text to Image

Lumoz Vision

High-precision multimodal visual perception. Analyzes lighting, subjects, styles, OCR, and extracts generative diffusion prompts.

Lumoz Video Video Generation

Lumoz Video

Flagship cinematic neural video synthesis engine. Generates fluid, ultra-high-definition motion sequences from text prompts or still images with seamless first-to-last frame interpolation.

Lumoz Decision Decision Models

Lumoz Decision

High-speed probabilistic decision model returning simplex-calibrated confidence scores across custom or preset rubrics at $0.035 / 1M tokens.

FLUX 3 Image Text to Image

FLUX 3 Image

FLUX 3 is Black Forest Labs' flagship visual model for text-to-image and reference-based editing with up to 10 images, research grounding, and multi-ratio outputs.

GPT Image 2.5 Flare Text to Image

GPT Image 2.5 Flare

Frontier multilingual visual synthesis engine specialized in rendering native Bengali text (বাংলা), complex non-Latin scripts, intricate typography, and photorealistic detail.

Nano Banana 2.1 Text to Image

Nano Banana 2.1

High-fidelity multimodal visual synthesis engine specialized in crisp on-image typography, legible signage, photorealistic rendering, and multi-image context.

Built for Velocity

Ship in 60 seconds with MCP or REST

One unified endpoint, automatic Cloudflare R2 media hosting, transparent pay-as-you-go billing, and zero GPU provisioning.

// Connect once in Claude Desktop, Cursor, or Windsurf
{
  "mcpServers": {
    "lumoz": {
      "url": "https://lumozai.com/api/mcp"
    }
  }
}

Frequently asked questions

Everything you need to know about LumozAI API, MCP, and Skills.

What do I get with one LumozAI API key?

A single pay-as-you-go balance unlocks 73+ frontier image, video, and audio models, Lumoz TTS with instant voice cloning across 90+ languages, ready-made microservices, and the Lumoz MCP server.

How does Lumoz MCP work with Claude, Cursor, and Antigravity?

Connect https://lumozai.com/api/mcp once in Claude Desktop, Claude Code, Cursor, or Windsurf. Your agent automatically gains image, video, and voice tools plus verified open-source skills via lumoz_list_skills and lumoz_get_skill.

Are LumozAI agent skills verified for security?

Yes. Every skill in the directory—including PaperMotion, Motionmaxxing, Line Art Animation, and Unslop UI—is scanned with NVIDIA SkillSpector (0 critical/high findings) and pinned to an immutable mirror under LumozAI-com.

Is there a monthly subscription required?

No. LumozAI is pay-as-you-go with transparent per-request pricing—instant voice cloning is a $0.25 one-time fee, TTS starts at $0.18 per 1,000 characters, and connecting Lumoz MCP is completely free.

Start building with LumozAI today

One key for 78+ AI models, instant voice cloning, and verified agent skills. Free to connect, pay only for what you run.