One API for every modality
Text, vision, speech, image and video models from Groq, Gemini, Hugging Face and OpenRouter — accessed through a single, secure, metered gateway. Buy credits, create a key, start building.
New accounts get 100 free credits once. No card required.
curl https://models.adomicarts.com/api/v1/chat/completions \
-H "Authorization: Bearer $MMG_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"openai/gpt-oss-20b:free","messages":[{"role":"user","content":"Explain quantum entanglement simply."}]}'Powered by
Every modality you need
Eight capabilities behind one consistent, OpenAI-compatible API.
Text Generation
Chat and completion with open-source LLMs. OpenAI-compatible.
Image to Text
Vision understanding, captioning, and OCR from images.
Text to Image
Generate images from prompts with FLUX and SDXL.
Image to Image
Edit and transform images with a guiding prompt.
Text to Video
Create short video clips from text prompts.
Text to Speech
Natural-sounding speech synthesis from text.
Speech to Text
Fast, multilingual transcription with Whisper.
Embeddings
Vector embeddings for search and RAG (entity-to-entity).
Ship in three steps
Buy credits
Sign up and top up a prepaid credit balance. Pay only for what you use, across every modality.
Create an API key
Generate a secret key in your dashboard. We store only a hash — your key is shown once.
Call the gateway
Point your OpenAI-compatible client at our base URL. We route, meter, and bill automatically.
Featured models
A taste of what's available on the gateway.
OpenAI: gpt-oss-20b (free)
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...
OpenAI: gpt-oss-120b (free)
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...
Llama 3.3 70B Versatile
High-quality reasoning and generation for complex tasks.
Llama 3.1 8B Instant
Fast, capable general-purpose LLM. Great default for most tasks.
Gemini 2.5 Flash
Google's fast multimodal model with a large context window.
Qwen: Qwen3 Coder 480B A35B (free)
Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...
Keys stay secret
We store only a SHA-256 hash of your key. Provider keys never leave our servers.
Metered & rate-limited
Atomic credit accounting and per-key rate limits protect you from surprises.
One integration
Swap models and providers without touching your client code.
Build with open-source AI today
Create an account, grab your free credits, and make your first request in minutes.
Get started