Stability AI
stability-aiStability AI's 5 models on ModelRunner span Text-to-Image, Audio-to-Audio and Music, from $0.015 per megapixel upward.
5 public models — every one runnable in a free playground, through the REST API and JavaScript SDK, or from an AI assistant over MCP.
Stability AI models & pricing
Stable Audio 2.5 Audio-to-Audio
stability-ai
Transform an existing audio clip into new music or sound effects guided by a text prompt — restyle, re-instrument, or reimagine a source track, returned as a WAV.
Stable Diffusion 3.5 Large Turbo
stability-ai
Generate high-quality images from a text prompt in just a few steps — the fastest, lowest-cost Stable Diffusion 3.5 tier.
Stable Diffusion 3.5 Medium
stability-ai
Generate high-quality images from a text prompt with a fast, low-cost 2.5B model tuned for prompt adherence and typography.
Stable Audio 2.5
stability-ai
Generate long-form music and sound effects from a text prompt — up to ~190 seconds of WAV audio in a single call.
Stable Diffusion 3.5 Large
stability-ai
Generate high-quality images from a text prompt with strong prompt adherence, accurate typography, and diverse visual styles.
What you can build with Stability AI models
- Restyle a track into a new genre — folk guitar into cinematic orchestral Stable Audio 2.5 Audio-to-Audio
- Remix a source clip into an electronic, lofi, or acoustic version Stable Audio 2.5 Audio-to-Audio
- Turn a rough musical idea into a fuller arranged version from a prompt Stable Audio 2.5 Audio-to-Audio
- Generate prompt-guided variations of a reference audio clip Stable Audio 2.5 Audio-to-Audio
- Reimagine ambience or sound effects in a different style Stable Audio 2.5 Audio-to-Audio
- Generate images fast and cheaply from a text description in bulk Stable Diffusion 3.5 Large Turbo
- Get near-real-time image previews while iterating on a prompt Stable Diffusion 3.5 Large Turbo
- Batch-generate many AI art variations at low cost Stable Diffusion 3.5 Large Turbo
Browse by capability
Call a Stability AI model in one request
Every endpoint shares the same lifecycle: submit to the queue, poll the status URL, fetch the result. Swap the endpoint to switch models — nothing else changes.
cURL
curl -X POST https://queue.modelrunner.run/stability-ai/stable-audio-2.5/audio-to-audio \
-H "Authorization: Key $MRUN_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "prompt": "..." }'
# → { "request_id": "...", "status_url": "...", "response_url": "..." }Use Stability AI models from Claude & Cursor
Connect the ModelRunner MCP server once and your AI assistant can run every Stability AI model on this page as a tool — authorized via OAuth, results returned as hosted URLs in the conversation.
Claude Code
claude mcp add --transport http modelrunner https://mcp.modelrunner.run/mcpFrequently asked questions
What Stability AI models can I run on ModelRunner?
The catalog has 5 public Stability AI models: Stable Audio 2.5 Audio-to-Audio, Stable Diffusion 3.5 Large Turbo, Stable Diffusion 3.5 Medium and 2 more. They cover text-to-image, audio-to-audio and music. Each one has its own page with a free playground, the full input schema, and copy-paste code.
How much do Stability AI models cost?
Pay-per-use, with no subscription: the 3 Stability AI models billed per megapixel start at $0.015, and every page publishes its own rate — some are tiered, so a lower resolution or a shorter clip costs less per run. You buy credits and pay only for what you generate.
How do I call a Stability AI model from the API?
POST to https://queue.modelrunner.run/stability-ai/stable-audio-2.5/audio-to-audio with an Authorization: Key header and the input fields as the top-level JSON body (no wrapper object), then poll the returned status_url and fetch the result from response_url. The JavaScript SDK (@modelrunner/client) wraps that in a single subscribe() call, which is the one place an { input } object is used.
Can I run Stability AI models from Claude or Cursor?
Yes. Connect the ModelRunner MCP server (https://mcp.modelrunner.run/mcp) once and all 5 Stability AI models become tools your assistant can call with run_model — authorized over OAuth 2.1, so no API key goes into a config file. Results come back as hosted URLs in the conversation.
More on ModelRunner
Browse the full model catalog, compare live per-configuration rates on the pricing page, see curated sets on explore, or view every model creator.