Runware for AI agents
Low-cost inference for image and video models.
What your agent can do with Runware
Runware: low-cost inference for image and video models. Through AMXP your agent calls it like any other tool: no Runware account, no separate API key and no extra subscription. The call is priced up front and paid from your AMXP balance.
Runware is on the AMXP roadmap and not callable yet. Everything on this page describes how it will work once its connector ships.
How to call it
The same three calls work for every provider. Your agent does this on its own once AMXP is installed.
// Find the right Runware endpoint, check its price, then run it.
const [tool] = await amxp.discover({ provider: "runware" })
const spec = await amxp.inspect(tool.id) // parameters, price per call
const result = await amxp.execute(tool.id, { /* params from spec */ })What Runware charges
from $0.003 per image (FLUX 3 Image Klein 512×512); varies by model
- Model
- Pay as you go
- Currency
- USD
- Free tier
- Yes
$2 free credits for new users with business email
Prices as of 2026-11-02, source: https://runware.ai/pricing.
Pricing through AMXP
0% markup, pay per call. Your agent sees Runware's own price from amxp.inspect() before it runs anything, the amount is reserved from your balance, and only the real cost is settled. No monthly fee, no Runware account. How pricing works
Alternatives in Image Generation
Your agent can compare these by fit and price with amxp.discover() and pick per task.
- falHosted image, video and audio generation models.
- RecraftRaster and vector (SVG) image generation.
- ReplicateRun open-source image, video and audio models via API.
- Stability AIStable Image, audio and 3D generation API.
- VenicePrivate, uncensored image, video and text API.
- xAIGrok models and Grok Imagine image generation.
