Skip to content
ModelRunner logo

ModelRunner

Claimed

Run image, video, audio, 3D and text models, paying only per use

Paid plans only Visit Website
Tracked since 2026

The Bottom Line

Best for
Developers and product teams adding image, video, audio, 3D or text AI features to their applications.
Price
Paid plans only. Compare plans

Key facts

  • One API key for image, video, audio, 3D and text models.
  • Python and TypeScript SDKs with streaming, webhooks and polling.
  • Hosted MCP server with OAuth sign-in for AI assistants.

Not for

Teams that require offline inference or want to operate the model-serving infrastructure themselves.

What is ModelRunner?

ModelRunner is a pay-per-use API for image, video, audio, 3D and text AI models. Developers can test models in a browser playground, integrate with Python or TypeScript SDKs, and run models from AI assistants through MCP. Generated outputs are hosted and reusable, and custom endpoints let teams package preset prompts and selected inputs. No monthly subscription.

Available on: API

Key Features

  • Unified API for image, video, audio, 3D, and text models
  • Playground for testing models with example prompts
  • MCP server for calling models from AI assistants
  • Asset library for uploads, inputs, and generated outputs
  • Custom model wrappers with selected inputs and prompts

Pricing

Paid

ModelRunner offers paid plans. Visit their website for current pricing details.

View pricing

Reviews

Improve Your Thinking Patterns Using ChatGPT cover
$99 Free with your review

Review ModelRunner, get a free AI guide

Share your experience and we will send you Improve Your Thinking Patterns Using ChatGPT, free.

Write a review

Best ModelRunner Alternatives

Top alternatives based on features, pricing, and user needs.

Most buyers shortlist 2 or 3 tools before committing. Pull a side-by-side comparison or browse the full alternatives shortlist below.

Explore More

ModelRunner FAQ

How does ModelRunner help developers test AI models before integrating them?

ModelRunner provides a browser playground where developers can test image, video, audio, 3D and text models without writing any code. Once satisfied, they can integrate using Python or TypeScript SDKs for production use.

How does ModelRunner compare to Replicate for running AI models?

Like Replicate, ModelRunner offers a pay-per-use API for a variety of AI models. However, ModelRunner emphasizes custom endpoints that let teams package preset prompts and selected inputs, and it supports running models from AI assistants through MCP, which Replicate does not.

What are the main limitations or trade-offs of using ModelRunner?

ModelRunner has no permanently free tier, so every API call incurs a cost. Teams with high volume or unpredictable usage should plan their budgets accordingly since there is no monthly subscription to cap spending.

Which teams benefit most from using ModelRunner?

Teams building AI-powered applications that need to generate or process images, videos, audio, 3D models, or text benefit most from ModelRunner. It is especially suited for developers who want to test models quickly in a playground and then integrate via SDKs or AI assistants.

How is ModelRunner priced?

ModelRunner uses a pay-per-use pricing model where you pay only for each API call you make across image, video, audio, 3D and text models. There is no monthly subscription, so costs scale directly with usage.

Can ModelRunner be used from within an AI assistant workflow?

Yes, ModelRunner supports the Model Context Protocol (MCP), which allows developers to run models directly from AI assistants. This enables seamless integration of AI model generation into assistant-driven workflows.

How do custom endpoints work in ModelRunner?

Custom endpoints in ModelRunner let teams package preset prompts and selected inputs into a reusable endpoint. This simplifies repeated use of the same model configuration without re-entering parameters each time.

Guides & Articles