Skip to main content

​
Studio pricing tiers

Current pricing is confirmed at https://livepeer.studio/pricing. The table above reflects pricing as of April 2026.

​
AI inference pricing

AI inference cost is orchestrator-set, not fixed by Studio. Orchestrators set their own prices per pipeline. The Studio-managed gateway routes to the cheapest available orchestrator by default. The indicative rate for text-to-image inference is approximately $0.019 per megapixel of output (illustrative — actual rates vary by orchestrator and network conditions). Cost estimation example (text-to-image at 1024x1024):
  • Output area: 1,024 x 1,024 = 1,048,576 pixels = ~1.05 megapixels
  • At 0.019/MP:approximately0.019/MP: approximately 0.020 per image
  • At 1,000 images/day: approximately $20/day
Check your actual costs in the Studio billing dashboard after the first week of production traffic. AI inference costs appear as a line item separate from transcoding costs.

​
Rate limits

Rate limits are per API key and enforced by the Studio gateway. Limits are visible in the Studio dashboard under Settings > API Keys > [key name] > Rate Limits. Default limits by tier:
  • Free: Lower request/minute limits; not suitable for sustained load
  • Growth: Standard production limits; sufficient for most applications
  • Enterprise: Custom limits by agreement
When a rate limit is exceeded, the API returns 429 Too Many Requests. Implement exponential backoff in your retry logic to handle 429 responses gracefully. Rate limit headers are included in every response: 
X-RateLimit-Limit: 100
X-RateLimit-Remaining: 42
X-RateLimit-Reset: 1712345678

​
Streaming credits

Studio offers streaming credits for qualifying projects (open-source, non-profit, hackathon participants). Apply via the Studio dashboard or by contacting support@livepeer.org. Credit allocation is at Livepeer’s discretion and subject to review.

AI Production Checklist

Cost estimation, monitoring, and launch readiness for AI applications.

APIs

Full endpoint reference and OpenAPI spec.
Last modified on April 7, 2026