varg API
API by varg.ai · rest
Unified REST API for AI media generation at api.varg.ai/v2. One API key, ~80 models across 8 providers, async jobs, stable output URLs on s3.varg.ai, files with lineage, and transparent billing: 1 credit = 1 cent = $0.01, and models are priced pass-through — you pay what the provider charges, no markup. Every amount comes as integer credits (*_cents / credits fields) and as dollars (*_usd fields). The async job pattern: every generation request returns 202 Accepted with a job object (status: queued). Poll GET /jobs/{id} until the job reaches a terminal status (completed, failed, or cancelled), then read output.outputs[0].url. Alternatively, set options.webhook_url in the request to receive an HMAC-signed callback when the job finishes. Rate limits (sliding one-minute windows; a 429 carries Retry-After and X-RateLimit-*): - every request with an API key or session: 1,200 a minute per credential; - every request without one: 120 a minute per…
Endpoint: https://api.varg.ai/v2
Verification: observed. Source: crawl.
Capabilities (115)
- List charges or runs
- Spend breakdown
- Files generated over time
- Analytics definitions
- Spend summary
- Spend over time
- List API keys
- Create an API key
- Rename an API key
- Revoke an API key
- Reveal an API key
- List who an API key is shared with
- Share an API key
- Remove someone from an API key
- Get balance
- Get transaction ledger
- Get usage records
- Get lifetime credits and usage (USD)
- Estimate a price without creating a job
- Send product-analytics events
- Every analytics event varg records
- Platform analytics reports
- Send feedback about varg
- Run an ffmpeg operation
- List files