Replicate video models vs Runway API

Replicate video models

One bearer token reaches more than twenty official video models at published per-second prices, each with a typed input schema, and failed runs aren't charged. Tokens have no scopes or spend cap, no SLA is published, and the terms let Replicate withdraw any model without notice.

Runway API

OpenAPI 3.1, llms.txt and Markdown copies of every docs page. Gen-3 Alpha Turbo and Gen-4 Aleph were removed on 2026-07-30 with no prior notice in the changelog.

Replicate video models

1. Call official models at POST /v1/models/{owner}/{name}/predictions with no version, then poll GET /v1/predictions/{id} or pass webhook. Video jobs usually outlast the 60-second Prefer: wait window
2. Download the output file within the hour. API predictions lose inputs, outputs and logs after 60 minutes
3. Read the model's price tiers before setting resolution, mode or generate_audio. Kling 3.0 runs from $0.168 to $0.42 a second and Veo 3.1 doubles with audio
4. Send Cancel-After on every create. There is no idempotency key, so a blind retry is a second paid video
5. Keep credit above $20 or enable auto-reload. Low balances are throttled, and granted credit with no card is held to 6 requests a minute

Runway API

1. Send X-Runway-Version: 2024-11-06 on every request or it fails
2. Use the SDK's wait-for-output helper or poll GET /v1/tasks/{id} until SUCCEEDED or FAILED
3. Don't retry a SAFETY.* failure unchanged. It's moderation, not an outage
4. Take model IDs from the models page, not memory. Two were removed without notice on 2026-07-30
5. Copy outputs to your own storage. URLs expire within 24 to 48 hours