Providers & pricing
| Provider | Input | Output | Free tier |
|---|---|---|---|
 Vertex Default | — RODI/M | — RODI/M | — |
Pricing
| Rate | RODI | USD (ref.) | Unit |
|---|---|---|---|
| Per second | 75.4 | ~ 0.100 | USD/s · RODI/s |
| With audio / s | 75.4 | ~ 0.100 | USD/s · RODI/s |
| No audio / s | 60.3 | ~ 0.0800 | USD/s · RODI/s |
| 1080p with audio | 90.5 | ~ 0.120 | USD/s · RODI/s |
| 1080p no audio | 75.4 | ~ 0.100 | USD/s · RODI/s |
| 4K with audio | 226.1 | ~ 0.300 | USD/s · RODI/s |
| 4K no audio | 188.4 | ~ 0.250 | USD/s · RODI/s |
RODI prices include RodiumAi markup and upstream fees. USD figures are wholesale reference rates.
Capabilities
Streaming
Tool calling
Vision
JSON mode
Reasoning
About this model
Google Veo 3.1 Fast — lower-latency text/image-to-video with synchronized audio. GA on Vertex AI (us-central1). Optimized for faster iteration at 720p, 1080p, or 4K.
API usage
Generate video with client.videos() — POST /v1/videos/generations (long timeout).
RodiumAi SDK
videos() maps to POST /v1/videos/generations — allow up to 600s timeout.
…Compatible SDKs (OpenAI / Anthropic packages)
…