Replicate API exposes Veo 3.1 through model ID google/veo-3.1. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.
Last refreshed 2026-10-23. Next refresh: weekly.
Quick Start
- 1
- 2Use the Replicate API SDK or REST API to call
google/veo-3.1— see the documentation for request format. - 3
Code Examples
pip install replicateREPLICATE_API_TOKENgoogle/veo-3.1Replicate uses "owner/model-name" format (e.g. "meta/meta-llama-3-8b-instruct") for the latest version, or "owner/model-name:version-sha" to pin to a specific version. The REST endpoint splits owner and model-name into the path: /v1/models/{owner}/{model-name}/predictions.
import replicate
# reads REPLICATE_API_TOKEN from env
# google/veo-3.1 format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
"google/veo-3.1",
input={"prompt": "Hello"}
)
# Output is a list or generator depending on the model
print("".join(output))Pricing on Replicate API
| Type | Rate |
|---|---|
| Video output | $0.40/sec |
Capabilities
About Veo 3.1
Veo 3.1 (veo-3.1-generate-001) is the generally available version of Google DeepMind's Veo 3.1 video generation model, released 2025-11-17 on Google Cloud's Vertex AI (now Gemini Enterprise Agent Platform). It generates 4, 6 or 8-second videos at 720p, 1080p or 4K (24 fps, 16:9 or 9:16) with native audio from text or image prompts, and supports first/last-frame generation, reference images and video extension. It replaces the veo-3.1-generate-preview model.