Google: google/veo-3.1-generate-preview
veo-3.1-generate-preview
google/veo-3.1-generate-previewCapabilities
1
Context length
—
Tokens
Max output tokens
—
Tokens
Type
Video
Google
Playground
Output
Ready to generate
Configure the options and submit a prompt. Task status and generated videos will appear here.
Pricing
Pricing breakdown
Usage-based pricing, broken down by billing item at your current rates.
Video duration (s)
3 price tiers
Output resolution: 720p
1 credits
Output resolution: 1080p
3 credits
All other cases
1 credits
Billing items are additive. Only one matching price tier applies to each item. Charges are calculated from actual usage per request, with each item rounded up.
API
cURL example
request.sh
POST
/v1beta/models/google/veo-3.1-generate-preview:predictLongRunningAsynchronousGemini
CREATE_RESPONSE=$(curl "http://127.0.0.1:11113/v1beta/models/google/veo-3.1-generate-preview:predictLongRunning" \ -X POST \ -H "Authorization: Bearer $API_KEY" \ -H "Content-Type: application/json" \ -d '{ "instances": [ { "prompt": "Explain model gateways in one sentence." } ], "parameters": { "durationSeconds": 8, "resolution": "720p", "aspectRatio": "16:9" }}')# Requires jq.TASK_ID=$(printf '%s' "$CREATE_RESPONSE" | jq -r '.name')for attempt in $(seq 1 120); do RESPONSE=$(curl -sS "http://127.0.0.1:11113/v1/tasks/"$TASK_ID -H "Authorization: Bearer $API_KEY") DONE=$(printf '%s' "$RESPONSE" | jq -r '.done') if [ "$DONE" = "true" ]; then printf '%s' "$RESPONSE"; break; fi sleep 10doneThis request creates a task
The example creates a task, polls the platform task endpoint every 10 seconds, and prints the terminal JSON response. It stops after 120 attempts.
Set your API_KEY environment variable before running. Keep your key server-side.
Uptime
Coming soonUptime workspace
This release includes the core layout and display area. The full feature will be added later.