OctopusX

Google

Latency—

Throughput—

Upload rate—

Context length1024 tokens

Max output—

Input price$0.4per second

Output price—per second

Cache read—per second

Cache write—per second

Performance

Avg TPS—

Avg latency—

Avg success rate—

TPS—

TTFT—

Latency—

Success rate—

Success rate

Speed

Code Example

curl ${API_BASE_URL}/v1beta/models/veo-3-1:predictLongRunning \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "veo-3-1",
    "messages": [
      {
        "role": "user",
        "content": "Hello"
      }
    ]
  }'

Replace <YOUR_API_KEY> with the API key generated on your token management page.

Authentication

All requests must include the Authorization: Bearer <TOKEN> header.

Endpoint Path

POST

google-native

Supported Parameters

ParameterTypeDefaultDescription

string720pControls the output video resolution. Supported values: 720p, 1080p, and 4k.

integer8Controls the generated video duration. Supported values: 4, 6, and 8 seconds. 1080p, 4K, reference-image, and video-extension workflows require an 8-second duration.

string16:9Controls the output video aspect ratio. Supported values: 16:9 and 9:16.

string-Describes visual elements or characteristics that should be avoided in the generated video.

integer-Optional random seed that may improve generation consistency but does not guarantee deterministic output.

array-Provides up to three reference images to guide subject, character, product, style, or visual consistency.

Rate Limits

GroupRPMTPMRPD

RPM = requests per minute, TPM = tokens per minute, RPD = requests per day. Limits apply by token group.

Pricing

ProviderBilling typePrice summary

G

Gemini

Per second