veo3.1-fast - ByteSpike

veo3.1-fast is the Fast tier of veo3.1. Trade-offs: drops the native audio option, slightly looser fidelity on hard motion, and meaningfully lower per-second cost. The right default for programmatic / volume video work where top-tier fidelity isn’t the bar. Pricing:

0.20 / second of generated footage — see the [rate card](/pricing). Failures don't bill. For the very cheapest Veo tier, `veo3.1-lite` runs at

0.05 / second.

Protocols

Protocol	Path	Purpose
OpenAI Video — submit	`POST https://llm.bytespike.ai/v1/videos/generations`	enqueues; returns `task_id`
OpenAI Video — poll	`GET https://llm.bytespike.ai/v1/videos/tasks/{task_id}`	returns `status` and `result_url`

Quickstart

TASK_ID=$(curl -s https://llm.bytespike.ai/v1/videos/generations \
  -H "Authorization: Bearer $BYTESPIKE_API_KEY" \
  -H "content-type: application/json" \
  -d '{
    "model": "veo3.1-fast",
    "prompt": "A coffee cup steaming on a kitchen counter, morning light",
    "duration_seconds": 5,
    "size": "1280x720"
  }' | jq -r .task_id)

# Poll GET /v1/videos/tasks/{task_id} until status is "succeeded"

Capabilities

Capability	Supported
Text-to-video	✅
Image-to-video (with `source_image`)	✅
Audio generation	— (use `veo3.1` for audio)
`duration_seconds` 5 / 10	✅
`size` 1280×720	✅
Modality	video
Capability bucket	`video_generate`

When to use

Volume / programmatic video — short social-card clips, A/B variants, demo placeholders.
No audio needed — explainer-style clips that will be dubbed or scored separately.
Internal-facing creative — quick visualizations for design review.

When not to use:

Audio matters in the deliverable — go to veo3.1.

Next

veo3.1 — full tier with audio
Multimodal endpoints — overview