veo-3.1

High-quality video generation model, supports text-to-video and single-image-driven video. Suitable for ad shorts and cinematic sequences (slower speed, higher quality).

Overview

Field	Value
Model ID	`veo-3-1`
CLI	`dlazy veo-3.1`
MCP	`veo-3.1` (Claude Code surfaces this as `mcp__dlazy__veo-3.1`)
Type	`video`
Execution	Async task; the CLI polls until completion (`--no-wait` returns `generateId` immediately)
Batch	Supports `--batch <n>` parallel fan-out

Parameters

Arg	Type	Required	Notes
`prompt`	string	Yes	Prompt
`generation_mode`	"frames" \| "components" \| "extend"	No	Generation Mode（frames=Frames; components=Components; extend=Extend Video）; default `"frames"`
`firstFrame`	url	No	First Frame; image (accepts URL, local path, or data: URL); only when generation_mode="frames"
`lastFrame`	url	No	Last Frame; image (accepts URL, local path, or data: URL); only when generation_mode="frames"
`images`	array<url>	No	Images; image (accepts URL, local path, or data: URL); max 3 items; only when generation_mode="components"
`video`	url	No	Video (URL); video (accepts URL, local path, or data: URL); only when generation_mode="extend"
`size`	"16:9" \| "9:16"	No	Size; default `"16:9"`; only when generation_mode!="extend"
`resolution`	"720P" \| "1080P" \| "4K"	No	Resolution; default `"720P"`; only when generation_mode!="extend"
`duration`	"4" \| "6" \| "8" \| "7"	No	Duration (s) (4/6/8 in frames mode; fixed 8 in components mode; fixed 7 in extend mode) Options depend on "generation_mode". when generation_mode="": 4 (4s), 6 (6s), 8 (8s); when generation_mode="generation_mode=components": 8 (8s); when generation_mode="generation_mode=extend": 7 (+7s); default `"8"`

--input @file.json or --input '{...}' can supply all args at once; flags take precedence over --input keys.

CLI Examples

dlazy veo-3.1 --help
dlazy veo-3.1 --prompt "Write your prompt here" --firstFrame "https://example.com/reference.jpg" --lastFrame "https://example.com/reference.jpg"
dlazy veo-3.1 --prompt "Write your prompt here" --firstFrame "./local-image.png" --lastFrame "https://example.com/reference.jpg"
dlazy veo-3.1 --prompt "Write your prompt here" --firstFrame "https://example.com/reference.jpg" --lastFrame "https://example.com/reference.jpg" --dry-run
dlazy veo-3.1 --prompt "Write your prompt here" --firstFrame "https://example.com/reference.jpg" --lastFrame "https://example.com/reference.jpg" --no-wait
dlazy veo-3.1 --prompt "Write your prompt here" --firstFrame "https://example.com/reference.jpg" --lastFrame "https://example.com/reference.jpg" --batch 4

Compose with a pipeline

dlazy gpt-image-2 --prompt "reference visual" \
  | dlazy veo-3.1 --firstFrame - --prompt "Write your prompt here"

MCP is consumed by AI clients, not handwritten. Once dLazy is registered as an MCP server the tool appears in the client's tool list — Claude Code surfaces it as mcp__dlazy__veo-3.1; generic clients (e.g. OpenClaw) call it as veo-3.1.

See MCP setup for how to add the server.

Output

{
  "outputs": [
    { "type": "video", "id": "o_...", "url": "https://files.dlazy.com/result.mp4", "mimeType": "video/mp4" }
  ]
}

Media tools emit image / video / audio / file outputs. Use --output url to print only the URLs on stdout.