Claude Imagine

Generate Video

generate_video

Destructive

Generate an AI video with H3 Max Turbo (default: renders in seconds, 5-15 s), Grok Imagine, Seedance, Veo, or Kling. Every account gets its first H3 Max Turbo clip at 5 s / 480p free; after that it costs credits like any other preset. Users can name a model family naturally: H3, Hailuo or MiniMax map to H3 Max Turbo, Veo to Veo 3.1 Fast, Kling to Kling 2.5 Turbo, Grok to Grok Imagine, and Seedance to Seedance 2.0 Mini. Seedance 1.5 Pro was retired by its provider on October 21, 2026; if the user asks for it, say so and suggest Seedance 2.0 Mini rather than switching silently. Never omit model when the user named one. Call list_models or quote_generation first when the user wants to review models and costs before spending credits.

Input Schema

Name	Required	Description
`model`	No	Video model or friendly name. Shortcuts: h3, hailuo or minimax -> h3-max-turbo; grok -> grok-imagine; seedance or seedance-mini -> seedance-2.0-mini; veo -> veo-3.1-fast; kling -> kling-2.5-turbo. Defaults to h3-max-turbo only when the user did not name a model.
`prompt`	Yes	Video description
`duration`	No	Seconds: H3 Max Turbo 5-15, Grok 6-30, Seedance 2.0 Mini 4-15, Veo 3.1 Fast 4/6/8, Kling 5/10. Defaults to the selected model preset.
`image_url`	No	Optional public image URL to animate
`resolution`	No	Quality: H3 Max Turbo supports 480p/768p; Grok supports 480p/720p/1080p; Seedance 2.0 Mini supports 480p/720p; Veo 3.1 Fast currently uses 720p; Kling uses fixed Pro quality.
`max_credits`	No	Budget cap in credits, when the person stated one. If the exact cost of this call is above it, nothing is started and the reply lists what fits.
`aspect_ratio`	No	Video aspect ratio, default 16:9. Veo supports 16:9 or 9:16; Kling and H3 Max Turbo image-to-video follow the source image instead.

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedOct 22, 2026

changedInput schema / properties / duration / description

Previous value: -"Seconds: H3 Max Turbo 5-15, Grok 6-30, Seedance 1.5 Pro 4-12, Seedance 2.0 Mini 4-15, Veo 3.1 Fast 4/6/8, Kling 5/10. Defaults to the selected model preset."New value: +"Seconds: H3 Max Turbo 5-15, Grok 6-30, Seedance 2.0 Mini 4-15, Veo 3.1 Fast 4/6/8, Kling 5/10. Defaults to the selected model preset."

changedInput schema / properties / model / description

Previous value: -"Video model or friendly name. Shortcuts: h3, hailuo or minimax -> h3-max-turbo; grok -> grok-imagine; seedance or seedance-mini -> seedance-2.0-mini; seedance-pro -> seedance-1.5-pro; veo -> veo-3.1-fast; kling -> kling-2.5-turbo. Defaults to h3-max-turbo only when the user did not name a model."New value: +"Video model or friendly name. Shortcuts: h3, hailuo or minimax -> h3-max-turbo; grok -> grok-imagine; seedance or seedance-mini -> seedance-2.0-mini; veo -> veo-3.1-fast; kling -> kling-2.5-turbo. Defaults to h3-max-turbo only when the user did not name a model."

changedInput schema / properties / model / enum

Previous value: -[
-  "h3-max-turbo",
-  "grok-imagine",
-  "seedance-1.5-pro",
-  "seedance-2.0-mini",
-  "veo-3.1-fast",
-  "kling-2.5-turbo",
-  "h3",
-  "hailuo",
-  "minimax",
-  "grok",
-  "seedance",
-  "seedance-mini",
-  "seedance-pro",
-  "veo",
-  "kling"
-]New value: +[
+  "h3-max-turbo",
+  "grok-imagine",
+  "seedance-2.0-mini",
+  "veo-3.1-fast",
+  "kling-2.5-turbo",
+  "h3",
+  "hailuo",
+  "minimax",
+  "grok",
+  "seedance",
+  "seedance-mini",
+  "veo",
+  "kling"
+]

changedInput schema / properties / resolution / description

Previous value: -"Quality: H3 Max Turbo supports 480p/768p; Grok and Seedance 1.5 support 480p/720p/1080p; Seedance 2.0 Mini supports 480p/720p; Veo 3.1 Fast currently uses 720p; Kling uses fixed Pro quality."New value: +"Quality: H3 Max Turbo supports 480p/768p; Grok supports 480p/720p/1080p; Seedance 2.0 Mini supports 480p/720p; Veo 3.1 Fast currently uses 720p; Kling uses fixed Pro quality."

Changed1 schema field changedSep 7, 2026

addedInput schema / properties / max_credits

Added value: +{
+  "description": "Budget cap in credits, when the person stated one. If the exact cost of this call is above it, nothing is started and the reply lists what fits.",
+  "maximum": 9007199254740991,
+  "minimum": 0,
+  "type": "integer"
+}

Changed6 schema fields changedSep 7, 2026

changedInput schema / properties / aspect_ratio / description

Previous value: -"Video aspect ratio, default 16:9. Veo supports 16:9 or 9:16; Kling image-to-video follows the source image instead."New value: +"Video aspect ratio, default 16:9. Veo supports 16:9 or 9:16; Kling and H3 Max Turbo image-to-video follow the source image instead."

changedInput schema / properties / duration / description

Previous value: -"Seconds: Grok 6-30, Seedance 1.5 Pro 4-12, Seedance 2.0 Mini 4-15, Veo 3.1 Fast 4/6/8, Kling 5/10. Defaults to the selected model preset."New value: +"Seconds: H3 Max Turbo 5-15, Grok 6-30, Seedance 1.5 Pro 4-12, Seedance 2.0 Mini 4-15, Veo 3.1 Fast 4/6/8, Kling 5/10. Defaults to the selected model preset."

changedInput schema / properties / model / description

Previous value: -"Video model or friendly name. Shortcuts: grok -> grok-imagine; seedance or seedance-mini -> seedance-2.0-mini; seedance-pro -> seedance-1.5-pro; veo -> veo-3.1-fast; kling -> kling-2.5-turbo. Defaults to grok-imagine only when the user did not name a model."New value: +"Video model or friendly name. Shortcuts: h3, hailuo or minimax -> h3-max-turbo; grok -> grok-imagine; seedance or seedance-mini -> seedance-2.0-mini; seedance-pro -> seedance-1.5-pro; veo -> veo-3.1-fast; kling -> kling-2.5-turbo. Defaults to h3-max-turbo only when the user did not name a model."

changedInput schema / properties / model / enum

Previous value: -[
-  "grok-imagine",
-  "seedance-1.5-pro",
-  "seedance-2.0-mini",
-  "veo-3.1-fast",
-  "kling-2.5-turbo",
-  "grok",
-  "seedance",
-  "seedance-mini",
-  "seedance-pro",
-  "veo",
-  "kling"
-]New value: +[
+  "h3-max-turbo",
+  "grok-imagine",
+  "seedance-1.5-pro",
+  "seedance-2.0-mini",
+  "veo-3.1-fast",
+  "kling-2.5-turbo",
+  "h3",
+  "hailuo",
+  "minimax",
+  "grok",
+  "seedance",
+  "seedance-mini",
+  "seedance-pro",
+  "veo",
+  "kling"
+]

changedInput schema / properties / resolution / description

Previous value: -"Quality: Grok and Seedance 1.5 support 480p/720p/1080p; Seedance 2.0 Mini supports 480p/720p; Veo 3.1 Fast currently uses 720p; Kling uses fixed Pro quality."New value: +"Quality: H3 Max Turbo supports 480p/768p; Grok and Seedance 1.5 support 480p/720p/1080p; Seedance 2.0 Mini supports 480p/720p; Veo 3.1 Fast currently uses 720p; Kling uses fixed Pro quality."

changedInput schema / properties / resolution / enum

Previous value: -[
-  "480p",
-  "720p",
-  "1080p"
-]New value: +[
+  "480p",
+  "720p",
+  "768p",
+  "1080p"
+]

AddedAug 25, 2026

TDQS

A4.3/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true, openWorldHint=true, and non-idempotent, so the safety profile is covered structurally. The description adds non-obvious behavioral context the annotations can't: credit cost per clip, the free first H3 Max Turbo render, and the no-silent-substitution policy. It stops short of describing what a successful call returns (job id vs. finished asset) or that generation is asynchronous.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and default model are front-loaded, followed by model-name mappings and the pre-purchase alternatives. It is a bit long and redundantly repeats the shortcut mapping that the model parameter schema already contains verbatim, which is the main thing that doesn't fully earn its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given seven parameters, no output schema, and existing annotations, the description covers selection, cost, and prerequisite workflow well. The remaining gap is that it never indicates generation is asynchronous or points to check_generation, so an agent must infer how to retrieve the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents every parameter including the friendly-name shortcuts, durations, and resolutions. The description largely restates the model mapping already present in the schema's model field, adding the user-facing naming intent but little new syntax. Baseline 3 applies when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Generate an AI video') and enumerates the concrete model options, which immediately separates it from generate_image and edit_image. An agent knows exactly what this tool produces without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly routes to alternatives: 'Call list_models or quote_generation first when the user wants to review models and costs before spending credits.' It also gives a rule for the retired Seedance 1.5 Pro (say so, suggest Seedance 2.0 Mini rather than switching silently), which is exactly the when/when-not guidance the dimension asks for.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Claude Imagine tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?