generate_video

Added value: +{
+  "default": true,
+  "description": "Save the completed result locally (default true). Set false for URL-only workflows. Ignored when wait=false. Other providers may return inline image content when local saving is disabled.",
+  "type": "boolean"
+}

Previous value: -"Video duration in seconds. seedance-2-0 / happyhorse-1.0 currently accept ~3–15s (any integer in range). veo-3.1 accepts exactly 4, 6, or 8 (default 4) — other values will be rejected. Defaults to the model's default duration. Call list_models for the current allowed values per model."New value: +"Video duration in seconds. Use list_models for the model's enum/range; when omitted the server uses the omitted-request default shown there."

Previous value: -"First-frame image to control where the video starts. Accepts public URL or local file path (auto-uploaded). REQUIRED for grok-video (image-to-video only — backend rejects it without a firstFrame). For seedance/happyhorse/veo it is optional: with no first frame they do pure text-to-video."New value: +"First-frame image when required or supported by the selected model. Accepts a public URL or local file path (auto-uploaded); use list_models and let the server enforce the live model contract."

Previous value: -"Optional last-frame image to also control where the video ends. Used by seedance-2-0 and veo-3.1; happyhorse-1.0 ignores this field. Accepts public URL or local file path. Requires firstFrame to also be provided — passing lastFrame alone is rejected."New value: +"Optional last-frame image for a model that supports it. Accepts a public URL or local file path; requires firstFrame. Use list_models for the live model contract."

Previous value: -"Video model ID. Use list_models to see available video models. Common (as of writing): \"seedance-2-0\" (multi-tier general purpose), \"happyhorse-1.0\" (cost-effective i2v/t2v), \"veo-3.1\" (Google Veo with two tiers, 4/6/8s, native audio), \"grok-video\" (xAI Grok Imagine 1.5 — IMAGE-TO-VIDEO ONLY: firstFrame REQUIRED, pure text-to-video is rejected; native audio; 4-15s; 480p/720p)."New value: +"Video model ID. REQUIRED; call list_models for the live lineup and capabilities."

Added value: +{
+  "description": "Alias of model. Provide at least one; both must match when supplied.",
+  "minLength": 1,
+  "type": "string"
+}

Added value: +{
+  "description": "Reference audio clips for a model whose list_models entry shows a \"Reference audio\" line. Each entry is either an https://images.meigen.ai/... URL or a local .wav/.mp3 path, which is uploaded for you (local paths require MEIGEN_API_TOKEN). Other hosts are rejected: pass the local file and the server uploads it. Per-model limits (clip count, per-clip seconds, total seconds, accepted formats and per-file size) come from list_models. On a model whose line says it requires a visual reference (Seedance 2.0), the request must also carry at least one reference image or reference video — audio alone is rejected. Refer to a clip in the prompt as \"Audio 1\", \"Audio 2\" … numbered in the order given here. Reference audio seconds are never billed.",
+  "items": {
+    "type": "string"
+  },
+  "maxItems": 10,
+  "type": "array"
+}

Previous value: -"Optional reference video URL for Seedance 2.0 \"video continuation\". Must be a publicly accessible HTTPS URL (typically a previous generation result `videoUrl`); local paths are not supported. Only seedance-2-0 accepts this — passing it with other models will fail. IMPORTANT — prompt requirement: to make the new clip semantically continue the reference, the `prompt` MUST explicitly say \"extend\" / \"continue\" (e.g. prefix with \"Extend this video with the following plot:\"). Without that, the model treats the video as visual reference only and the new clip may drift from a true continuation. Output behavior: the output is ONLY your `duration` seconds (4-15s) of new content — the reference video is NOT concatenated into the output. To get a single \"original + new\" clip the user must stitch them locally. Billing: credits are charged at the With-reference-video rate, with `billable_seconds = max(reference_duration + duration, min_billable[duration])`. Total cost is often higher than direct generation of the same output length. Always pass `referenceVideoDuration` alongside this field — omitting it causes underbilling and broken continuation behavior."New value: +"Deprecated single-clip alias of referenceVideos. Still accepted forever; when referenceVideos is also supplied it must equal its first entry. Prefer referenceVideos."

Previous value: -"Duration of the reference video in seconds (typically 2–15 — backend validates the current allowed range). REQUIRED whenever `referenceVideo` is set; if omitted the backend treats it as 0, leading to undercharged credits and misconfigured generation. Pass the actual duration of the clip at `referenceVideo`."New value: +"Deprecated compatibility hint. Ignored because the server probes the authoritative duration of every clip."

Added value: +{
+  "description": "Reference video clips for a model that advertises reference-video support in list_models. Each entry is either an https://images.meigen.ai/... URL — typically a clip MeiGen generated earlier, passed through unchanged — or a local .mp4/.mov path, which is uploaded for you (local paths require MEIGEN_API_TOKEN). Other hosts are rejected: the server only probes clips it can fetch from that CDN, so pass the local file instead. Per-model limits — maximum number of clips, per-clip seconds and the maximum SUM of clip seconds — come from list_models; the server enforces them and rejects an over-limit request before charging. IMPORTANT — prompt requirement: to make the new clip semantically continue a reference, the `prompt` MUST explicitly say \"extend\" / \"continue\" (e.g. \"Extend this video with the following plot:\"). Without that, the model treats the clips as visual reference only. Refer to a specific clip in the prompt as \"Video 1\", \"Video 2\" … numbered in the order given here. Output behavior: the output is only the configured `duration` of new content — reference clips are never concatenated into it. Billing counts the SUM of the server-probed input video seconds plus the output; do not estimate it from client-side metadata.",
+  "items": {
+    "type": "string"
+  },
+  "maxItems": 10,
+  "type": "array"
+}

Added value: +{
+  "description": "Persistent UUID for this workflow step. Required when wait=false. Reuse with identical inputs after interruption, including after MCP restart; use a new UUID for a new generation. Omit only for a new interactive generation.",
+  "format": "uuid",
+  "type": "string"
+}

Previous value: -"Output resolution. Common: \"480p\" / \"720p\" / \"1080p\" / \"4k\" (model-dependent; e.g. Seedance Pro adds 1080p and 4k, while Fast/Mini are 480p/720p only). Use list_models to see what each model supports. Higher resolutions cost more credits per second."New value: +"Output resolution. Use list_models for the selected model/tier's live values."

Previous value: -"Quality tier — only for models that support tiers. seedance-2-0 accepts \"mini\" (default, cheapest; 480p/720p, no reference video), \"fast\" (480p/720p), or \"pro\" (highest fidelity; native 1080p and 4K); veo-3.1 accepts \"fast\" (default) or \"pro\". Tiers may be added by the platform — call list_models to see what each model exposes."New value: +"Optional model tier. Use list_models for the selected model's live tier values."

Added value: +{
+  "default": true,
+  "description": "MeiGen only: false returns the accepted generation ID immediately; poll check_generation separately. Default true waits for completion. Submit-only requires requestId.",
+  "type": "boolean"
+}

Previous value: -[
-  "prompt",
-  "model"
-]New value: +[
+  "prompt"
+]

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "creditsStatus": {
+      "type": "string"
+    },
+    "creditsUsed": {
+      "type": "number"
+    },
+    "deduped": {
+      "type": "boolean"
+    },
+    "downloadWarning": {
+      "type": "string"
+    },
+    "error": {
+      "additionalProperties": false,
+      "properties": {
+        "available": {
+          "type": "number"
+        },
+        "code": {
+          "type": "string"
+        },
+        "httpStatus": {
+          "type": "number"
+        },
+        "message": {
+          "type": "string"
+        },
+        "required": {
+          "type": "number"
+        },
+        "retryAfterSeconds": {
+          "type": "number"
+        },
+        "retryable": {
+          "type": "boolean"
+        }
+      },
+      "required": [
+        "code",
+        "message",
+        "retryable"
+      ],
+      "type": "object"
+    },
+    "generationId": {
+      "type": "string"
+    },
+    "imageUrl": {
+      "type": "string"
+    },
+    "mediaType": {
+      "enum": [
+        "image",
+        "video"
+      ],
+      "type": "string"
+    },
+    "modelId": {
+      "type": "string"
+    },
+    "nextAction": {
+      "additionalProperties": false,
+      "properties": {
+        "afterSeconds": {
+          "type": "number"
+        },
+        "arguments": {
+          "additionalProperties": {},
+          "type": "object"
+        },
+        "message": {
+          "type": "string"
+        },
+        "tool": {
+          "type": "string"
+        },
+        "type": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "type"
+      ],
+      "type": "object"
+    },
+    "observationEnded": {
+      "type": "boolean"
+    },
+    "pollAfterSeconds": {
+      "type": "number"
+    },
+    "provider": {
+      "enum": [
+        "meigen",
+        "openai",
+        "comfyui"
+      ],
+      "type": "string"
+    },
+    "receiptWarning": {
+      "type": "string"
+    },
+    "requestId": {
+      "type": "string"
+    },
+    "requestedMediaType": {
+      "enum": [
+        "image",
+        "video"
+      ],
+      "type": "string"
+    },
+    "savedPath": {
+      "type": "string"
+    },
+    "status": {
+      "enum": [
+        "processing",
+        "completed",
+        "failed",
+        "error",
+        "unknown"
+      ],
+      "type": "string"
+    },
+    "success": {
+      "type": "boolean"
+    },
+    "urls": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "videoUrl": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "success",
+    "status",
+    "urls"
+  ],
+  "type": "object"
+}

Previous value: -"Optional first-frame image to control where the video starts. Accepts public URL or local file path (auto-uploaded). Highly recommended for image-to-video; with no first frame the model does pure text-to-video."New value: +"First-frame image to control where the video starts. Accepts public URL or local file path (auto-uploaded). REQUIRED for grok-video (image-to-video only — backend rejects it without a firstFrame). For seedance/happyhorse/veo it is optional: with no first frame they do pure text-to-video."

Previous value: -"Video model ID. Use list_models to see available video models. Common (as of writing): \"seedance-2-0\" (multi-tier general purpose), \"happyhorse-1.0\" (cost-effective i2v/t2v), \"veo-3.1\" (Google Veo with two tiers, 4/6/8s, native audio)."New value: +"Video model ID. Use list_models to see available video models. Common (as of writing): \"seedance-2-0\" (multi-tier general purpose), \"happyhorse-1.0\" (cost-effective i2v/t2v), \"veo-3.1\" (Google Veo with two tiers, 4/6/8s, native audio), \"grok-video\" (xAI Grok Imagine 1.5 — IMAGE-TO-VIDEO ONLY: firstFrame REQUIRED, pure text-to-video is rejected; native audio; 4-15s; 480p/720p)."

Previous value: -"Output resolution. Common: \"480p\" / \"720p\" / \"1080p\" (model-dependent). Use list_models to see what each model supports. Higher resolutions cost more credits per second."New value: +"Output resolution. Common: \"480p\" / \"720p\" / \"1080p\" / \"4k\" (model-dependent; e.g. Seedance Pro adds 1080p and 4k, while Fast/Mini are 480p/720p only). Use list_models to see what each model supports. Higher resolutions cost more credits per second."

Previous value: -"Quality tier — only for models that support tiers. seedance-2-0 and veo-3.1 currently accept \"fast\" (default, cheaper) or \"pro\" (higher fidelity). Tiers may be added by the platform — call list_models to see what each model exposes."New value: +"Quality tier — only for models that support tiers. seedance-2-0 accepts \"mini\" (default, cheapest; 480p/720p, no reference video), \"fast\" (480p/720p), or \"pro\" (highest fidelity; native 1080p and 4K); veo-3.1 accepts \"fast\" (default) or \"pro\". Tiers may be added by the platform — call list_models to see what each model exposes."