@evolinkai/cli 0.13.0 → 0.14.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +20 -6
- package/package.json +1 -1
- package/skills/evolink-cli/SKILL.md +21 -7
- package/skills/evolink-cli/references/capabilities.md +1 -1
- package/skills/evolink-cli/references/media-workflows.md +1 -1
- package/skills/evolink-cli/references/usage-and-budget.md +5 -3
- package/src/cli.mjs +76 -21
- package/src/help.mjs +12 -5
- package/src/media.mjs +142 -37
- package/src/platform/core/src/data/model-constraints.js +8 -5
- package/src/platform/core/src/data/model-params.overrides.generated.js +1 -1
- package/src/platform/core/src/services/api-client.js +1 -1
- package/src/platform/core/src/services/batch-generation.js +117 -0
- package/src/platform/core/src/services/gpt-image-tokens.js +264 -0
- package/src/platform/core/src/services/omni-tokens.js +245 -0
- package/src/platform/core/src/services/param-validator.js +48 -1
- package/src/platform/core/src/services/pricing-call-limit.js +4 -4
- package/src/platform/core/src/services/pricing-derived.js +3 -3
- package/src/platform/core/src/services/pricing-rules-client.js +23 -5
- package/src/platform/core/src/services/pricing-rules-estimate.js +266 -67
- package/src/platform/core/src/tool-guidance.js +25 -2
- package/src/platform/core/src/tools/estimate-cost.js +201 -60
- package/src/platform/core/src/tools/generate.js +497 -75
- package/src/platform/core/src/tools/get-model.js +15 -3
- package/src/platform/core/src/tools/get-pricing-rules.js +4 -3
- package/src/platform/core/src/tools/shared.js +1 -1
- package/src/platform/core/src/version.js +1 -1
- package/src/platform/source.json +41 -35
|
@@ -1,4 +1,4 @@
|
|
|
1
1
|
// Copyright 2024 EvoLink AI. SPDX-License-Identifier: Apache-2.0
|
|
2
2
|
// Generated from Evolink-AI/evolink-mcp; adapted for direct REST operations. See platform/LICENSE and platform/NOTICE.
|
|
3
3
|
// Generated by scripts/build-model-params.mjs from the docs site OpenAPI files. Do not edit by hand.
|
|
4
|
-
export const MODEL_PARAMS_OVERRIDES_JSON = "{\"meta\":{\"source\":\"mintlify-docs en/api-manual\",\"commit\":\"06edf6dd\",\"files\":211,\"endpoints\":158,\"models\":8},\"models\":{\"gemini-nano-banana-2.1\":{\"model\":\"gemini-nano-banana-2.1\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"Nano Banana 2.1 API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/nanobanana/nanobanana-2.1/nanobanana-2.1-image-generate\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the image to generate or how to edit an input image, up to 4000 tokens\",\"required\":true},\"size\":{\"type\":\"string\",\"description\":\"Aspect ratio of the generated image, default is auto\",\"enum\":[\"auto\",\"1:1\",\"1:4\",\"4:1\",\"1:8\",\"8:1\",\"2:3\",\"3:2\",\"3:4\",\"4:3\",\"4:5\",\"5:4\",\"9:16\",\"16:9\",\"21:9\"],\"default\":\"auto\"},\"quality\":{\"type\":\"string\",\"description\":\"Output image resolution, default is 2K Note: Prices vary by resolution. Output images are billed at the selected resolution. Setting this parameter explicitly is recommended\",\"enum\":[\"1K\",\"2K\",\"4K\"],\"default\":\"2K\"},\"image_urls\":{\"type\":\"array\",\"description\":\"List of reference image URLs for image to image generation, image editing, and multi-image composition Note: Up to 14 input images per request; Image size: no more than 20MB; Supported file formats: .jpeg, .jpg, .png, .webp; Image URLs must be directly accessible by the server or trigger a direct image download when accessed (such URLs typically end in an image extension such as .png or .jpg); Input images are billed per image\",\"maxItems\":14,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"model_params\":{\"type\":\"object\",\"description\":\"Model extension parameters\",\"properties\":{\"web_search\":{\"type\":\"boolean\",\"description\":\"Whether to enable web search, default is false. When enabled, the model searches for the latest information on the web before generating the image Note: Billed by the actual number of searches performed by the model. A single request may involve multiple searches\",\"default\":false},\"image_search\":{\"type\":\"boolean\",\"description\":\"Whether to enable image search, default is false. When enabled, the model retrieves images from the web as visual references before generating the image Note: Billed by the actual number of searches performed by the model. A single request may involve multiple searches\",\"default\":false},\"thinking_level\":{\"type\":\"string\",\"description\":\"Reasoning level controlling how deeply the model reasons before generating an image, default is auto; auto: leave unspecified and let the model decide; min: minimal reasoning, fastest generation; medium: balanced reasoning; high: deep reasoning Note: Reasoning tokens are billed as text output\",\"enum\":[\"auto\",\"min\",\"medium\",\"high\"],\"default\":\"auto\"}}}},\"inputSchema\":{\"schema\":{\"type\":\"object\",\"required\":[\"prompt\"],\"properties\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the image to generate or how to edit an input image, up to `4000` tokens\",\"example\":\"A cat playing in the grass\"},\"size\":{\"type\":\"string\",\"description\":\"Aspect ratio of the generated image, default is `auto`\",\"enum\":[\"auto\",\"1:1\",\"1:4\",\"4:1\",\"1:8\",\"8:1\",\"2:3\",\"3:2\",\"3:4\",\"4:3\",\"4:5\",\"5:4\",\"9:16\",\"16:9\",\"21:9\"],\"default\":\"auto\"},\"quality\":{\"type\":\"string\",\"description\":\"Output image resolution, default is `2K`\\n\\n**Note:**\\n- Prices vary by resolution. Output images are billed at the selected resolution. Setting this parameter explicitly is recommended\",\"enum\":[\"1K\",\"2K\",\"4K\"],\"default\":\"2K\"},\"image_urls\":{\"type\":\"array\",\"description\":\"List of reference image URLs for image to image generation, image editing, and multi-image composition\\n\\n**Note:**\\n- Up to `14` input images per request\\n- Image size: no more than `20MB`\\n- Supported file formats: `.jpeg`, `.jpg`, `.png`, `.webp`\\n- Image URLs must be directly accessible by the server or trigger a direct image download when accessed (such URLs typically end in an image extension such as `.png` or `.jpg`)\\n- Input images are billed per image\",\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"maxItems\":14,\"example\":[\"https://example.com/image1.png\",\"https://example.com/image2.png\"]},\"model_params\":{\"type\":\"object\",\"description\":\"Model extension parameters\",\"properties\":{\"web_search\":{\"type\":\"boolean\",\"description\":\"Whether to enable web search, default is `false`. When enabled, the model searches for the latest information on the web before generating the image\\n\\n**Note:**\\n- Billed by the actual number of searches performed by the model. A single request may involve multiple searches\",\"default\":false,\"example\":true},\"image_search\":{\"type\":\"boolean\",\"description\":\"Whether to enable image search, default is `false`. When enabled, the model retrieves images from the web as visual references before generating the image\\n\\n**Note:**\\n- Billed by the actual number of searches performed by the model. A single request may involve multiple searches\",\"default\":false,\"example\":true},\"thinking_level\":{\"type\":\"string\",\"description\":\"Reasoning level controlling how deeply the model reasons before generating an image, default is `auto`\\n\\n- `auto`: leave unspecified and let the model decide\\n- `min`: minimal reasoning, fastest generation\\n- `medium`: balanced reasoning\\n- `high`: deep reasoning\\n\\n**Note:**\\n- Reasoning tokens are billed as text output\",\"enum\":[\"auto\",\"min\",\"medium\",\"high\"],\"default\":\"auto\",\"example\":\"medium\"}}}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"responseSchema\":{\"schema\":{\"$ref\":\"#/$defs/ImageGenerationResponse\",\"$defs\":{\"ImageGenerationResponse\":{\"type\":\"object\",\"properties\":{\"created\":{\"type\":\"integer\",\"description\":\"Task creation timestamp\",\"example\":1757165031},\"id\":{\"type\":\"string\",\"description\":\"Task ID\",\"example\":\"task-unified-1757165031-uyujaw3d\"},\"model\":{\"type\":\"string\",\"description\":\"Actual model name used\",\"example\":\"gemini-nano-banana-2.1\"},\"object\":{\"type\":\"string\",\"enum\":[\"image.generation.task\"],\"description\":\"Specific task type\"},\"progress\":{\"type\":\"integer\",\"description\":\"Task progress percentage (0-100)\",\"minimum\":0,\"maximum\":100,\"example\":0},\"status\":{\"type\":\"string\",\"description\":\"Task status\",\"enum\":[\"pending\",\"processing\",\"completed\",\"failed\"],\"example\":\"pending\"},\"task_info\":{\"$ref\":\"#/$defs/TaskInfo\",\"description\":\"Asynchronous task information\"},\"type\":{\"type\":\"string\",\"enum\":[\"text\",\"image\",\"audio\",\"video\"],\"description\":\"Task output type\",\"example\":\"image\"},\"usage\":{\"$ref\":\"#/$defs/Usage\",\"description\":\"Usage and billing information\"}}},\"TaskInfo\":{\"type\":\"object\",\"properties\":{\"estimated_time\":{\"type\":\"integer\",\"description\":\"Estimated completion time (seconds)\",\"minimum\":0,\"example\":45}}},\"Usage\":{\"type\":\"object\",\"description\":\"Usage and billing information\",\"properties\":{\"billing_rule\":{\"type\":\"string\",\"description\":\"Billing rule\",\"enum\":[\"per_call\",\"per_image\",\"per_token\",\"per_second\"],\"example\":\"per_image\"},\"credits_reserved\":{\"type\":\"number\",\"description\":\"Estimated credits consumed\",\"minimum\":0,\"example\":3.0845},\"user_group\":{\"type\":\"string\",\"description\":\"Billing group the user belongs to\",\"example\":\"default\"}}}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"example\":{\"prompt\":\"A cat playing on the grass\",\"size\":\"16:9\",\"quality\":\"2K\"}},\"grok-imagine-video-1.5-lite\":{\"model\":\"grok-imagine-video-1.5-lite\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"grok-imagine-video-1.5-lite Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/grok/grok-imagine-video-1.5-lite\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Video description prompt (required, cannot be empty) EvoLink platform length limit: Up to 2000 tokens (counted with the cl100k tokenizer, so CJK prompts hit the cap at far fewer characters than Latin ones). The platform also enforces a limit of 60000 UTF-8 bytes.\",\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Input image URL (optional). One image switches the request to image-to-video. Mode selection: 0 images (omit the field): text-to-video, no image charge; 1 image: image-to-video, used as the first frame; input images are billed separately (see the [pricing section](https://evolink.ai/grok-imagine-video-1-5-lite#pricing)); 2 or more images are rejected — reference-to-video is not supported on Lite Requirements: Playground local uploads: up to 10MiB (10485760 bytes) per image. Image URLs sent directly to the API are validated upstream and do not use this local upload check.; Supported formats: J…\",\"minItems\":0,\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds), any integer between 1 and 15 seconds\",\"default\":6,\"minimum\":1,\"maximum\":15},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution, default is 480p Description: 480p: Standard definition (default); 720p: High definition; 1080p: Upscaled from 720p, billed at a higher per-second rate See the [pricing section](https://evolink.ai/grok-imagine-video-1-5-lite#pricing) for the per-resolution rates.\",\"enum\":[\"480p\",\"720p\",\"1080p\"],\"default\":\"480p\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Output aspect ratio, default is auto Applies to: text-to-video (0 images). With an input image the output follows that image's dimensions and this parameter is ignored. Description: auto: No ratio is sent upstream and the upstream channel decides the framing (text-to-video currently renders 16:9); this is the default value; 16:9: Landscape; 9:16: Portrait; 1:1: Square; 4:3: Landscape, classic TV ratio; 3:4: Portrait, classic TV ratio; 3:2: Landscape, classic photo ratio; 2:3: Portrait, classic photo ratio\",\"enum\":[\"auto\",\"16:9\",\"9:16\",\"1:1\",\"4:3\",\"3:4\",\"3:2\",\"2:3\"],\"default\":\"auto\"}},\"inputSchema\":{\"schema\":{\"type\":\"object\",\"required\":[\"prompt\"],\"properties\":{\"prompt\":{\"type\":\"string\",\"description\":\"Video description prompt (required, cannot be empty)\\n\\n**EvoLink platform length limit:** Up to `2000` tokens (counted with the cl100k tokenizer, so CJK prompts hit the cap at far fewer characters than Latin ones). The platform also enforces a limit of 60000 UTF-8 bytes.\",\"example\":\"The person starts dancing\"},\"image_urls\":{\"type\":\"array\",\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"description\":\"Input image URL (optional). One image switches the request to image-to-video.\\n\\n**Mode selection:**\\n- `0` images (omit the field): text-to-video, no image charge\\n- `1` image: image-to-video, used as the first frame; input images are billed separately (see the [pricing section](https://evolink.ai/grok-imagine-video-1-5-lite#pricing))\\n- `2` or more images are rejected — reference-to-video is not supported on Lite\\n\\n**Requirements:**\\n- Playground local uploads: up to `10MiB` (10485760 bytes) per image. Image URLs sent directly to the API are validated upstream and do not use this local upload check.\\n- Supported formats: JPEG, PNG, WebP\",\"minItems\":0,\"maxItems\":1,\"example\":[\"https://example.com/image.jpg\"]},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds), any integer between `1` and `15` seconds\",\"minimum\":1,\"maximum\":15,\"default\":6,\"example\":6},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution, default is `480p`\\n\\n**Description:**\\n- `480p`: Standard definition (default)\\n- `720p`: High definition\\n- `1080p`: Upscaled from 720p, billed at a higher per-second rate\\n\\nSee the [pricing section](https://evolink.ai/grok-imagine-video-1-5-lite#pricing) for the per-resolution rates.\",\"enum\":[\"480p\",\"720p\",\"1080p\"],\"default\":\"480p\",\"example\":\"480p\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Output aspect ratio, default is `auto`\\n\\n**Applies to:** text-to-video (`0` images). With an input image the output follows that image's dimensions and this parameter is ignored.\\n\\n**Description:**\\n- `auto`: No ratio is sent upstream and the upstream channel decides the framing (text-to-video currently renders 16:9); this is the default value\\n- `16:9`: Landscape\\n- `9:16`: Portrait\\n- `1:1`: Square\\n- `4:3`: Landscape, classic TV ratio\\n- `3:4`: Portrait, classic TV ratio\\n- `3:2`: Landscape, classic photo ratio\\n- `2:3`: Portrait, classic photo ratio\",\"enum\":[\"auto\",\"16:9\",\"9:16\",\"1:1\",\"4:3\",\"3:4\",\"3:2\",\"2:3\"],\"default\":\"auto\",\"example\":\"16:9\"}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"responseSchema\":{\"schema\":{\"$ref\":\"#/$defs/VideoGenerationResponse\",\"$defs\":{\"VideoGenerationResponse\":{\"type\":\"object\",\"properties\":{\"created\":{\"type\":\"integer\",\"description\":\"Task creation timestamp\",\"example\":1757169743},\"id\":{\"type\":\"string\",\"description\":\"Task ID\",\"example\":\"task-unified-1757169743-7cvnl5zw\"},\"model\":{\"type\":\"string\",\"description\":\"Actual model name used\",\"example\":\"grok-imagine-video-1.5-lite\"},\"object\":{\"type\":\"string\",\"enum\":[\"video.generation.task\"],\"description\":\"Specific task type\"},\"progress\":{\"type\":\"integer\",\"description\":\"Task progress percentage (0-100)\",\"minimum\":0,\"maximum\":100,\"example\":0},\"status\":{\"type\":\"string\",\"description\":\"Task status\",\"enum\":[\"pending\",\"processing\",\"completed\",\"failed\"],\"example\":\"pending\"},\"task_info\":{\"$ref\":\"#/$defs/VideoTaskInfo\",\"description\":\"Video task detailed information\"},\"type\":{\"type\":\"string\",\"enum\":[\"text\",\"image\",\"audio\",\"video\"],\"description\":\"Task output type\",\"example\":\"video\"},\"usage\":{\"$ref\":\"#/$defs/Usage\",\"description\":\"Usage and billing information\"}}},\"VideoTaskInfo\":{\"type\":\"object\",\"properties\":{\"estimated_time\":{\"type\":\"integer\",\"description\":\"Estimated completion time (seconds)\",\"minimum\":0,\"example\":120},\"video_duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds)\",\"example\":6}}},\"Usage\":{\"type\":\"object\",\"description\":\"Usage and billing information\",\"properties\":{\"billing_rule\":{\"type\":\"string\",\"description\":\"Billing rule\",\"enum\":[\"per_call\",\"per_token\",\"per_second\"],\"example\":\"per_second\"},\"credits_reserved\":{\"type\":\"number\",\"description\":\"Estimated credits consumed\",\"minimum\":0,\"example\":5.712},\"user_group\":{\"type\":\"string\",\"description\":\"User group category\",\"example\":\"default\"}}}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"example\":{\"prompt\":\"A neon-lit street at night, slow dolly forward through the rain\",\"duration\":6,\"quality\":\"480p\",\"aspect_ratio\":\"16:9\"}},\"kling-v4-image-to-video\":{\"model\":\"kling-v4-image-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"kling-v4-image-to-video API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/kling/kling-v4-image-to-video\",\"required\":[\"image_start\",\"prompt\"],\"params\":{\"image_start\":{\"type\":\"string\",\"description\":\"First frame image URL for image-to-video generation (required) Note: Image size: up to 10MB; Supported formats: .jpg, .jpeg, .png; Image dimensions: width and height >= 300px, aspect ratio between 1:2.5 and 2.5:1; Image URL must be directly accessible by the server or trigger a direct download when accessed\",\"format\":\"uri\",\"required\":true},\"image_end\":{\"type\":\"string\",\"description\":\"Last frame image URL Note: image_start (first frame) must be provided when using last frame; Supported formats: .jpg, .jpeg, .png; Image size: up to 10MB; Image URL must be directly accessible by the server or trigger a direct download when accessed\",\"format\":\"uri\"},\"keyframes\":{\"type\":\"array\",\"description\":\"Intermediate frame images, evenly spaced in order between the first and last frames Note: Count: 1 to 8 images; The first frame, intermediate frames, and last frame combined must not exceed 10 images or duration + 1 (for example, up to 4 images for 3 seconds or 6 images for 5 seconds); The last frame is optional. If omitted, the model generates the ending frame; Image size: up to 10MB; Supported formats: .jpg, .jpeg, .png; Image dimensions: width and height >= 300px, aspect ratio between 1:2.5 and 2.5:1; Image URL must be directly accessible by the server or trigger a direct download when acc…\",\"minItems\":0,\"maxItems\":8,\"items\":{\"type\":\"object\",\"properties\":{\"image_url\":{\"type\":\"string\",\"description\":\"Intermediate frame image URL\",\"format\":\"uri\",\"required\":true}}}},\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing the video to generate Note: Maximum 2500 characters\",\"maxLength\":2500,\"required\":true},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds. Defaults to 5 seconds Range: Integer from 3 to 30\",\"default\":5,\"minimum\":3,\"maximum\":30},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier Options: 720p: Standard 720P; 1080p: High quality 1080P\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\"}},\"inputSchema\":{\"schema\":{\"type\":\"object\",\"required\":[\"image_start\",\"prompt\"],\"properties\":{\"image_start\":{\"type\":\"string\",\"format\":\"uri\",\"description\":\"First frame image URL for image-to-video generation (**required**)\\n\\n**Note:**\\n- Image size: up to `10MB`\\n- Supported formats: `.jpg`, `.jpeg`, `.png`\\n- Image dimensions: width and height >= `300px`, aspect ratio between `1:2.5` and `2.5:1`\\n- Image URL must be directly accessible by the server or trigger a direct download when accessed\",\"example\":\"https://example.com/portrait.jpg\"},\"image_end\":{\"type\":\"string\",\"format\":\"uri\",\"description\":\"Last frame image URL\\n\\n**Note:**\\n- `image_start` (first frame) must be provided when using last frame\\n- Supported formats: `.jpg`, `.jpeg`, `.png`\\n- Image size: up to `10MB`\\n- Image URL must be directly accessible by the server or trigger a direct download when accessed\",\"example\":\"https://example.com/night.jpg\"},\"keyframes\":{\"type\":\"array\",\"description\":\"Intermediate frame images, evenly spaced in order between the first and last frames\\n\\n**Note:**\\n- Count: `1` to `8` images\\n- The first frame, intermediate frames, and last frame combined must not exceed `10` images or `duration` + 1 (for example, up to `4` images for `3` seconds or `6` images for `5` seconds)\\n- The last frame is optional. If omitted, the model generates the ending frame\\n- Image size: up to `10MB`\\n- Supported formats: `.jpg`, `.jpeg`, `.png`\\n- Image dimensions: width and height >= `300px`, aspect ratio between `1:2.5` and `2.5:1`\\n- Image URL must be directly accessible by the server or trigger a direct download when accessed\",\"items\":{\"type\":\"object\",\"properties\":{\"image_url\":{\"type\":\"string\",\"format\":\"uri\",\"description\":\"Intermediate frame image URL\"}},\"required\":[\"image_url\"],\"additionalProperties\":false},\"minItems\":0,\"maxItems\":8,\"example\":[{\"image_url\":\"https://example.com/half-open.jpg\"},{\"image_url\":\"https://example.com/open.jpg\"}]},\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing the video to generate\\n\\n**Note:**\\n- Maximum `2500` characters\",\"example\":\"The person in the image slowly turns their head and smiles\",\"maxLength\":2500},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds. Defaults to `5` seconds\\n\\n**Range:**\\n- Integer from `3` to `30`\",\"minimum\":3,\"maximum\":30,\"default\":5,\"example\":5},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier\\n\\n**Options:**\\n- `720p`: Standard 720P\\n- `1080p`: High quality 1080P\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\",\"example\":\"720p\"}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"responseSchema\":{\"schema\":{\"$ref\":\"#/$defs/VideoGenerationResponse\",\"$defs\":{\"VideoGenerationResponse\":{\"type\":\"object\",\"properties\":{\"created\":{\"type\":\"integer\",\"description\":\"Task creation timestamp\",\"example\":1757169743},\"id\":{\"type\":\"string\",\"description\":\"Task ID\",\"example\":\"task-unified-1757169743-7cvnl5zw\"},\"model\":{\"type\":\"string\",\"description\":\"Actual model name used\",\"example\":\"kling-v4-image-to-video\"},\"object\":{\"type\":\"string\",\"enum\":[\"video.generation.task\"],\"description\":\"Task type\"},\"progress\":{\"type\":\"integer\",\"description\":\"Task progress percentage (0-100)\",\"minimum\":0,\"maximum\":100,\"example\":0},\"status\":{\"type\":\"string\",\"description\":\"Task status\",\"enum\":[\"pending\",\"processing\",\"completed\",\"failed\"],\"example\":\"pending\"},\"task_info\":{\"$ref\":\"#/$defs/VideoTaskInfo\",\"description\":\"Video task details\"},\"type\":{\"type\":\"string\",\"enum\":[\"text\",\"image\",\"audio\",\"video\"],\"description\":\"Task output type\",\"example\":\"video\"},\"usage\":{\"$ref\":\"#/$defs/VideoUsage\",\"description\":\"Usage and billing information\"}}},\"VideoTaskInfo\":{\"type\":\"object\",\"properties\":{\"estimated_time\":{\"type\":\"integer\",\"description\":\"Estimated completion time (seconds)\",\"minimum\":0,\"example\":300},\"video_duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds)\",\"example\":5}}},\"VideoUsage\":{\"type\":\"object\",\"description\":\"Usage and billing information\",\"properties\":{\"billing_rule\":{\"type\":\"string\",\"description\":\"Billing rule\",\"enum\":[\"per_call\",\"per_token\",\"per_second\"],\"example\":\"per_second\"},\"credits_reserved\":{\"type\":\"number\",\"description\":\"Estimated credits consumed\",\"minimum\":0,\"example\":53.38},\"user_group\":{\"type\":\"string\",\"description\":\"User group category\",\"example\":\"default\"}}}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"example\":{\"prompt\":\"The person in the image slowly turns their head and smiles\",\"image_start\":\"https://example.com/portrait.jpg\",\"duration\":5,\"quality\":\"720p\"}},\"kling-v4-reference-to-video\":{\"model\":\"kling-v4-reference-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"kling-v4-reference-to-video API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/kling/kling-v4-reference-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt, up to 2500 characters Reference syntax: Use <<<xxx>>> in the prompt to reference images and videos, for example: The person from <<<image_1>>> walks down the street following the camera movement in <<<video_1>>>\",\"maxLength\":2500,\"required\":true},\"video_urls\":{\"type\":\"array\",\"description\":\"Reference video URL array, up to 5 clips, corresponding in order to <<<video_1>>>, <<<video_2>>>, etc. in the prompt Video requirements: Formats: MP4 / MOV; Size: ≤ 200MB per clip; Duration: ≥ 3 seconds per clip, ≤ 30 seconds in total; Dimensions: width and height from 720px to 2160px; Frame rate: 24fps to 60fps; Video URLs must be directly accessible by the server\",\"maxItems\":5,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL array (style, scene, or subject references), corresponding in order to <<<image_1>>>, <<<image_2>>>, etc. in the prompt Constraints: Up to 10 images Note: Image URLs must be directly accessible by the server or trigger a direct download when accessed\",\"maxItems\":10,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds, from 3 to 30\",\"default\":5,\"minimum\":3,\"maximum\":30},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio Options: 16:9: Landscape; 9:16: Portrait; 1:1: Square; 21:9: Ultrawide\",\"enum\":[\"16:9\",\"9:16\",\"1:1\",\"21:9\"],\"default\":\"16:9\"},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier Options: 720p: Standard 720P; 1080p: High quality 1080P\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\"}},\"inputSchema\":{\"schema\":{\"type\":\"object\",\"required\":[\"prompt\"],\"properties\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt, up to 2500 characters\\n\\n**Reference syntax:** Use `<<<xxx>>>` in the prompt to reference images and videos, for example: `The person from <<<image_1>>> walks down the street following the camera movement in <<<video_1>>>`\",\"example\":\"The person from <<<image_1>>> walks down the street following the camera movement in <<<video_1>>>\",\"maxLength\":2500},\"video_urls\":{\"type\":\"array\",\"description\":\"Reference video URL array, up to `5` clips, corresponding in order to `<<<video_1>>>`, `<<<video_2>>>`, etc. in the prompt\\n\\n**Video requirements:**\\n- Formats: MP4 / MOV\\n- Size: ≤ 200MB per clip\\n- Duration: ≥ 3 seconds per clip, ≤ 30 seconds in total\\n- Dimensions: width and height from 720px to 2160px\\n- Frame rate: 24fps to 60fps\\n- Video URLs must be directly accessible by the server\",\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"maxItems\":5,\"example\":[\"https://example.com/reference.mp4\"]},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL array (style, scene, or subject references), corresponding in order to `<<<image_1>>>`, `<<<image_2>>>`, etc. in the prompt\\n\\n**Constraints:** Up to `10` images\\n**Note:** Image URLs must be directly accessible by the server or trigger a direct download when accessed\",\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"example\":[\"https://example.com/character.jpg\"],\"maxItems\":10},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds, from 3 to 30\",\"minimum\":3,\"maximum\":30,\"default\":5,\"example\":5},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio\\n\\n**Options:**\\n- `16:9`: Landscape\\n- `9:16`: Portrait\\n- `1:1`: Square\\n- `21:9`: Ultrawide\",\"enum\":[\"16:9\",\"9:16\",\"1:1\",\"21:9\"],\"example\":\"16:9\",\"default\":\"16:9\"},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier\\n\\n**Options:**\\n- `720p`: Standard 720P\\n- `1080p`: High quality 1080P\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\",\"example\":\"720p\"}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"responseSchema\":{\"schema\":{\"$ref\":\"#/$defs/VideoGenerationResponse\",\"$defs\":{\"VideoGenerationResponse\":{\"type\":\"object\",\"properties\":{\"created\":{\"type\":\"integer\",\"description\":\"Task creation timestamp\",\"example\":1757169743},\"id\":{\"type\":\"string\",\"description\":\"Task ID\",\"example\":\"task-unified-1757169743-7cvnl5zw\"},\"model\":{\"type\":\"string\",\"description\":\"Actual model name used\",\"example\":\"kling-v4-reference-to-video\"},\"object\":{\"type\":\"string\",\"enum\":[\"video.generation.task\"],\"description\":\"Task type\"},\"progress\":{\"type\":\"integer\",\"description\":\"Task progress percentage (0-100)\",\"minimum\":0,\"maximum\":100,\"example\":0},\"status\":{\"type\":\"string\",\"description\":\"Task status\",\"enum\":[\"pending\",\"processing\",\"completed\",\"failed\"],\"example\":\"pending\"},\"task_info\":{\"$ref\":\"#/$defs/VideoTaskInfo\",\"description\":\"Video task details\"},\"type\":{\"type\":\"string\",\"enum\":[\"text\",\"image\",\"audio\",\"video\"],\"description\":\"Task output type\",\"example\":\"video\"},\"usage\":{\"$ref\":\"#/$defs/VideoUsage\",\"description\":\"Usage and billing information\"}}},\"VideoTaskInfo\":{\"type\":\"object\",\"properties\":{\"estimated_time\":{\"type\":\"integer\",\"description\":\"Estimated completion time (seconds)\",\"minimum\":0,\"example\":300},\"video_duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds)\",\"example\":9}}},\"VideoUsage\":{\"type\":\"object\",\"description\":\"Usage and billing information\",\"properties\":{\"billing_rule\":{\"type\":\"string\",\"description\":\"Billing rule\",\"enum\":[\"per_call\",\"per_token\",\"per_second\"],\"example\":\"per_second\"},\"credits_reserved\":{\"type\":\"number\",\"description\":\"Estimated credits consumed\",\"minimum\":0,\"example\":53.38},\"user_group\":{\"type\":\"string\",\"description\":\"User group category\",\"example\":\"default\"}}}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"example\":{\"prompt\":\"Keep the same motion style as <<<video_1>>> and replace the background with a snowy scene\",\"video_urls\":[\"https://example.com/reference.mp4\"],\"duration\":5,\"aspect_ratio\":\"16:9\",\"quality\":\"720p\"}},\"kling-v4-text-to-video\":{\"model\":\"kling-v4-text-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"kling-v4-text-to-video API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/kling/kling-v4-text-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing the video to generate Note: Maximum 2500 characters\",\"maxLength\":2500,\"required\":true},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds. Defaults to 5 seconds Range: Integer from 3 to 30\",\"default\":5,\"minimum\":3,\"maximum\":30},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio Options: 16:9: Landscape; 9:16: Portrait; 1:1: Square; 21:9: Ultrawide\",\"enum\":[\"16:9\",\"9:16\",\"1:1\",\"21:9\"],\"default\":\"16:9\"},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier Options: 720p: Standard 720P; 1080p: High quality 1080P\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\"}},\"inputSchema\":{\"schema\":{\"type\":\"object\",\"required\":[\"prompt\"],\"properties\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing the video to generate\\n\\n**Note:**\\n- Maximum `2500` characters\",\"example\":\"A cat running on a grassy field under bright sunshine\",\"maxLength\":2500},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds. Defaults to `5` seconds\\n\\n**Range:**\\n- Integer from `3` to `30`\",\"minimum\":3,\"maximum\":30,\"default\":5,\"example\":5},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio\\n\\n**Options:**\\n- `16:9`: Landscape\\n- `9:16`: Portrait\\n- `1:1`: Square\\n- `21:9`: Ultrawide\",\"enum\":[\"16:9\",\"9:16\",\"1:1\",\"21:9\"],\"example\":\"16:9\",\"default\":\"16:9\"},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier\\n\\n**Options:**\\n- `720p`: Standard 720P\\n- `1080p`: High quality 1080P\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\",\"example\":\"720p\"}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"responseSchema\":{\"schema\":{\"$ref\":\"#/$defs/VideoGenerationResponse\",\"$defs\":{\"VideoGenerationResponse\":{\"type\":\"object\",\"properties\":{\"created\":{\"type\":\"integer\",\"description\":\"Task creation timestamp\",\"example\":1757169743},\"id\":{\"type\":\"string\",\"description\":\"Task ID\",\"example\":\"task-unified-1757169743-7cvnl5zw\"},\"model\":{\"type\":\"string\",\"description\":\"Actual model name used\",\"example\":\"kling-v4-text-to-video\"},\"object\":{\"type\":\"string\",\"enum\":[\"video.generation.task\"],\"description\":\"Task type\"},\"progress\":{\"type\":\"integer\",\"description\":\"Task progress percentage (0-100)\",\"minimum\":0,\"maximum\":100,\"example\":0},\"status\":{\"type\":\"string\",\"description\":\"Task status\",\"enum\":[\"pending\",\"processing\",\"completed\",\"failed\"],\"example\":\"pending\"},\"task_info\":{\"$ref\":\"#/$defs/VideoTaskInfo\",\"description\":\"Video task details\"},\"type\":{\"type\":\"string\",\"enum\":[\"text\",\"image\",\"audio\",\"video\"],\"description\":\"Task output type\",\"example\":\"video\"},\"usage\":{\"$ref\":\"#/$defs/VideoUsage\",\"description\":\"Usage and billing information\"}}},\"VideoTaskInfo\":{\"type\":\"object\",\"properties\":{\"estimated_time\":{\"type\":\"integer\",\"description\":\"Estimated completion time (seconds)\",\"minimum\":0,\"example\":300},\"video_duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds)\",\"example\":5}}},\"VideoUsage\":{\"type\":\"object\",\"description\":\"Usage and billing information\",\"properties\":{\"billing_rule\":{\"type\":\"string\",\"description\":\"Billing rule\",\"enum\":[\"per_call\",\"per_token\",\"per_second\"],\"example\":\"per_second\"},\"credits_reserved\":{\"type\":\"number\",\"description\":\"Estimated credits consumed\",\"minimum\":0,\"example\":53.38},\"user_group\":{\"type\":\"string\",\"description\":\"User group category\",\"example\":\"default\"}}}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"example\":{\"prompt\":\"A cat running on a grassy field under bright sunshine\",\"duration\":5,\"aspect_ratio\":\"16:9\",\"quality\":\"720p\"}},\"kling-v4-video-edit\":{\"model\":\"kling-v4-video-edit\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"kling-v4-video-edit API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/kling/kling-v4-video-edit\",\"required\":[\"prompt\",\"video_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Editing instructions, up to 2500 characters Reference syntax: Use <<<xxx>>> in the prompt to reference images and videos, for example: Replace the coat worn by the person in <<<video_1>>> with the style in <<<image_1>>>\",\"maxLength\":2500,\"required\":true},\"video_urls\":{\"type\":\"array\",\"description\":\"Video URL array for editing. Exactly 1 clip is supported, referenced as <<<video_1>>> in the prompt Video requirements: Formats: MP4 / MOV; Size: ≤ 200MB; Duration: 3 to 30 seconds; Dimensions: width and height from 720px to 2160px; Frame rate: 24fps to 60fps; The video URL must be directly accessible by the server\",\"minItems\":1,\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL array (style references) Constraints: Up to 10 images Note: Image URLs must be directly accessible by the server or trigger a direct download when accessed\",\"maxItems\":10,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"duration\":{\"type\":\"integer|string\",\"description\":\"Output video duration in seconds. Defaults to auto Values: Integer: 3 to 30 seconds; auto: Match the original video duration\",\"default\":\"auto\",\"minimum\":3,\"maximum\":30},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier Options: 720p: Standard 720P; 1080p: High quality 1080P\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\"}},\"inputSchema\":{\"schema\":{\"type\":\"object\",\"required\":[\"prompt\",\"video_urls\"],\"properties\":{\"prompt\":{\"type\":\"string\",\"description\":\"Editing instructions, up to 2500 characters\\n\\n**Reference syntax:** Use `<<<xxx>>>` in the prompt to reference images and videos, for example: `Replace the coat worn by the person in <<<video_1>>> with the style in <<<image_1>>>`\",\"example\":\"Adjust the color to warm tones and add a cinematic feel\",\"maxLength\":2500},\"video_urls\":{\"type\":\"array\",\"description\":\"Video URL array for editing. Exactly `1` clip is supported, referenced as `<<<video_1>>>` in the prompt\\n\\n**Video requirements:**\\n- Formats: MP4 / MOV\\n- Size: ≤ 200MB\\n- Duration: 3 to 30 seconds\\n- Dimensions: width and height from 720px to 2160px\\n- Frame rate: 24fps to 60fps\\n- The video URL must be directly accessible by the server\",\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"minItems\":1,\"maxItems\":1,\"example\":[\"https://example.com/original.mp4\"]},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL array (style references)\\n\\n**Constraints:** Up to `10` images\\n**Note:** Image URLs must be directly accessible by the server or trigger a direct download when accessed\",\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"example\":[\"https://example.com/style_ref.jpg\"],\"maxItems\":10},\"duration\":{\"description\":\"Output video duration in seconds. Defaults to `auto`\\n\\n**Values:**\\n- Integer: `3` to `30` seconds\\n- `auto`: Match the original video duration\",\"oneOf\":[{\"type\":\"integer\",\"minimum\":3,\"maximum\":30},{\"type\":\"string\",\"enum\":[\"auto\"]}],\"default\":\"auto\",\"example\":\"auto\"},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier\\n\\n**Options:**\\n- `720p`: Standard 720P\\n- `1080p`: High quality 1080P\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\",\"example\":\"720p\"}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"responseSchema\":{\"schema\":{\"$ref\":\"#/$defs/VideoGenerationResponse\",\"$defs\":{\"VideoGenerationResponse\":{\"type\":\"object\",\"properties\":{\"created\":{\"type\":\"integer\",\"description\":\"Task creation timestamp\",\"example\":1757169743},\"id\":{\"type\":\"string\",\"description\":\"Task ID\",\"example\":\"task-unified-1757169743-7cvnl5zw\"},\"model\":{\"type\":\"string\",\"description\":\"Actual model name used\",\"example\":\"kling-v4-video-edit\"},\"object\":{\"type\":\"string\",\"enum\":[\"video.generation.task\"],\"description\":\"Task type\"},\"progress\":{\"type\":\"integer\",\"description\":\"Task progress percentage (0-100)\",\"minimum\":0,\"maximum\":100,\"example\":0},\"status\":{\"type\":\"string\",\"description\":\"Task status\",\"enum\":[\"pending\",\"processing\",\"completed\",\"failed\"],\"example\":\"pending\"},\"task_info\":{\"$ref\":\"#/$defs/VideoTaskInfo\",\"description\":\"Video task details\"},\"type\":{\"type\":\"string\",\"enum\":[\"text\",\"image\",\"audio\",\"video\"],\"description\":\"Task output type\",\"example\":\"video\"},\"usage\":{\"$ref\":\"#/$defs/VideoUsage\",\"description\":\"Usage and billing information\"}}},\"VideoTaskInfo\":{\"type\":\"object\",\"properties\":{\"estimated_time\":{\"type\":\"integer\",\"description\":\"Estimated completion time (seconds)\",\"minimum\":0,\"example\":300},\"video_duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds)\",\"example\":9}}},\"VideoUsage\":{\"type\":\"object\",\"description\":\"Usage and billing information\",\"properties\":{\"billing_rule\":{\"type\":\"string\",\"description\":\"Billing rule\",\"enum\":[\"per_call\",\"per_token\",\"per_second\"],\"example\":\"per_second\"},\"credits_reserved\":{\"type\":\"number\",\"description\":\"Estimated credits consumed\",\"minimum\":0,\"example\":63.92},\"user_group\":{\"type\":\"string\",\"description\":\"User group category\",\"example\":\"default\"}}}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"example\":{\"prompt\":\"Adjust the color to warm tones and add a cinematic feel\",\"video_urls\":[\"https://example.com/original.mp4\"],\"quality\":\"720p\"}},\"qwen-audio-3.1-tts-flash\":{\"model\":\"qwen-audio-3.1-tts-flash\",\"kind\":\"audio\",\"path\":\"/v1/audios/generations\",\"title\":\"Qwen Audio 3.1 TTS Flash Speech Synthesis\",\"docs\":\"https://evolink.ai/docs/en/api-manual/audio-series/qwen-audio-tts/qwen-audio-3.1-tts-flash\",\"required\":[],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text to synthesize Constraints: Maximum 5000 characters; Keep punctuation in long text: long continuous passages without sentence breaks may be truncated upstream at about 1500 output tokens (about 120 seconds of audio). The task still reports success and is billed for the tokens actually generated; the gateway cannot detect this truncation; You can also use input. At least one non-empty text field is required; supplying just one is recommended. Different contents in both fields return 400 (parameter_conflict); Text must be in a language supported by the selected voice; otherwise pronunciatio…\",\"maxLength\":5000},\"input\":{\"type\":\"string\",\"description\":\"Alias for prompt, with the same length limits and usage rules; Provide at least one non-empty text field, prompt or input; If both are supplied, their contents must match; otherwise 400 (parameter_conflict) is returned\",\"maxLength\":5000},\"voice\":{\"type\":\"string\",\"description\":\"Voice name, case-sensitive; 68 system voices; see the [voice list](/en/api-manual/audio-series/qwen-audio-tts/qwen-audio-3.1-tts-flash-voices) for names, gender, and use cases; Defaults to longanhuan_v3.1 if omitted; You can also supply a voice you created with [Voice Enrollment](/en/api-manual/audio-series/qwen-audio-tts/voice-enrollment): cloned voices follow qwen-audio-3.1-tts-flash-{prefix}-{32-character-id}, and designed voices follow qwen-audio-3.1-tts-flash-vd-{prefix}-{32-character-id}. Only the account that created the voice can use it. Voices from other models, such as qwen-tts-vd-……\",\"default\":\"longanhuan_v3.1\"},\"response_format\":{\"type\":\"string\",\"description\":\"Output audio format: mp3, wav, or opus; defaults to mp3; opus uses an Ogg Opus container; You can also use format. Supplying just one field is recommended; conflicting values return 400 (parameter_conflict)\",\"enum\":[\"mp3\",\"wav\",\"opus\"],\"default\":\"mp3\"},\"format\":{\"type\":\"string\",\"description\":\"Alias for response_format; supports mp3, wav, and opus; Defaults to mp3 when neither field is supplied; If both fields are supplied, their values must match; otherwise 400 (parameter_conflict) is returned\",\"enum\":[\"mp3\",\"wav\",\"opus\"]},\"sample_rate\":{\"type\":\"integer\",\"description\":\"Output sample rate (Hz); 22050 and 44100 are not supported when response_format is opus; Omitted or null uses the default; 0 or a value outside the list returns 400\",\"enum\":[8000,12000,16000,22050,24000,44100,48000,null],\"default\":24000},\"volume\":{\"type\":\"integer\",\"description\":\"Volume, from 0 to 100\",\"default\":50,\"minimum\":0,\"maximum\":100},\"speech_rate\":{\"type\":\"number\",\"description\":\"Speech rate multiplier; 1.0: normal speed (default); 2.0: double speed; 0.5: half speed Range: 0.5 to 2.0. Adjusting speech rate does not change output token count\",\"default\":1,\"minimum\":0.5,\"maximum\":2},\"pitch\":{\"type\":\"number\",\"description\":\"Pitch multiplier; 1.0: default pitch; Above 1.0 raises pitch; below 1.0 lowers it Range: 0.5 to 2.0 Changing pitch also changes speech rate and audio duration; Higher pitch speeds up speech and shortens audio; lower pitch slows it down and lengthens audio. Duration varies approximately inversely with the square of the pitch value; For a sentence lasting about 2.8 seconds at 1.0: 0.8 is about 4.3 seconds, 1.2 about 2.1 seconds, 0.5 about 10.9 seconds, and 2.0 about 0.7 seconds; Small adjustments between 0.8 and 1.2 are recommended; values near 0.5 or 2.0 make speech noticeably too slow or too…\",\"default\":1,\"minimum\":0.5,\"maximum\":2},\"instruction\":{\"type\":\"string\",\"description\":\"Natural-language instructions to control emotion, tone, character, dialect, and other delivery choices Constraints: Maximum 100 billing characters: Han characters (including Japanese kanji and Korean hanja) count as 2; other characters count as 1, including kana and Hangul (about 50 Han characters or 100 English characters). Exceeding the limit returns 400 Examples: 用欢快、热情的语气说 (speak cheerfully and enthusiastically); 请用上海话表达 (use Shanghainese; multilingual and dialect voices); Speak slowly in a calm and gentle tone Instructions do not count toward input tokens, but can change the generated au…\"},\"language\":{\"type\":\"string\",\"description\":\"Target-language hint to improve the reading of numbers, abbreviations, and symbols, and synthesis in less common languages For example, with zh, 110 in hello, this is 110 is read as “yao yao ling” in Chinese | Value | Language | Value | Language | |---|---|---|---| | zh | Chinese | th | Thai | | en | English | id | Indonesian | | fr | French | vi | Vietnamese | | de | German | es | Spanish | | ja | Japanese | it | Italian | | ko | Korean | ms | Malay | | ru | Russian | fil | Filipino | | pt | Portuguese | ar | Arabic | The model detects the language if omitted; this parameter does not transla…\",\"enum\":[\"zh\",\"en\",\"fr\",\"de\",\"ja\",\"ko\",\"ru\",\"pt\",\"th\",\"id\",\"vi\",\"es\",\"it\",\"ms\",\"fil\",\"ar\"]},\"enable_ssml\":{\"type\":\"boolean\",\"description\":\"Parse prompt as SSML When enabled, SSML tags can be used, such as <break time=\\\"1s\\\"/> for a pause: <speak>欢迎收听今天的节目。<break time=\\\"1s\\\"/>我们马上开始。</speak> Pauses inserted with SSML do not count toward output tokens\",\"default\":false},\"hot_fix\":{\"type\":\"object\",\"description\":\"Custom pronunciation and text replacement to correct polyphonic characters, proper names, and other pronunciations; pronunciation: annotate words with pinyin (separate syllables with spaces and mark tones with digits, such as tian1 qi4) to override the default pronunciation; replace: replace specified words before synthesis. Synthesis and billing use the replaced text, which must also stay within 5000 characters; exceeding the limit returns 400 (prompt_too_long) The two lists may contain at most 200 entries in total, counted as key-value pairs within the objects. Exceeding the limit returns 4…\",\"properties\":{\"pronunciation\":{\"type\":\"array\",\"description\":\"Custom pronunciation list; each item is an object such as {\\\"word\\\": \\\"pinyin\\\"}\",\"items\":{\"type\":\"object\"}},\"replace\":{\"type\":\"array\",\"description\":\"Text replacement list; each item is an object such as {\\\"original word\\\": \\\"replacement text\\\"}\",\"items\":{\"type\":\"object\"}}}},\"enable_aigc_tag\":{\"type\":\"boolean\",\"description\":\"Embed an invisible AIGC marker in generated audio (applies to wav / mp3 / opus)\",\"default\":false}},\"inputSchema\":{\"schema\":{\"type\":\"object\",\"required\":[],\"description\":\"Provide at least one non-empty text field, `prompt` or `input`; if both are supplied, their contents must match. If both `response_format` and `format` are supplied, their values must match.\",\"anyOf\":[{\"required\":[\"prompt\"],\"properties\":{\"prompt\":{\"pattern\":\"\\\\S\"}}},{\"required\":[\"input\"],\"properties\":{\"input\":{\"pattern\":\"\\\\S\"}}}],\"properties\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text to synthesize\\n\\n**Constraints:**\\n- Maximum `5000` characters\\n- Keep punctuation in long text: long continuous passages without sentence breaks may be truncated upstream at about `1500` output tokens (about 120 seconds of audio). The task still reports success and is billed for the tokens actually generated; the gateway cannot detect this truncation\\n- You can also use `input`. At least one non-empty text field is required; supplying just one is recommended. Different contents in both fields return `400` (`parameter_conflict`)\\n- Text must be in a language supported by the selected voice; otherwise pronunciation may be incorrect\\n\\n**Emotion and paralinguistic tags:** Embed tags directly in the text without extra parameters; tag text counts toward billing characters\\n- **Control tags**: Set the emotion or style of the following text until the next control tag. `[sad]` sad, `[amazed]` amazed, `[deep and loud shouting]` deep, loud shouting, `[trembling]` trembling, `[angry]` angry, `[excited]` excited, `[sarcastic]` sarcastic, `[curious]` curious, `[like dracula]` low and eerie, `[bored]` bored, `[tired]` tired, `[scornful]` scornful, `[shouting]` shouting, `[asmr]` soft ASMR whispers, `[panicked]` panicked, `[mischievously]` mischievous, `[empathetic]` empathetic, `[whispers]` whispering, `[reluctantly]` reluctant, `[crying]` crying, `[serious]` serious, `[very slowly]` very slowly, `[very fast]` very fast\\n- **Paralinguistic tags**: Insert a vocal effect at this position without changing the emotion of the surrounding text. `[gasp]` gasp, `[sighing]` sigh, `[clears throat]` clear the throat, `[giggles]` giggle, `[laughing]` laugh, `[cough]` cough, `[snorts]` snort\\n\\n**Example:** `[excited]今天的天气真不错![laughing]我们一起出去玩吧!`\\n\\nWhen `enable_ssml` is `true`, this field is parsed as SSML\",\"maxLength\":5000,\"example\":\"我家的后面有一个很大的花园。\"},\"input\":{\"type\":\"string\",\"description\":\"Alias for `prompt`, with the same length limits and usage rules\\n\\n- Provide at least one non-empty text field, `prompt` or `input`\\n- If both are supplied, their contents must match; otherwise `400` (`parameter_conflict`) is returned\",\"maxLength\":5000,\"example\":\"我家的后面有一个很大的花园。\"},\"voice\":{\"type\":\"string\",\"description\":\"Voice name, case-sensitive\\n\\n- 68 system voices; see the [voice list](/en/api-manual/audio-series/qwen-audio-tts/qwen-audio-3.1-tts-flash-voices) for names, gender, and use cases\\n- Defaults to `longanhuan_v3.1` if omitted\\n- You can also supply a voice you created with [Voice Enrollment](/en/api-manual/audio-series/qwen-audio-tts/voice-enrollment): cloned voices follow `qwen-audio-3.1-tts-flash-{prefix}-{32-character-id}`, and designed voices follow `qwen-audio-3.1-tts-flash-vd-{prefix}-{32-character-id}`. Only the account that created the voice can use it. Voices from other models, such as `qwen-tts-vd-…` from `qwen-voice-design`, return `400` (`invalid_voice`). Missing voices or voices owned by another account return `404` (`voice_not_found`)\\n- Custom voices expire by default `6 hours` after the creation task completes; synthesis after expiry returns `404` (`voice_expired`). Create a new voice with Voice Enrollment\",\"default\":\"longanhuan_v3.1\",\"example\":\"longanhuan_v3.1\"},\"response_format\":{\"type\":\"string\",\"description\":\"Output audio format: `mp3`, `wav`, or `opus`; defaults to `mp3`\\n\\n- `opus` uses an Ogg Opus container\\n- You can also use `format`. Supplying just one field is recommended; conflicting values return `400` (`parameter_conflict`)\",\"enum\":[\"mp3\",\"wav\",\"opus\"],\"default\":\"mp3\",\"example\":\"mp3\"},\"format\":{\"type\":\"string\",\"description\":\"Alias for `response_format`; supports `mp3`, `wav`, and `opus`\\n\\n- Defaults to `mp3` when neither field is supplied\\n- If both fields are supplied, their values must match; otherwise `400` (`parameter_conflict`) is returned\",\"enum\":[\"mp3\",\"wav\",\"opus\"],\"example\":\"mp3\"},\"sample_rate\":{\"type\":[\"integer\",\"null\"],\"description\":\"Output sample rate (Hz)\\n\\n- `22050` and `44100` are not supported when `response_format` is `opus`\\n- Omitted or `null` uses the default; `0` or a value outside the list returns `400`\",\"enum\":[8000,12000,16000,22050,24000,44100,48000,null],\"default\":24000,\"example\":24000},\"volume\":{\"type\":\"integer\",\"description\":\"Volume, from `0` to `100`\",\"minimum\":0,\"maximum\":100,\"default\":50,\"example\":50},\"speech_rate\":{\"type\":\"number\",\"description\":\"Speech rate multiplier\\n\\n- `1.0`: normal speed (default)\\n- `2.0`: double speed; `0.5`: half speed\\n\\nRange: `0.5` to `2.0`. Adjusting speech rate does not change output token count\",\"minimum\":0.5,\"maximum\":2,\"default\":1,\"example\":1},\"pitch\":{\"type\":\"number\",\"description\":\"Pitch multiplier\\n\\n- `1.0`: default pitch\\n- Above `1.0` raises pitch; below `1.0` lowers it\\n\\nRange: `0.5` to `2.0`\\n\\n**Changing pitch also changes speech rate and audio duration**\\n- Higher pitch speeds up speech and shortens audio; lower pitch slows it down and lengthens audio. Duration varies approximately inversely with the square of the pitch value\\n- For a sentence lasting about 2.8 seconds at `1.0`: `0.8` is about 4.3 seconds, `1.2` about 2.1 seconds, `0.5` about 10.9 seconds, and `2.0` about 0.7 seconds\\n- Small adjustments between `0.8` and `1.2` are recommended; values near `0.5` or `2.0` make speech noticeably too slow or too fast\\n- If `speech_rate` is also supplied with a value other than `1.0`, `pitch` has no effect; the two cannot be combined\\n- Adjusting pitch does not change output token count\",\"minimum\":0.5,\"maximum\":2,\"default\":1,\"example\":1},\"instruction\":{\"type\":\"string\",\"description\":\"Natural-language instructions to control emotion, tone, character, dialect, and other delivery choices\\n\\n**Constraints:**\\n- Maximum `100` billing characters: Han characters (including Japanese kanji and Korean hanja) count as 2; other characters count as 1, including kana and Hangul (about 50 Han characters or 100 English characters). Exceeding the limit returns `400`\\n\\n**Examples:**\\n- `用欢快、热情的语气说` (speak cheerfully and enthusiastically)\\n- `请用上海话表达` (use Shanghainese; multilingual and dialect voices)\\n- `Speak slowly in a calm and gentle tone`\\n\\nInstructions do not count toward input tokens, but can change the generated audio duration and therefore output tokens\\n\\n> The parameter is `instruction` (singular); `instructions` returns `400`\",\"example\":\"用欢快、热情的语气说\"},\"language\":{\"type\":\"string\",\"description\":\"Target-language hint to improve the reading of numbers, abbreviations, and symbols, and synthesis in less common languages\\n\\nFor example, with `zh`, `110` in `hello, this is 110` is read as “yao yao ling” in Chinese\\n\\n| Value | Language | Value | Language |\\n|---|---|---|---|\\n| `zh` | Chinese | `th` | Thai |\\n| `en` | English | `id` | Indonesian |\\n| `fr` | French | `vi` | Vietnamese |\\n| `de` | German | `es` | Spanish |\\n| `ja` | Japanese | `it` | Italian |\\n| `ko` | Korean | `ms` | Malay |\\n| `ru` | Russian | `fil` | Filipino |\\n| `pt` | Portuguese | `ar` | Arabic |\\n\\nThe model detects the language if omitted; this parameter does not translate text\",\"enum\":[\"zh\",\"en\",\"fr\",\"de\",\"ja\",\"ko\",\"ru\",\"pt\",\"th\",\"id\",\"vi\",\"es\",\"it\",\"ms\",\"fil\",\"ar\"],\"example\":\"zh\"},\"enable_ssml\":{\"type\":\"boolean\",\"description\":\"Parse `prompt` as SSML\\n\\nWhen enabled, SSML tags can be used, such as `<break time=\\\"1s\\\"/>` for a pause:\\n`<speak>欢迎收听今天的节目。<break time=\\\"1s\\\"/>我们马上开始。</speak>`\\n\\nPauses inserted with SSML do not count toward output tokens\",\"default\":false,\"example\":false},\"hot_fix\":{\"type\":\"object\",\"description\":\"Custom pronunciation and text replacement to correct polyphonic characters, proper names, and other pronunciations\\n\\n- `pronunciation`: annotate words with pinyin (separate syllables with spaces and mark tones with digits, such as `tian1 qi4`) to override the default pronunciation\\n- `replace`: replace specified words before synthesis. Synthesis and billing use the replaced text, which must also stay within `5000` characters; exceeding the limit returns `400` (`prompt_too_long`)\\n\\nThe two lists may contain at most `200` entries in total, counted as key-value pairs within the objects. Exceeding the limit returns `400` (`invalid_parameter`)\\n\\nProvide at least one list. Each provided list must be a non-empty array of objects in `{\\\"word\\\": \\\"value\\\"}` form\\n\\n**Example:**\\n```json\\n{\\n \\\"pronunciation\\\": [{\\\"天气\\\": \\\"tian1 qi4\\\"}],\\n \\\"replace\\\": [{\\\"今天\\\": \\\"金天\\\"}]\\n}\\n```\",\"properties\":{\"pronunciation\":{\"type\":\"array\",\"description\":\"Custom pronunciation list; each item is an object such as `{\\\"word\\\": \\\"pinyin\\\"}`\",\"items\":{\"type\":\"object\",\"additionalProperties\":{\"type\":\"string\"}},\"example\":[{\"天气\":\"tian1 qi4\"}]},\"replace\":{\"type\":\"array\",\"description\":\"Text replacement list; each item is an object such as `{\\\"original word\\\": \\\"replacement text\\\"}`\",\"items\":{\"type\":\"object\",\"additionalProperties\":{\"type\":\"string\"}},\"example\":[{\"今天\":\"金天\"}]}}},\"enable_aigc_tag\":{\"type\":\"boolean\",\"description\":\"Embed an invisible AIGC marker in generated audio (applies to `wav` / `mp3` / `opus`)\",\"default\":false,\"example\":false}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"responseSchema\":{\"schema\":{\"$ref\":\"#/$defs/QwenAudioTtsResponse\",\"$defs\":{\"QwenAudioTtsResponse\":{\"type\":\"object\",\"properties\":{\"created\":{\"type\":\"integer\",\"description\":\"Task creation timestamp\",\"example\":1790000000},\"id\":{\"type\":\"string\",\"description\":\"Task ID\",\"example\":\"task-unified-1790000000-abcd1234\"},\"model\":{\"type\":\"string\",\"description\":\"Model actually used\",\"example\":\"qwen-audio-3.1-tts-flash\"},\"object\":{\"type\":\"string\",\"enum\":[\"audio.generation.task\"],\"description\":\"Specific task object type\"},\"progress\":{\"type\":\"integer\",\"description\":\"Task progress percentage (0–100)\",\"minimum\":0,\"maximum\":100,\"example\":0},\"status\":{\"type\":\"string\",\"description\":\"Task status\",\"enum\":[\"pending\",\"processing\",\"completed\",\"failed\"],\"example\":\"pending\"},\"task_info\":{\"$ref\":\"#/$defs/AudioTaskInfo\",\"description\":\"Audio task details\"},\"type\":{\"type\":\"string\",\"enum\":[\"audio\"],\"description\":\"Task output type\",\"example\":\"audio\"},\"usage\":{\"$ref\":\"#/$defs/AudioUsage\",\"description\":\"Usage and billing information\"}}},\"AudioTaskInfo\":{\"type\":\"object\",\"properties\":{\"estimated_time\":{\"type\":\"integer\",\"description\":\"Estimated completion time in seconds; increases with text length, up to about `90` seconds\",\"minimum\":0,\"example\":3},\"audio_type\":{\"type\":\"string\",\"description\":\"Audio task type\",\"example\":\"tts\"}}},\"AudioUsage\":{\"type\":\"object\",\"description\":\"Usage information\",\"properties\":{\"credits_reserved\":{\"type\":\"number\",\"description\":\"Credits reserved based on text length; settled against actual token usage on completion, with excess refunded or shortfall charged\",\"minimum\":0,\"example\":0.0144}}}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"example\":{\"prompt\":\"我家的后面有一个很大的花园。\"}},\"veo-3.1-lite-generate-preview\":{\"model\":\"veo-3.1-lite-generate-preview\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Veo-3.1-Lite-Generate-Preview API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/veo3.1/veo-3.1-lite-generate-preview-generate\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the video, up to 2000 tokens. Counted with cl100k; tokens are not characters. Google lists English as the supported prompt language. EvoLink does not reject requests based on prompt language; results in other languages are not guaranteed.\",\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Input image URLs for image-to-video Notes: Up to 2 images per request: 1 image is used as the first frame, 2 images are used as the first and last frames; Image size: no larger than 10 MB; Supported file formats: .jpg, .jpeg, .png\",\"maxItems\":2,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"generation_type\":{\"type\":\"string\",\"description\":\"Generation mode. When omitted it is inferred from the number of images: TEXT: Text-to-video (input images, if any, are not used); FIRST&LAST: First-last frame, 1-2 images REFERENCE (reference images) is not supported by this model and returns 400\",\"enum\":[\"TEXT\",\"FIRST&LAST\"]},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio. auto is the same as omitting aspect_ratio: no ratio is specified and the model decides\",\"enum\":[\"auto\",\"16:9\",\"9:16\"]},\"generate_audio\":{\"type\":\"boolean\",\"description\":\"Whether to generate audio, default true. Generating audio increases the per-second rate\",\"default\":true},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds, default 4. Longer videos cost more\",\"enum\":[4,6,8],\"default\":4},\"n\":{\"type\":\"integer\",\"description\":\"Number of videos to generate, default 1. Each video is billed separately\",\"default\":1,\"minimum\":1,\"maximum\":4},\"quality\":{\"type\":\"string\",\"description\":\"Output resolution, default 720p. 1080p has a higher per-second rate; 4k is not supported by this model\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\"},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed used to reproduce generation results\",\"minimum\":1,\"maximum\":4294967295},\"negative_prompt\":{\"type\":\"string\",\"description\":\"Negative prompt describing content to exclude from the video\"},\"person_generation\":{\"type\":\"string\",\"description\":\"Person generation control. When omitted, the upstream default is allow_adult. allow_adult: allow adults only; dont_allow: do not generate videos containing people or faces\",\"enum\":[\"allow_adult\",\"dont_allow\"]},\"resize_mode\":{\"type\":\"string\",\"description\":\"Image resize mode for image-to-video. When omitted, the upstream default is pad. pad: add padding to fit the output aspect ratio; crop: center-crop to fit the output aspect ratio. Requires an input image; providing this parameter without an image returns 400\",\"enum\":[\"pad\",\"crop\"]}},\"inputSchema\":{\"schema\":{\"type\":\"object\",\"required\":[\"prompt\"],\"properties\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the video, up to `2000` tokens. Counted with cl100k; tokens are not characters. Google lists English as the supported prompt language. EvoLink does not reject requests based on prompt language; results in other languages are not guaranteed.\",\"example\":\"A golden retriever puppy running through a sunlit meadow, slow motion, cinematic lighting\"},\"image_urls\":{\"type\":\"array\",\"description\":\"Input image URLs for image-to-video\\n\\n**Notes:**\\n- Up to `2` images per request: `1` image is used as the first frame, `2` images are used as the first and last frames\\n- Image size: no larger than `10 MB`\\n- Supported file formats: `.jpg`, `.jpeg`, `.png`\",\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"maxItems\":2,\"example\":[\"https://example.com/first-frame.jpg\"]},\"generation_type\":{\"type\":\"string\",\"description\":\"Generation mode. When omitted it is inferred from the number of images:\\n- `TEXT`: Text-to-video (input images, if any, are not used)\\n- `FIRST&LAST`: First-last frame, 1-2 images\\n\\n`REFERENCE` (reference images) is not supported by this model and returns `400`\",\"enum\":[\"TEXT\",\"FIRST&LAST\"]},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio. `auto` is the same as omitting `aspect_ratio`: no ratio is specified and the model decides\",\"enum\":[\"auto\",\"16:9\",\"9:16\"]},\"generate_audio\":{\"type\":\"boolean\",\"description\":\"Whether to generate audio, default `true`. Generating audio increases the per-second rate\",\"default\":true},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds, default `4`. Longer videos cost more\",\"enum\":[4,6,8],\"default\":4},\"n\":{\"type\":\"integer\",\"description\":\"Number of videos to generate, default `1`. Each video is billed separately\",\"minimum\":1,\"maximum\":4,\"default\":1},\"quality\":{\"type\":\"string\",\"description\":\"Output resolution, default `720p`. `1080p` has a higher per-second rate; `4k` is not supported by this model\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\"},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed used to reproduce generation results\",\"minimum\":1,\"maximum\":4294967295},\"negative_prompt\":{\"type\":\"string\",\"description\":\"Negative prompt describing content to exclude from the video\"},\"person_generation\":{\"type\":\"string\",\"description\":\"Person generation control. When omitted, the upstream default is `allow_adult`. `allow_adult`: allow adults only; `dont_allow`: do not generate videos containing people or faces\",\"enum\":[\"allow_adult\",\"dont_allow\"]},\"resize_mode\":{\"type\":\"string\",\"description\":\"Image resize mode for image-to-video. When omitted, the upstream default is `pad`. `pad`: add padding to fit the output aspect ratio; `crop`: center-crop to fit the output aspect ratio. Requires an input image; providing this parameter without an image returns `400`\",\"enum\":[\"pad\",\"crop\"]}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"responseSchema\":{\"schema\":{\"$ref\":\"#/$defs/VideoGenerationResponse\",\"$defs\":{\"VideoGenerationResponse\":{\"type\":\"object\",\"properties\":{\"created\":{\"type\":\"integer\",\"description\":\"Task creation timestamp\",\"example\":1757169743},\"id\":{\"type\":\"string\",\"description\":\"Task ID\",\"example\":\"task-unified-1757169743-7cvnl5zw\"},\"model\":{\"type\":\"string\",\"description\":\"Actual model name used\",\"example\":\"veo-3.1-lite-generate-preview\"},\"object\":{\"type\":\"string\",\"enum\":[\"video.generation.task\"],\"description\":\"Specific type of the task\"},\"progress\":{\"type\":\"integer\",\"description\":\"Task progress percentage (0-100)\",\"minimum\":0,\"maximum\":100,\"example\":0},\"status\":{\"type\":\"string\",\"description\":\"Task status\",\"enum\":[\"pending\",\"processing\",\"completed\",\"failed\"],\"example\":\"processing\"},\"task_info\":{\"$ref\":\"#/$defs/VideoTaskInfo\",\"description\":\"Video task details\"},\"type\":{\"type\":\"string\",\"enum\":[\"text\",\"image\",\"audio\",\"video\"],\"description\":\"Output type of the task\",\"example\":\"video\"},\"usage\":{\"$ref\":\"#/$defs/VideoUsage\",\"description\":\"Usage and billing information\"}}},\"VideoTaskInfo\":{\"type\":\"object\",\"properties\":{\"estimated_time\":{\"type\":\"integer\",\"description\":\"Estimated completion time (seconds)\",\"minimum\":0,\"example\":600},\"video_duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds)\",\"example\":4}}},\"VideoUsage\":{\"type\":\"object\",\"description\":\"Usage and billing information\",\"properties\":{\"billing_rule\":{\"type\":\"string\",\"description\":\"Billing rule\",\"enum\":[\"per_call\",\"per_token\",\"per_second\"],\"example\":\"per_call\"},\"credits_reserved\":{\"type\":\"number\",\"description\":\"Estimated credits consumed\",\"minimum\":0,\"example\":12.24},\"user_group\":{\"type\":\"string\",\"description\":\"User group category\",\"example\":\"default\"}}}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"example\":{\"prompt\":\"A golden retriever puppy running through a sunlit meadow, slow motion, cinematic lighting\"}}}}";
|
|
4
|
+
export const MODEL_PARAMS_OVERRIDES_JSON = "{\"meta\":{\"source\":\"mintlify-docs en/api-manual\",\"commit\":\"047cc988\",\"files\":224,\"endpoints\":171,\"models\":21},\"models\":{\"gemini-nano-banana-2.1\":{\"model\":\"gemini-nano-banana-2.1\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"Nano Banana 2.1 API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/nanobanana/nanobanana-2.1/nanobanana-2.1-image-generate\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the image to generate or how to edit an input image, up to 4000 tokens\",\"required\":true},\"size\":{\"type\":\"string\",\"description\":\"Aspect ratio of the generated image, default is auto\",\"enum\":[\"auto\",\"1:1\",\"1:4\",\"4:1\",\"1:8\",\"8:1\",\"2:3\",\"3:2\",\"3:4\",\"4:3\",\"4:5\",\"5:4\",\"9:16\",\"16:9\",\"21:9\"],\"default\":\"auto\"},\"quality\":{\"type\":\"string\",\"description\":\"Output image resolution, default is 2K Note: Prices vary by resolution. Output images are billed at the selected resolution. Setting this parameter explicitly is recommended\",\"enum\":[\"1K\",\"2K\",\"4K\"],\"default\":\"2K\"},\"image_urls\":{\"type\":\"array\",\"description\":\"List of reference image URLs for image to image generation, image editing, and multi-image composition Note: Up to 14 input images per request; Image size: no more than 20MB; Supported file formats: .jpeg, .jpg, .png, .webp; Image URLs must be directly accessible by the server or trigger a direct image download when accessed (such URLs typically end in an image extension such as .png or .jpg); Input images are billed per image\",\"maxItems\":14,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"model_params\":{\"type\":\"object\",\"description\":\"Model extension parameters\",\"properties\":{\"web_search\":{\"type\":\"boolean\",\"description\":\"Whether to enable web search, default is false. When enabled, the model searches for the latest information on the web before generating the image Note: Billed by the actual number of searches performed by the model. A single request may involve multiple searches\",\"default\":false},\"image_search\":{\"type\":\"boolean\",\"description\":\"Whether to enable image search, default is false. When enabled, the model retrieves images from the web as visual references before generating the image Note: Billed by the actual number of searches performed by the model. A single request may involve multiple searches\",\"default\":false},\"thinking_level\":{\"type\":\"string\",\"description\":\"Reasoning level controlling how deeply the model reasons before generating an image, default is auto; auto: leave unspecified and let the model decide; min: minimal reasoning, fastest generation; medium: balanced reasoning; high: deep reasoning Note: Reasoning tokens are billed as text output\",\"enum\":[\"auto\",\"min\",\"medium\",\"high\"],\"default\":\"auto\"}}}},\"inputSchema\":{\"schema\":{\"type\":\"object\",\"required\":[\"prompt\"],\"properties\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the image to generate or how to edit an input image, up to `4000` tokens\",\"example\":\"A cat playing in the grass\"},\"size\":{\"type\":\"string\",\"description\":\"Aspect ratio of the generated image, default is `auto`\",\"enum\":[\"auto\",\"1:1\",\"1:4\",\"4:1\",\"1:8\",\"8:1\",\"2:3\",\"3:2\",\"3:4\",\"4:3\",\"4:5\",\"5:4\",\"9:16\",\"16:9\",\"21:9\"],\"default\":\"auto\"},\"quality\":{\"type\":\"string\",\"description\":\"Output image resolution, default is `2K`\\n\\n**Note:**\\n- Prices vary by resolution. Output images are billed at the selected resolution. Setting this parameter explicitly is recommended\",\"enum\":[\"1K\",\"2K\",\"4K\"],\"default\":\"2K\"},\"image_urls\":{\"type\":\"array\",\"description\":\"List of reference image URLs for image to image generation, image editing, and multi-image composition\\n\\n**Note:**\\n- Up to `14` input images per request\\n- Image size: no more than `20MB`\\n- Supported file formats: `.jpeg`, `.jpg`, `.png`, `.webp`\\n- Image URLs must be directly accessible by the server or trigger a direct image download when accessed (such URLs typically end in an image extension such as `.png` or `.jpg`)\\n- Input images are billed per image\",\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"maxItems\":14,\"example\":[\"https://example.com/image1.png\",\"https://example.com/image2.png\"]},\"model_params\":{\"type\":\"object\",\"description\":\"Model extension parameters\",\"properties\":{\"web_search\":{\"type\":\"boolean\",\"description\":\"Whether to enable web search, default is `false`. When enabled, the model searches for the latest information on the web before generating the image\\n\\n**Note:**\\n- Billed by the actual number of searches performed by the model. A single request may involve multiple searches\",\"default\":false,\"example\":true},\"image_search\":{\"type\":\"boolean\",\"description\":\"Whether to enable image search, default is `false`. When enabled, the model retrieves images from the web as visual references before generating the image\\n\\n**Note:**\\n- Billed by the actual number of searches performed by the model. A single request may involve multiple searches\",\"default\":false,\"example\":true},\"thinking_level\":{\"type\":\"string\",\"description\":\"Reasoning level controlling how deeply the model reasons before generating an image, default is `auto`\\n\\n- `auto`: leave unspecified and let the model decide\\n- `min`: minimal reasoning, fastest generation\\n- `medium`: balanced reasoning\\n- `high`: deep reasoning\\n\\n**Note:**\\n- Reasoning tokens are billed as text output\",\"enum\":[\"auto\",\"min\",\"medium\",\"high\"],\"default\":\"auto\",\"example\":\"medium\"}}}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"responseSchema\":{\"schema\":{\"$ref\":\"#/$defs/ImageGenerationResponse\",\"$defs\":{\"ImageGenerationResponse\":{\"type\":\"object\",\"properties\":{\"created\":{\"type\":\"integer\",\"description\":\"Task creation timestamp\",\"example\":1757165031},\"id\":{\"type\":\"string\",\"description\":\"Task ID\",\"example\":\"task-unified-1757165031-uyujaw3d\"},\"model\":{\"type\":\"string\",\"description\":\"Actual model name used\",\"example\":\"gemini-nano-banana-2.1\"},\"object\":{\"type\":\"string\",\"enum\":[\"image.generation.task\"],\"description\":\"Specific task type\"},\"progress\":{\"type\":\"integer\",\"description\":\"Task progress percentage (0-100)\",\"minimum\":0,\"maximum\":100,\"example\":0},\"status\":{\"type\":\"string\",\"description\":\"Task status\",\"enum\":[\"pending\",\"processing\",\"completed\",\"failed\"],\"example\":\"pending\"},\"task_info\":{\"$ref\":\"#/$defs/TaskInfo\",\"description\":\"Asynchronous task information\"},\"type\":{\"type\":\"string\",\"enum\":[\"text\",\"image\",\"audio\",\"video\"],\"description\":\"Task output type\",\"example\":\"image\"},\"usage\":{\"$ref\":\"#/$defs/Usage\",\"description\":\"Usage and billing information\"}}},\"TaskInfo\":{\"type\":\"object\",\"properties\":{\"estimated_time\":{\"type\":\"integer\",\"description\":\"Estimated completion time (seconds)\",\"minimum\":0,\"example\":45}}},\"Usage\":{\"type\":\"object\",\"description\":\"Usage and billing information\",\"properties\":{\"billing_rule\":{\"type\":\"string\",\"description\":\"Billing rule\",\"enum\":[\"per_call\",\"per_image\",\"per_token\",\"per_second\"],\"example\":\"per_image\"},\"credits_reserved\":{\"type\":\"number\",\"description\":\"Estimated credits consumed\",\"minimum\":0,\"example\":3.0845},\"user_group\":{\"type\":\"string\",\"description\":\"Billing group the user belongs to\",\"example\":\"default\"}}}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"example\":{\"prompt\":\"A cat playing on the grass\",\"size\":\"16:9\",\"quality\":\"2K\"}},\"gemini-omni-1.2-flash-image-to-video\":{\"model\":\"gemini-omni-1.2-flash-image-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Gemini Omni 1.2 Flash Image-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/gemini-omni-1.2-flash/gemini-omni-1.2-flash-image-to-video\",\"required\":[\"prompt\",\"image_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing how the first frame should move and how the scene should evolve. Supports Chinese and English. For more stable results, describe the desired action and changes clearly. Write negative requirements directly in prompt, such as No dialogue or No text; there is no separate negative prompt parameter. The prompt is required and must not be empty or contain only whitespace.\",\"minLength\":1,\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"First/last-frame image array, containing 1–2 images.; One image: the first frame.; Two images: the first frame, then the last frame. The model generates a transition between them; maximum duration is 10 seconds.; A last frame must accompany a first frame and cannot be supplied alone. Only HTTP/HTTPS image URLs are supported. Formats: png, jpeg, webp.\",\"minItems\":1,\"maxItems\":2,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution; default 720p. Supported values: 360p: landscape 640×360 / portrait 360×640; 720p: landscape 1280×720 / portrait 720×1280; default; 1080p: landscape 1920×1080 / portrait 1080×1920; 4k: landscape 3840×2160 / portrait 2160×3840 Orientation is controlled by aspect_ratio: 16:9 produces landscape and 9:16 produces portrait. Billing: Video output is billed by output tokens, which scale linearly with resolution. Relative to 720p, 360p uses about one third, 1080p about 1.5×, and 4k about 3×. Actual charges are based on generated usage.\",\"enum\":[\"360p\",\"720p\",\"1080p\",\"4k\"],\"default\":\"720p\"},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds; default 3.; One first-frame image: any integer from 3 to 15.; Two first/last-frame images: any integer from 3 to 10.; Duration directly affects billing.\",\"default\":3,\"minimum\":3,\"maximum\":15},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Aspect ratio: 16:9, 9:16, or auto; default auto.\",\"enum\":[\"16:9\",\"9:16\",\"auto\"],\"default\":\"auto\"},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed; random by default.; Range: 0–4294967295.; Fixing the seed reduces variation from parameter changes when tuning prompts and improves reproducibility.\",\"minimum\":0,\"maximum\":4294967295}},\"conditions\":[{\"if\":{\"properties\":{\"image_urls\":{\"minItems\":2}},\"required\":[\"image_urls\"]},\"then\":{\"properties\":{\"duration\":{\"maximum\":10}}}}],\"inputSchema\":{\"schema\":{\"required\":[\"prompt\",\"image_urls\"],\"type\":\"object\",\"additionalProperties\":false,\"properties\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing how the first frame should move and how the scene should evolve.\\n\\nSupports Chinese and English. For more stable results, describe the desired action and changes clearly. Write negative requirements directly in `prompt`, such as `No dialogue` or `No text`; there is no separate negative prompt parameter.\\n\\nThe prompt is required and must not be empty or contain only whitespace.\",\"example\":\"The person slowly turns their head and smiles while leaves in the background sway gently in the wind.\",\"minLength\":1,\"pattern\":\"\\\\S\"},\"image_urls\":{\"type\":\"array\",\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"minItems\":1,\"maxItems\":2,\"description\":\"First/last-frame image array, containing 1–2 images.\\n\\n- One image: the **first frame**.\\n- Two images: the **first frame**, then the **last frame**. The model generates a transition between them; maximum `duration` is `10` seconds.\\n- A last frame must accompany a first frame and cannot be supplied alone.\\n\\nOnly HTTP/HTTPS image URLs are supported. Formats: `png`, `jpeg`, `webp`.\",\"example\":[\"https://example.com/first-frame.jpg\",\"https://example.com/last-frame.jpg\"]},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution; default `720p`.\\n\\n**Supported values:**\\n- `360p`: landscape 640×360 / portrait 360×640\\n- `720p`: landscape 1280×720 / portrait 720×1280; default\\n- `1080p`: landscape 1920×1080 / portrait 1080×1920\\n- `4k`: landscape 3840×2160 / portrait 2160×3840\\n\\nOrientation is controlled by `aspect_ratio`: `16:9` produces landscape and `9:16` produces portrait.\\n\\n**Billing:** Video output is billed by output tokens, which scale linearly with resolution. Relative to `720p`, `360p` uses about one third, `1080p` about 1.5×, and `4k` about 3×. Actual charges are based on generated usage.\",\"enum\":[\"360p\",\"720p\",\"1080p\",\"4k\"],\"default\":\"720p\",\"example\":\"720p\"},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds; default `3`.\\n\\n- One first-frame image: any integer from `3` to `15`.\\n- Two first/last-frame images: any integer from `3` to `10`.\\n- Duration directly affects billing.\",\"minimum\":3,\"maximum\":15,\"default\":3,\"example\":3},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Aspect ratio: 16:9, 9:16, or auto; default auto.\",\"enum\":[\"16:9\",\"9:16\",\"auto\"],\"default\":\"auto\",\"example\":\"auto\"},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed; random by default.\\n\\n- Range: `0`–`4294967295`.\\n- Fixing the seed reduces variation from parameter changes when tuning prompts and improves reproducibility.\",\"minimum\":0,\"maximum\":4294967295,\"example\":42}},\"allOf\":[{\"if\":{\"properties\":{\"image_urls\":{\"minItems\":2}},\"required\":[\"image_urls\"]},\"then\":{\"properties\":{\"duration\":{\"maximum\":10}}}}]},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"responseSchema\":{\"schema\":{\"$ref\":\"#/$defs/VideoGenerationResponse\",\"$defs\":{\"VideoGenerationResponse\":{\"type\":\"object\",\"properties\":{\"created\":{\"type\":\"integer\",\"description\":\"Task creation timestamp\",\"example\":1757169743},\"id\":{\"type\":\"string\",\"description\":\"Task ID\",\"example\":\"task-unified-1757169743-7cvnl5zw\"},\"model\":{\"type\":\"string\",\"description\":\"The model name actually used\",\"example\":\"gemini-omni-1.2-flash-image-to-video\"},\"object\":{\"type\":\"string\",\"enum\":[\"video.generation.task\"],\"description\":\"The specific type of the task\"},\"progress\":{\"type\":\"integer\",\"description\":\"Task progress percentage (0-100)\",\"minimum\":0,\"maximum\":100,\"example\":0},\"status\":{\"type\":\"string\",\"description\":\"Task status. The create endpoint always returns `processing`; the internal `pending` state is also exposed to clients as `processing`.\",\"enum\":[\"pending\",\"processing\",\"completed\",\"failed\"],\"example\":\"processing\"},\"task_info\":{\"$ref\":\"#/$defs/VideoTaskInfo\",\"description\":\"Detailed video task information\"},\"type\":{\"type\":\"string\",\"enum\":[\"text\",\"image\",\"audio\",\"video\"],\"description\":\"The output type of the task\",\"example\":\"video\"},\"usage\":{\"$ref\":\"#/$defs/Usage\",\"description\":\"Usage and billing information\"}}},\"VideoTaskInfo\":{\"type\":\"object\",\"properties\":{\"estimated_time\":{\"type\":\"integer\",\"description\":\"Estimated completion time (seconds)\",\"minimum\":0,\"example\":60},\"video_duration\":{\"type\":\"integer\",\"description\":\"Output duration in seconds; equals duration.\",\"example\":3}}},\"Usage\":{\"type\":\"object\",\"description\":\"Usage and billing information\",\"properties\":{\"billing_rule\":{\"type\":\"string\",\"description\":\"Billing rule\",\"enum\":[\"per_call\",\"per_token\",\"per_second\"],\"example\":\"per_token\"},\"credits_reserved\":{\"type\":\"number\",\"description\":\"Estimated credits to be consumed\",\"minimum\":0,\"example\":102.34},\"user_group\":{\"type\":\"string\",\"description\":\"Billing group the user belongs to\",\"example\":\"default\"}}}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"example\":{\"prompt\":\"The person slowly turns their head and smiles while leaves in the background sway gently in the wind.\",\"image_urls\":[\"https://example.com/portrait.jpg\"],\"quality\":\"720p\",\"aspect_ratio\":\"16:9\",\"duration\":3}},\"gemini-omni-1.2-flash-reference-to-video\":{\"model\":\"gemini-omni-1.2-flash-reference-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Gemini Omni 1.2 Flash Reference-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/gemini-omni-1.2-flash/gemini-omni-1.2-flash-reference-to-video\",\"required\":[\"prompt\",\"image_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing how the reference subjects, style, and motion should appear in the output. Supports Chinese and English. For more stable results, describe the desired action and changes clearly. Write negative requirements directly in prompt, such as No dialogue or No text; there is no separate negative prompt parameter. The prompt is required and must not be empty or contain only whitespace.\",\"minLength\":1,\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL array. Required; supports 1 to 10 images for constraining subjects, style, or elements. Input requirements: HTTP/HTTPS image URLs only; Supported formats: png, jpeg, webp\",\"minItems\":1,\"maxItems\":10,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"video_urls\":{\"type\":\"array\",\"description\":\"Optional reference video array. Up to 3 videos; when duration exceeds 10 seconds, at most 1. Use alongside image_urls to guide action, camera movement, or style. Input: HTTP/HTTPS video URLs only; mp4 format. Billing: Each reference video's duration contributes to input tokens. Each reference video must be no longer than 10 seconds.\",\"minItems\":1,\"maxItems\":3,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution; default 720p. Supported values: 360p: landscape 640×360 / portrait 360×640; 720p: landscape 1280×720 / portrait 720×1280; default; 1080p: landscape 1920×1080 / portrait 1080×1920; 4k: landscape 3840×2160 / portrait 2160×3840 Orientation is controlled by aspect_ratio: 16:9 produces landscape and 9:16 produces portrait. Billing: Video output is billed by output tokens, which scale linearly with resolution. Relative to 720p, 360p uses about one third, 1080p about 1.5×, and 4k about 3×. Actual charges are based on generated usage.\",\"enum\":[\"360p\",\"720p\",\"1080p\",\"4k\"],\"default\":\"720p\"},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds; default 3. Accepts any integer from 3 to 15. Duration directly affects billing.\",\"default\":3,\"minimum\":3,\"maximum\":15},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Aspect ratio: 16:9, 9:16, or auto; default auto.\",\"enum\":[\"16:9\",\"9:16\",\"auto\"],\"default\":\"auto\"},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed; random by default.; Range: 0–4294967295.; Fixing the seed reduces variation from parameter changes when tuning prompts and improves reproducibility.\",\"minimum\":0,\"maximum\":4294967295}},\"conditions\":[{\"if\":{\"properties\":{\"duration\":{\"type\":\"integer\",\"minimum\":11}},\"required\":[\"duration\"]},\"then\":{\"properties\":{\"video_urls\":{\"maxItems\":1}}}}],\"inputSchema\":{\"schema\":{\"required\":[\"prompt\",\"image_urls\"],\"type\":\"object\",\"additionalProperties\":false,\"properties\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing how the reference subjects, style, and motion should appear in the output.\\n\\nSupports Chinese and English. For more stable results, describe the desired action and changes clearly. Write negative requirements directly in `prompt`, such as `No dialogue` or `No text`; there is no separate negative prompt parameter.\\n\\nThe prompt is required and must not be empty or contain only whitespace.\",\"example\":\"A kitten playfully paws at a ball of yarn.\",\"minLength\":1,\"pattern\":\"\\\\S\"},\"image_urls\":{\"type\":\"array\",\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"minItems\":1,\"maxItems\":10,\"description\":\"Reference image URL array. Required; supports 1 to 10 images for constraining subjects, style, or elements.\\n\\n**Input requirements:**\\n- HTTP/HTTPS image URLs only\\n- Supported formats: `png`, `jpeg`, `webp`\",\"example\":[\"https://example.com/character.png\",\"https://example.com/scene.png\"]},\"video_urls\":{\"type\":\"array\",\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"minItems\":1,\"maxItems\":3,\"description\":\"Optional reference video array. Up to 3 videos; when `duration` exceeds `10` seconds, at most 1.\\n\\nUse alongside `image_urls` to guide action, camera movement, or style.\\n\\n**Input:** HTTP/HTTPS video URLs only; mp4 format.\\n\\n**Billing:** Each reference video's duration contributes to input tokens.\\n\\nEach reference video must be no longer than `10` seconds.\",\"example\":[\"https://example.com/reference.mp4\"]},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution; default `720p`.\\n\\n**Supported values:**\\n- `360p`: landscape 640×360 / portrait 360×640\\n- `720p`: landscape 1280×720 / portrait 720×1280; default\\n- `1080p`: landscape 1920×1080 / portrait 1080×1920\\n- `4k`: landscape 3840×2160 / portrait 2160×3840\\n\\nOrientation is controlled by `aspect_ratio`: `16:9` produces landscape and `9:16` produces portrait.\\n\\n**Billing:** Video output is billed by output tokens, which scale linearly with resolution. Relative to `720p`, `360p` uses about one third, `1080p` about 1.5×, and `4k` about 3×. Actual charges are based on generated usage.\",\"enum\":[\"360p\",\"720p\",\"1080p\",\"4k\"],\"default\":\"720p\",\"example\":\"720p\"},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds; default `3`. Accepts any integer from `3` to `15`. Duration directly affects billing.\",\"minimum\":3,\"maximum\":15,\"default\":3,\"example\":3},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Aspect ratio: 16:9, 9:16, or auto; default auto.\",\"enum\":[\"16:9\",\"9:16\",\"auto\"],\"default\":\"auto\",\"example\":\"auto\"},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed; random by default.\\n\\n- Range: `0`–`4294967295`.\\n- Fixing the seed reduces variation from parameter changes when tuning prompts and improves reproducibility.\",\"minimum\":0,\"maximum\":4294967295,\"example\":42}},\"allOf\":[{\"if\":{\"properties\":{\"duration\":{\"type\":\"integer\",\"minimum\":11}},\"required\":[\"duration\"]},\"then\":{\"properties\":{\"video_urls\":{\"maxItems\":1}}}}]},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"responseSchema\":{\"schema\":{\"$ref\":\"#/$defs/VideoGenerationResponse\",\"$defs\":{\"VideoGenerationResponse\":{\"type\":\"object\",\"properties\":{\"created\":{\"type\":\"integer\",\"description\":\"Task creation timestamp\",\"example\":1757169743},\"id\":{\"type\":\"string\",\"description\":\"Task ID\",\"example\":\"task-unified-1757169743-7cvnl5zw\"},\"model\":{\"type\":\"string\",\"description\":\"The model name actually used\",\"example\":\"gemini-omni-1.2-flash-reference-to-video\"},\"object\":{\"type\":\"string\",\"enum\":[\"video.generation.task\"],\"description\":\"The specific type of the task\"},\"progress\":{\"type\":\"integer\",\"description\":\"Task progress percentage (0-100)\",\"minimum\":0,\"maximum\":100,\"example\":0},\"status\":{\"type\":\"string\",\"description\":\"Task status. The create endpoint always returns `processing`; the internal `pending` state is also exposed to clients as `processing`.\",\"enum\":[\"pending\",\"processing\",\"completed\",\"failed\"],\"example\":\"processing\"},\"task_info\":{\"$ref\":\"#/$defs/VideoTaskInfo\",\"description\":\"Detailed video task information\"},\"type\":{\"type\":\"string\",\"enum\":[\"text\",\"image\",\"audio\",\"video\"],\"description\":\"The output type of the task\",\"example\":\"video\"},\"usage\":{\"$ref\":\"#/$defs/Usage\",\"description\":\"Usage and billing information\"}}},\"VideoTaskInfo\":{\"type\":\"object\",\"properties\":{\"estimated_time\":{\"type\":\"integer\",\"description\":\"Estimated completion time (seconds)\",\"minimum\":0,\"example\":60},\"video_duration\":{\"type\":\"integer\",\"description\":\"Output duration in seconds; equals duration.\",\"example\":3}}},\"Usage\":{\"type\":\"object\",\"description\":\"Usage and billing information\",\"properties\":{\"billing_rule\":{\"type\":\"string\",\"description\":\"Billing rule\",\"enum\":[\"per_call\",\"per_token\",\"per_second\"],\"example\":\"per_token\"},\"credits_reserved\":{\"type\":\"number\",\"description\":\"Estimated credits to be consumed\",\"minimum\":0,\"example\":102.34},\"user_group\":{\"type\":\"string\",\"description\":\"Billing group the user belongs to\",\"example\":\"default\"}}}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"example\":{\"prompt\":\"Let the character from the reference image stroll through the reference scene.\",\"image_urls\":[\"https://example.com/character.png\",\"https://example.com/scene.png\"],\"quality\":\"720p\",\"aspect_ratio\":\"16:9\",\"duration\":3}},\"gemini-omni-1.2-flash-text-to-video\":{\"model\":\"gemini-omni-1.2-flash-text-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Gemini Omni 1.2 Flash Text-to-Video\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/gemini-omni-1.2-flash/gemini-omni-1.2-flash-text-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing the subject, action, scene, and camera movement. Write negative requirements directly in the prompt. Supports Chinese and English. For more stable results, describe the desired action and changes clearly. Write negative requirements directly in prompt, such as No dialogue or No text; there is no separate negative prompt parameter. The prompt is required and must not be empty or contain only whitespace.\",\"minLength\":1,\"required\":true},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution; default 720p. Supported values: 360p: landscape 640×360 / portrait 360×640; 720p: landscape 1280×720 / portrait 720×1280; default; 1080p: landscape 1920×1080 / portrait 1080×1920; 4k: landscape 3840×2160 / portrait 2160×3840 Orientation is controlled by aspect_ratio: 16:9 produces landscape and 9:16 produces portrait. Billing: Video output is billed by output tokens, which scale linearly with resolution. Relative to 720p, 360p uses about one third, 1080p about 1.5×, and 4k about 3×. Actual charges are based on generated usage.\",\"enum\":[\"360p\",\"720p\",\"1080p\",\"4k\"],\"default\":\"720p\"},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds; default 3. Accepts any integer from 3 to 15. Duration directly affects billing.\",\"default\":3,\"minimum\":3,\"maximum\":15},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Aspect ratio: 16:9, 9:16, or auto; default auto.\",\"enum\":[\"16:9\",\"9:16\",\"auto\"],\"default\":\"auto\"},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed; random by default.; Range: 0–4294967295.; Fixing the seed reduces variation from parameter changes when tuning prompts and improves reproducibility.\",\"minimum\":0,\"maximum\":4294967295}},\"inputSchema\":{\"schema\":{\"required\":[\"prompt\"],\"type\":\"object\",\"additionalProperties\":false,\"properties\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing the subject, action, scene, and camera movement. Write negative requirements directly in the prompt.\\n\\nSupports Chinese and English. For more stable results, describe the desired action and changes clearly. Write negative requirements directly in `prompt`, such as `No dialogue` or `No text`; there is no separate negative prompt parameter.\\n\\nThe prompt is required and must not be empty or contain only whitespace.\",\"example\":\"A glass marble rolls quickly along a wooden track, then falls into water with a splash.\",\"minLength\":1,\"pattern\":\"\\\\S\"},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution; default `720p`.\\n\\n**Supported values:**\\n- `360p`: landscape 640×360 / portrait 360×640\\n- `720p`: landscape 1280×720 / portrait 720×1280; default\\n- `1080p`: landscape 1920×1080 / portrait 1080×1920\\n- `4k`: landscape 3840×2160 / portrait 2160×3840\\n\\nOrientation is controlled by `aspect_ratio`: `16:9` produces landscape and `9:16` produces portrait.\\n\\n**Billing:** Video output is billed by output tokens, which scale linearly with resolution. Relative to `720p`, `360p` uses about one third, `1080p` about 1.5×, and `4k` about 3×. Actual charges are based on generated usage.\",\"enum\":[\"360p\",\"720p\",\"1080p\",\"4k\"],\"default\":\"720p\",\"example\":\"720p\"},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds; default `3`. Accepts any integer from `3` to `15`. Duration directly affects billing.\",\"minimum\":3,\"maximum\":15,\"default\":3,\"example\":3},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Aspect ratio: 16:9, 9:16, or auto; default auto.\",\"enum\":[\"16:9\",\"9:16\",\"auto\"],\"default\":\"auto\",\"example\":\"auto\"},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed; random by default.\\n\\n- Range: `0`–`4294967295`.\\n- Fixing the seed reduces variation from parameter changes when tuning prompts and improves reproducibility.\",\"minimum\":0,\"maximum\":4294967295,\"example\":42}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"responseSchema\":{\"schema\":{\"$ref\":\"#/$defs/VideoGenerationResponse\",\"$defs\":{\"VideoGenerationResponse\":{\"type\":\"object\",\"properties\":{\"created\":{\"type\":\"integer\",\"description\":\"Task creation timestamp\",\"example\":1757169743},\"id\":{\"type\":\"string\",\"description\":\"Task ID\",\"example\":\"task-unified-1757169743-7cvnl5zw\"},\"model\":{\"type\":\"string\",\"description\":\"The model name actually used\",\"example\":\"gemini-omni-1.2-flash-text-to-video\"},\"object\":{\"type\":\"string\",\"enum\":[\"video.generation.task\"],\"description\":\"The specific type of the task\"},\"progress\":{\"type\":\"integer\",\"description\":\"Task progress percentage (0-100)\",\"minimum\":0,\"maximum\":100,\"example\":0},\"status\":{\"type\":\"string\",\"description\":\"Task status. The create endpoint always returns `processing`; the internal `pending` state is also exposed to clients as `processing`.\",\"enum\":[\"pending\",\"processing\",\"completed\",\"failed\"],\"example\":\"processing\"},\"task_info\":{\"$ref\":\"#/$defs/VideoTaskInfo\",\"description\":\"Detailed video task information\"},\"type\":{\"type\":\"string\",\"enum\":[\"text\",\"image\",\"audio\",\"video\"],\"description\":\"The output type of the task\",\"example\":\"video\"},\"usage\":{\"$ref\":\"#/$defs/Usage\",\"description\":\"Usage and billing information\"}}},\"VideoTaskInfo\":{\"type\":\"object\",\"properties\":{\"estimated_time\":{\"type\":\"integer\",\"description\":\"Estimated completion time (seconds)\",\"minimum\":0,\"example\":60},\"video_duration\":{\"type\":\"integer\",\"description\":\"Output duration in seconds; equals duration.\",\"example\":3}}},\"Usage\":{\"type\":\"object\",\"description\":\"Usage and billing information\",\"properties\":{\"billing_rule\":{\"type\":\"string\",\"description\":\"Billing rule\",\"enum\":[\"per_call\",\"per_token\",\"per_second\"],\"example\":\"per_token\"},\"credits_reserved\":{\"type\":\"number\",\"description\":\"Estimated credits to be consumed\",\"minimum\":0,\"example\":102.34},\"user_group\":{\"type\":\"string\",\"description\":\"Billing group the user belongs to\",\"example\":\"default\"}}}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"example\":{\"prompt\":\"A glass marble rolls quickly along a wooden track, then falls into water with a splash.\",\"quality\":\"1080p\",\"aspect_ratio\":\"16:9\",\"duration\":3}},\"gemini-omni-1.2-flash-video-edit\":{\"model\":\"gemini-omni-1.2-flash-video-edit\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Gemini Omni 1.2 Flash Video Edit\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/gemini-omni-1.2-flash/gemini-omni-1.2-flash-video-edit\",\"required\":[\"prompt\",\"video_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text instruction describing the desired edit and what should remain unchanged. Supports Chinese and English. For more stable results, describe the desired action and changes clearly. Write negative requirements directly in prompt, such as No dialogue or No text; there is no separate negative prompt parameter. The prompt is required and must not be empty or contain only whitespace.\",\"minLength\":1,\"required\":true},\"video_urls\":{\"type\":\"array\",\"description\":\"Video array to edit; exactly 1 video.; HTTP/HTTPS video URLs only.; Format: mp4.; Duration: up to 15 seconds, with no lower limit; short 1–2 second videos are also accepted.\",\"minItems\":1,\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Optional reference image array, up to 10 images. It may be used with the input video to constrain subjects, style, or elements. Input requirements: HTTP/HTTPS image URLs only; Supported formats: png, jpeg, webp Billing: Every reference image contributes input tokens.\",\"minItems\":1,\"maxItems\":10,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"quality\":{\"type\":\"string\",\"description\":\"Output video resolution; default auto.; 360p: short edge 360.; 720p: short edge 720.; 1080p: short edge 1080.; 4k: short edge 2160.; auto: follows the input resolution; this is the default. Choosing an explicit value can raise or lower output resolution. Billing: Output video tokens increase with output resolution. Input video also contributes tokens; higher resolution costs more.\",\"enum\":[\"360p\",\"720p\",\"1080p\",\"4k\",\"auto\"],\"default\":\"auto\"},\"duration\":{\"type\":\"string\",\"description\":\"Only auto is accepted and it is the default. Output duration follows the input video.\",\"enum\":[\"auto\"],\"default\":\"auto\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Only auto is accepted and it is the default. Output aspect ratio follows the input video.\",\"enum\":[\"auto\"],\"default\":\"auto\"},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed; random by default.; Range: 0–4294967295.; Fixing the seed reduces variation from parameter changes when tuning prompts and improves reproducibility.\",\"minimum\":0,\"maximum\":4294967295}},\"inputSchema\":{\"schema\":{\"required\":[\"prompt\",\"video_urls\"],\"type\":\"object\",\"additionalProperties\":false,\"properties\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text instruction describing the desired edit and what should remain unchanged.\\n\\nSupports Chinese and English. For more stable results, describe the desired action and changes clearly. Write negative requirements directly in `prompt`, such as `No dialogue` or `No text`; there is no separate negative prompt parameter.\\n\\nThe prompt is required and must not be empty or contain only whitespace.\",\"example\":\"Make the lighting warmer while keeping everything else unchanged.\",\"minLength\":1,\"pattern\":\"\\\\S\"},\"video_urls\":{\"type\":\"array\",\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"minItems\":1,\"maxItems\":1,\"description\":\"Video array to edit; exactly 1 video.\\n\\n- HTTP/HTTPS video URLs only.\\n- Format: mp4.\\n- Duration: up to `15` seconds, with no lower limit; short 1–2 second videos are also accepted.\",\"example\":[\"https://example.com/source.mp4\"]},\"image_urls\":{\"type\":\"array\",\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"minItems\":1,\"maxItems\":10,\"description\":\"Optional reference image array, up to 10 images. It may be used with the input video to constrain subjects, style, or elements.\\n\\n**Input requirements:**\\n- HTTP/HTTPS image URLs only\\n- Supported formats: `png`, `jpeg`, `webp`\\n\\n**Billing:** Every reference image contributes input tokens.\",\"example\":[\"https://example.com/reference.png\"]},\"quality\":{\"type\":\"string\",\"description\":\"Output video resolution; default `auto`.\\n\\n- `360p`: short edge 360.\\n- `720p`: short edge 720.\\n- `1080p`: short edge 1080.\\n- `4k`: short edge 2160.\\n- `auto`: follows the input resolution; this is the default.\\n\\nChoosing an explicit value can raise or lower output resolution.\\n\\n**Billing:** Output video tokens increase with output resolution. Input video also contributes tokens; higher resolution costs more.\",\"enum\":[\"360p\",\"720p\",\"1080p\",\"4k\",\"auto\"],\"default\":\"auto\",\"example\":\"auto\"},\"duration\":{\"type\":\"string\",\"description\":\"Only auto is accepted and it is the default. Output duration follows the input video.\",\"enum\":[\"auto\"],\"default\":\"auto\",\"example\":\"auto\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Only auto is accepted and it is the default. Output aspect ratio follows the input video.\",\"enum\":[\"auto\"],\"default\":\"auto\",\"example\":\"auto\"},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed; random by default.\\n\\n- Range: `0`–`4294967295`.\\n- Fixing the seed reduces variation from parameter changes when tuning prompts and improves reproducibility.\",\"minimum\":0,\"maximum\":4294967295,\"example\":42}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"responseSchema\":{\"schema\":{\"$ref\":\"#/$defs/VideoGenerationResponse\",\"$defs\":{\"VideoGenerationResponse\":{\"type\":\"object\",\"properties\":{\"created\":{\"type\":\"integer\",\"description\":\"Task creation timestamp\",\"example\":1757169743},\"id\":{\"type\":\"string\",\"description\":\"Task ID\",\"example\":\"task-unified-1757169743-7cvnl5zw\"},\"model\":{\"type\":\"string\",\"description\":\"The model name actually used\",\"example\":\"gemini-omni-1.2-flash-video-edit\"},\"object\":{\"type\":\"string\",\"enum\":[\"video.generation.task\"],\"description\":\"The specific type of the task\"},\"progress\":{\"type\":\"integer\",\"description\":\"Task progress percentage (0-100)\",\"minimum\":0,\"maximum\":100,\"example\":0},\"status\":{\"type\":\"string\",\"description\":\"Task status. The create endpoint always returns `processing`; the internal `pending` state is also exposed to clients as `processing`.\",\"enum\":[\"pending\",\"processing\",\"completed\",\"failed\"],\"example\":\"processing\"},\"task_info\":{\"$ref\":\"#/$defs/VideoTaskInfo\",\"description\":\"Detailed video task information\"},\"type\":{\"type\":\"string\",\"enum\":[\"text\",\"image\",\"audio\",\"video\"],\"description\":\"The output type of the task\",\"example\":\"video\"},\"usage\":{\"$ref\":\"#/$defs/Usage\",\"description\":\"Usage and billing information\"}}},\"VideoTaskInfo\":{\"type\":\"object\",\"properties\":{\"estimated_time\":{\"type\":\"integer\",\"description\":\"Estimated completion time (seconds)\",\"minimum\":0,\"example\":60},\"video_duration\":{\"type\":\"integer\",\"description\":\"Output duration follows the input video and returns the probed input duration.\",\"example\":5}}},\"Usage\":{\"type\":\"object\",\"description\":\"Usage and billing information\",\"properties\":{\"billing_rule\":{\"type\":\"string\",\"description\":\"Billing rule\",\"enum\":[\"per_call\",\"per_token\",\"per_second\"],\"example\":\"per_token\"},\"credits_reserved\":{\"type\":\"number\",\"description\":\"Estimated credits to be consumed\",\"minimum\":0,\"example\":102.34},\"user_group\":{\"type\":\"string\",\"description\":\"Billing group the user belongs to\",\"example\":\"default\"}}}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"example\":{\"prompt\":\"Make the lighting warmer while keeping everything else unchanged.\",\"video_urls\":[\"https://example.com/source.mp4\"],\"quality\":\"auto\",\"duration\":\"auto\",\"aspect_ratio\":\"auto\"}},\"gemini-omni-1.2-flash-video-extend\":{\"model\":\"gemini-omni-1.2-flash-video-extend\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Gemini Omni 1.2 Flash Video Extend\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/gemini-omni-1.2-flash/gemini-omni-1.2-flash-video-extend\",\"required\":[\"prompt\",\"video_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing what should happen after the input video ends. Supports Chinese and English. For more stable results, describe the desired action and changes clearly. Write negative requirements directly in prompt, such as No dialogue or No text; there is no separate negative prompt parameter. The prompt is required and must not be empty or contain only whitespace.\",\"minLength\":1,\"required\":true},\"video_urls\":{\"type\":\"array\",\"description\":\"Exactly one directly reachable HTTP/HTTPS MP4, no longer than 30 seconds.\",\"minItems\":1,\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Optional reference image array, up to 10 images. It may be used with the video being extended to constrain subjects, style, or elements. Input requirements: HTTP/HTTPS image URLs only; Supported formats: png, jpeg, webp Billing: Every reference image contributes input tokens.\",\"minItems\":1,\"maxItems\":10,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"duration\":{\"type\":\"integer\",\"description\":\"Appended video duration in seconds; default 3. Notes: Accepts any integer from 3 to 10; Specifies how many seconds are generated after the input video, not the total output duration; Total output duration = input video duration + duration; Appended duration directly affects billing\",\"default\":3,\"minimum\":3,\"maximum\":10},\"quality\":{\"type\":\"string\",\"description\":\"Output video resolution; default auto.; 360p: short edge 360.; 720p: short edge 720.; 1080p: short edge 1080.; 4k: short edge 2160.; auto: follows the input resolution; this is the default. Choosing an explicit value can raise or lower output resolution. Billing: Output video tokens increase with output resolution. Input video also contributes tokens; higher resolution costs more.\",\"enum\":[\"360p\",\"720p\",\"1080p\",\"4k\",\"auto\"],\"default\":\"auto\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Only auto is accepted and it is the default. Output aspect ratio follows the input video.\",\"enum\":[\"auto\"],\"default\":\"auto\"},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed; random by default.; Range: 0–4294967295.; Fixing the seed reduces variation from parameter changes when tuning prompts and improves reproducibility.\",\"minimum\":0,\"maximum\":4294967295}},\"inputSchema\":{\"schema\":{\"required\":[\"prompt\",\"video_urls\"],\"type\":\"object\",\"additionalProperties\":false,\"properties\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing what should happen after the input video ends.\\n\\nSupports Chinese and English. For more stable results, describe the desired action and changes clearly. Write negative requirements directly in `prompt`, such as `No dialogue` or `No text`; there is no separate negative prompt parameter.\\n\\nThe prompt is required and must not be empty or contain only whitespace.\",\"example\":\"The person continues walking forward and slowly exits the frame.\",\"minLength\":1,\"pattern\":\"\\\\S\"},\"video_urls\":{\"type\":\"array\",\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"minItems\":1,\"maxItems\":1,\"description\":\"Exactly one directly reachable HTTP/HTTPS MP4, no longer than 30 seconds.\",\"example\":[\"https://example.com/source.mp4\"]},\"image_urls\":{\"type\":\"array\",\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"minItems\":1,\"maxItems\":10,\"description\":\"Optional reference image array, up to 10 images. It may be used with the video being extended to constrain subjects, style, or elements.\\n\\n**Input requirements:**\\n- HTTP/HTTPS image URLs only\\n- Supported formats: `png`, `jpeg`, `webp`\\n\\n**Billing:** Every reference image contributes input tokens.\",\"example\":[\"https://example.com/reference.png\"]},\"duration\":{\"type\":\"integer\",\"description\":\"Appended video duration in seconds; default `3`.\\n\\n**Notes:**\\n- Accepts any integer from `3` to `10`\\n- Specifies how many seconds are generated after the input video, not the total output duration\\n- Total output duration = input video duration + `duration`\\n- Appended duration directly affects billing\",\"minimum\":3,\"maximum\":10,\"default\":3,\"example\":3},\"quality\":{\"type\":\"string\",\"description\":\"Output video resolution; default `auto`.\\n\\n- `360p`: short edge 360.\\n- `720p`: short edge 720.\\n- `1080p`: short edge 1080.\\n- `4k`: short edge 2160.\\n- `auto`: follows the input resolution; this is the default.\\n\\nChoosing an explicit value can raise or lower output resolution.\\n\\n**Billing:** Output video tokens increase with output resolution. Input video also contributes tokens; higher resolution costs more.\",\"enum\":[\"360p\",\"720p\",\"1080p\",\"4k\",\"auto\"],\"default\":\"auto\",\"example\":\"auto\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Only auto is accepted and it is the default. Output aspect ratio follows the input video.\",\"enum\":[\"auto\"],\"default\":\"auto\",\"example\":\"auto\"},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed; random by default.\\n\\n- Range: `0`–`4294967295`.\\n- Fixing the seed reduces variation from parameter changes when tuning prompts and improves reproducibility.\",\"minimum\":0,\"maximum\":4294967295,\"example\":42}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"responseSchema\":{\"schema\":{\"$ref\":\"#/$defs/VideoGenerationResponse\",\"$defs\":{\"VideoGenerationResponse\":{\"type\":\"object\",\"properties\":{\"created\":{\"type\":\"integer\",\"description\":\"Task creation timestamp\",\"example\":1757169743},\"id\":{\"type\":\"string\",\"description\":\"Task ID\",\"example\":\"task-unified-1757169743-7cvnl5zw\"},\"model\":{\"type\":\"string\",\"description\":\"The model name actually used\",\"example\":\"gemini-omni-1.2-flash-video-extend\"},\"object\":{\"type\":\"string\",\"enum\":[\"video.generation.task\"],\"description\":\"The specific type of the task\"},\"progress\":{\"type\":\"integer\",\"description\":\"Task progress percentage (0-100)\",\"minimum\":0,\"maximum\":100,\"example\":0},\"status\":{\"type\":\"string\",\"description\":\"Task status. The create endpoint always returns `processing`; the internal `pending` state is also exposed to clients as `processing`.\",\"enum\":[\"pending\",\"processing\",\"completed\",\"failed\"],\"example\":\"processing\"},\"task_info\":{\"$ref\":\"#/$defs/VideoTaskInfo\",\"description\":\"Detailed video task information\"},\"type\":{\"type\":\"string\",\"enum\":[\"text\",\"image\",\"audio\",\"video\"],\"description\":\"The output type of the task\",\"example\":\"video\"},\"usage\":{\"$ref\":\"#/$defs/Usage\",\"description\":\"Usage and billing information\"}}},\"VideoTaskInfo\":{\"type\":\"object\",\"properties\":{\"estimated_time\":{\"type\":\"integer\",\"description\":\"Estimated completion time (seconds)\",\"minimum\":0,\"example\":60},\"video_duration\":{\"type\":\"integer\",\"description\":\"Total output duration: input duration plus appended duration.\",\"example\":6}}},\"Usage\":{\"type\":\"object\",\"description\":\"Usage and billing information\",\"properties\":{\"billing_rule\":{\"type\":\"string\",\"description\":\"Billing rule\",\"enum\":[\"per_call\",\"per_token\",\"per_second\"],\"example\":\"per_token\"},\"credits_reserved\":{\"type\":\"number\",\"description\":\"Estimated credits to be consumed\",\"minimum\":0,\"example\":102.34},\"user_group\":{\"type\":\"string\",\"description\":\"Billing group the user belongs to\",\"example\":\"default\"}}}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"example\":{\"prompt\":\"The person continues walking forward and slowly exits the frame.\",\"video_urls\":[\"https://example.com/source.mp4\"],\"duration\":3,\"quality\":\"auto\",\"aspect_ratio\":\"auto\"}},\"gemini-omni-1.2-flash-video-upscale\":{\"model\":\"gemini-omni-1.2-flash-video-upscale\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"gemini-omni-1.2-flash-video-upscale API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/gemini-omni-1.2-flash/gemini-omni-1.2-flash-video-upscale\",\"required\":[\"video_urls\",\"quality\"],\"params\":{\"video_urls\":{\"type\":\"array\",\"description\":\"Video array to upscale; required, exactly 1 video.; HTTP/HTTPS video URLs only.; Format: mp4.; Duration: up to 15 seconds.; Sizes: 640×360, 1280×720, 1920×1080, or portrait 360×640, 720×1280, 1080×1920 only.\",\"minItems\":1,\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"quality\":{\"type\":\"string\",\"description\":\"Target resolution; required and must exceed the input resolution.; 360p input: 720p, 1080p.; 720p input: 1080p, 4k.; 1080p input: 4k. Billing: Billed by actual video output token usage, with no input or thinking token charges. Output token usage depends on the input video duration and the input/target resolution combination. The charge at submission is an estimate; final billing uses actual usage.\",\"enum\":[\"720p\",\"1080p\",\"4k\"],\"required\":true},\"duration\":{\"type\":\"string\",\"description\":\"May be omitted; if supplied, only auto is supported. Output duration follows the input video. A duration in seconds cannot be specified.\",\"enum\":[\"auto\"],\"default\":\"auto\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"May be omitted; if supplied, only auto is supported. Output aspect ratio follows the input video. Other aspect ratios cannot be specified.\",\"enum\":[\"auto\"],\"default\":\"auto\"},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed; random by default. Range: 0–4294967295. A fixed seed improves reproducibility.\",\"minimum\":0,\"maximum\":4294967295}},\"inputSchema\":{\"schema\":{\"required\":[\"video_urls\",\"quality\"],\"type\":\"object\",\"additionalProperties\":false,\"properties\":{\"video_urls\":{\"type\":\"array\",\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"minItems\":1,\"maxItems\":1,\"description\":\"Video array to upscale; required, exactly 1 video.\\n\\n- HTTP/HTTPS video URLs only.\\n- Format: mp4.\\n- Duration: up to `15` seconds.\\n- Sizes: `640×360`, `1280×720`, `1920×1080`, or portrait `360×640`, `720×1280`, `1080×1920` only.\",\"example\":[\"https://example.com/source-720p.mp4\"]},\"quality\":{\"type\":\"string\",\"description\":\"Target resolution; required and must exceed the input resolution.\\n\\n- 360p input: `720p`, `1080p`.\\n- 720p input: `1080p`, `4k`.\\n- 1080p input: `4k`.\\n\\n**Billing:** Billed by actual video output token usage, with no input or thinking token charges. Output token usage depends on the input video duration and the input/target resolution combination. The charge at submission is an estimate; final billing uses actual usage.\",\"enum\":[\"720p\",\"1080p\",\"4k\"],\"example\":\"1080p\"},\"duration\":{\"type\":\"string\",\"description\":\"May be omitted; if supplied, only `auto` is supported. Output duration follows the input video. A duration in seconds cannot be specified.\",\"enum\":[\"auto\"],\"default\":\"auto\",\"example\":\"auto\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"May be omitted; if supplied, only `auto` is supported. Output aspect ratio follows the input video. Other aspect ratios cannot be specified.\",\"enum\":[\"auto\"],\"default\":\"auto\",\"example\":\"auto\"},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed; random by default. Range: `0`–`4294967295`. A fixed seed improves reproducibility.\",\"minimum\":0,\"maximum\":4294967295,\"example\":42}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"responseSchema\":{\"schema\":{\"$ref\":\"#/$defs/VideoGenerationResponse\",\"$defs\":{\"VideoGenerationResponse\":{\"type\":\"object\",\"properties\":{\"created\":{\"type\":\"integer\",\"description\":\"Task creation timestamp\",\"example\":1757169743},\"id\":{\"type\":\"string\",\"description\":\"Task ID\",\"example\":\"task-unified-1757169743-7cvnl5zw\"},\"model\":{\"type\":\"string\",\"description\":\"The model name actually used\",\"example\":\"gemini-omni-1.2-flash-video-upscale\"},\"object\":{\"type\":\"string\",\"enum\":[\"video.generation.task\"],\"description\":\"The specific type of the task\"},\"progress\":{\"type\":\"integer\",\"description\":\"Task progress percentage (0-100)\",\"minimum\":0,\"maximum\":100,\"example\":0},\"status\":{\"type\":\"string\",\"description\":\"Task status. The create endpoint always returns `processing`; the internal `pending` state is also exposed to clients as `processing`.\",\"enum\":[\"pending\",\"processing\",\"completed\",\"failed\"],\"example\":\"processing\"},\"task_info\":{\"$ref\":\"#/$defs/VideoTaskInfo\",\"description\":\"Detailed video task information\"},\"type\":{\"type\":\"string\",\"enum\":[\"text\",\"image\",\"audio\",\"video\"],\"description\":\"The output type of the task\",\"example\":\"video\"},\"usage\":{\"$ref\":\"#/$defs/Usage\",\"description\":\"Usage and billing information\"}}},\"VideoTaskInfo\":{\"type\":\"object\",\"properties\":{\"estimated_time\":{\"type\":\"integer\",\"description\":\"Estimated completion time (seconds)\",\"minimum\":0,\"example\":60},\"video_duration\":{\"type\":\"integer\",\"description\":\"Output video duration in seconds, equal to the input duration. Reports the input duration detected by the system.\",\"example\":5}}},\"Usage\":{\"type\":\"object\",\"description\":\"Usage and billing information\",\"properties\":{\"billing_rule\":{\"type\":\"string\",\"description\":\"Billing rule\",\"enum\":[\"per_call\",\"per_token\",\"per_second\"],\"example\":\"per_token\"},\"credits_reserved\":{\"type\":\"number\",\"description\":\"Estimated credits to be consumed\",\"minimum\":0,\"example\":102.34},\"user_group\":{\"type\":\"string\",\"description\":\"Billing group the user belongs to\",\"example\":\"default\"}}}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"example\":{\"video_urls\":[\"https://example.com/source-720p.mp4\"],\"quality\":\"1080p\"}},\"gpt-image-2.6-flare\":{\"model\":\"gpt-image-2.6-flare\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"gpt-image-2.6 API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/gpt-image-2.6/gpt-image-2.6-image-generation\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the image to generate or how to edit the input image Length limits (both must be met): Up to 32,000 characters (counted as Unicode code points); The prompt text itself must not exceed 60,000 bytes when encoded in UTF-8 Different characters use different numbers of UTF-8 bytes. Use the actual encoded byte count. If either limit is exceeded, shorten the prompt before resubmitting. Recommendation: If the prompt exceeds 8000 tokens, the generated image may not match expectations; shortening the prompt is recommended.\",\"maxLength\":32000,\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference images as public URLs, for image-to-image and image editing Note: Number of input images per request: 1~16; Size of a single image: not exceeding 50MB; Pixels of a single image: width × height not exceeding 178,956,970 px; Side length of a single image: width / height each not exceeding 23170 px; exceeding this may cause errors; Supported file formats: .jpeg, .jpg, .png, .webp; Image URLs must be directly accessible by the server, or the image URL should directly download when accessed (typically these URLs end with image file extensions, such as .png, .jpg); In image-to-image / ima…\",\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"mask_url\":{\"type\":\"string\",\"description\":\"Inpainting mask URL — marks the region of the reference image to regenerate. Only valid in image edit mode (must be combined with image_urls); the mask is silently ignored in pure text-to-image requests. Format requirements: Must be a PNG with an alpha channel: transparent pixels (alpha < 255) = regions to regenerate; opaque pixels = preserved; Mask dimensions must exactly match the reference image dimensions (width × height in pixels); Single mask per request Note: At least one reference image is required in image_urls; a mask sent alone has no effect; Cannot be combined with markup_url; Com…\",\"format\":\"uri\"},\"markup_url\":{\"type\":\"string\",\"description\":\"Public URL of a markup layer. Use circles, arrows or freehand marks to indicate what to change in the reference image, and describe the changes in prompt. Only valid in image editing mode (requires image_urls). Format requirements: Must be a PNG with transparent pixels: draw only the annotations and leave the rest transparent. Do not draw directly on the original image; Dimensions must exactly match the first reference image (width × height in pixels); The first reference image and the markup layer must each have width × height ≤ 16,777,216 px; File size: no more than 50MB Note: Markup applie…\",\"format\":\"uri\"},\"size\":{\"type\":\"string\",\"description\":\"Generated image dimensions. Defaults to auto. Standard images use the following rules; GIF uses the separate rules in section ④. ① Standard images: ratio format (15 options); 1:1: Square; 1:2 / 2:1: Extreme portrait / landscape; 1:3 / 3:1: Ultra portrait / landscape (3:1 limit); 2:3 / 3:2: Standard portrait / landscape; 3:4 / 4:3: Classic portrait / landscape; 4:5 / 5:4: Common social media; 9:16 / 16:9: Mobile / desktop widescreen; 9:21 / 21:9: Ultra-wide ② Standard images: explicit pixel format: WxH (or W×H), e.g. 1024x1024, 1536x1024, 3840×2160; Both width and height must be multiples of 1…\",\"default\":\"auto\"},\"resolution\":{\"type\":\"string\",\"description\":\"Resolution tier shortcut, only effective when size is a ratio; ignored in explicit pixel mode and for GIF output Pixel budget rules (dimensions are derived from the target pixel count and the size ratio, aligned to multiples of 16): 1K: ~1 MP (1024² = 1,048,576 pixels); 2K: ~4 MP (2048² = 4,194,304 pixels); 4K: ~8.29 MP (3840×2160 = 8,294,400 pixels, the maximum) Landscape / square output dimensions (portrait dimensions are the landscape width/height swapped, e.g. 2:3 = 3:2 reversed): | Ratio | 1K | 2K | 4K | |---|---|---|---| | 1:1 | 1024×1024 | 2048×2048 | 2880×2880 | | 2:1 | 1456×720 | 289…\",\"enum\":[\"1K\",\"2K\",\"4K\"],\"default\":\"1K\"},\"quality\":{\"type\":\"string\",\"description\":\"Rendering quality, which directly affects output token count and cost. Defaults to medium | Value | Output tokens (1024²) | Relative image output cost (1024²) | |---|---|---| | low | 824 | ~0.57× | | medium | 1,449 | 1.0× | | high | 1,756 | ~1.21× | | xhigh | 3,122 | ~2.15× | | max | 7,024 | ~4.85× | Note: This table compares image output costs only, excluding input costs; Calculated for 1024×1024; output tokens vary with total pixels and aspect ratio. Use the returned usage for actual consumption; For GIF output, tokens are calculated for the combined image containing all frames; Use low for…\",\"enum\":[\"low\",\"medium\",\"high\",\"xhigh\",\"max\"],\"default\":\"medium\"},\"complexity\":{\"type\":\"string\",\"description\":\"Planning depth before image generation, independent of quality. Defaults to high; low: Suitable for local changes such as replacing a background or changing sign text; medium: Balanced; high: Suitable for text-heavy images, complex layouts or complex relationships between objects Note: Higher levels take longer and may introduce unwanted changes; compare results for your task; Changing complexity does not incur an additional charge; Can also be supplied as model_params.complexity; the top-level value takes precedence when both are present\",\"enum\":[\"low\",\"medium\",\"high\"],\"default\":\"high\"},\"background\":{\"type\":\"string\",\"description\":\"Alpha channel of the output image. Defaults to opaque; opaque: Flat background, no alpha channel; transparent: Keeps the alpha channel Note: transparent is a Preview feature and results may be unstable; When using transparent, output_format must be png or webp; When output_format is gif, only opaque is supported\",\"enum\":[\"opaque\",\"transparent\"],\"default\":\"opaque\"},\"output_format\":{\"type\":\"string\",\"description\":\"Output file format. Defaults to png; png: Lossless, supports transparent backgrounds; jpeg: Lossy compression with smaller files; webp: Balances file size and quality; also supports transparency; gif: Animated GIF; see model_params for frame count and frame duration Note: When background is transparent, only png or webp is allowed; gif supports both text-to-image and image editing; For gif, n must be 1\",\"enum\":[\"png\",\"jpeg\",\"webp\",\"gif\"],\"default\":\"png\"},\"n\":{\"type\":\"integer\",\"description\":\"Number of images to generate, each billed independently Note: Text input tokens scale linearly with n; Support for n > 1 is currently unreliable: even with a value greater than 1, only one image is often returned. The actual count is whatever results holds in the response, and billing follows the returned usage. If you need several images, send multiple single-image requests instead; When output_format is gif, this must be 1\",\"default\":1,\"minimum\":1,\"maximum\":10},\"model_params\":{\"type\":\"object\",\"description\":\"Model-specific parameters. GIF frame parameters must be supplied in this object.; frame_count and frame_duration_ms are only allowed with output_format=gif; Parameters incompatible with the output format return HTTP 400; they are not silently ignored\",\"properties\":{\"frame_count\":{\"type\":\"integer\",\"description\":\"Number of GIF frames. Only available when output_format is gif. Defaults to 9. All frames are generated together as one combined image. Explicit frame width and height must be positive multiples of 16; individual frames are not subject to the minimum pixel count for standard images. Edge lengths below are in pixels. | Frames | Per-frame limits | Example size | |---|---|---| | 2~8 | ≤ 1,036,800 pixels; one edge ≤ 960, the other ≤ 1920 | 960x1072 | | 9 | ≤ 921,600 pixels; both edges ≤ 1280 | 1280x720 | | 10~12 | ≤ 691,200 pixels; one edge ≤ 1280, the other ≤ 960 | 960x720 | | 13~16 | ≤ 518,400…\",\"default\":9,\"minimum\":2,\"maximum\":16},\"frame_duration_ms\":{\"type\":\"integer\",\"description\":\"Duration of each GIF frame in milliseconds. Only available when output_format is gif. Defaults to 200, rounded to 10-millisecond increments\",\"default\":200,\"minimum\":20,\"maximum\":2000}}}},\"inputSchema\":{\"schema\":{\"type\":\"object\",\"required\":[\"prompt\"],\"properties\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the image to generate or how to edit the input image\\n\\n**Length limits (both must be met):**\\n- Up to `32,000` characters (counted as Unicode code points)\\n- The `prompt` text itself must not exceed `60,000` bytes when encoded in UTF-8\\n\\nDifferent characters use different numbers of UTF-8 bytes. Use the actual encoded byte count.\\n\\nIf either limit is exceeded, shorten the prompt before resubmitting.\\n\\n**Recommendation:** If the prompt exceeds `8000` tokens, the generated image may not match expectations; shortening the prompt is recommended.\",\"example\":\"A beautiful colorful sunset over the ocean\",\"maxLength\":32000},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference images as public URLs, for image-to-image and image editing\\n\\n**Note:**\\n- Number of input images per request: `1~16`\\n- Size of a single image: not exceeding `50MB`\\n- Pixels of a single image: width × height not exceeding `178,956,970` px\\n- Side length of a single image: width / height each not exceeding `23170` px; exceeding this may cause errors\\n- Supported file formats: `.jpeg`, `.jpg`, `.png`, `.webp`\\n- Image URLs must be directly accessible by the server, or the image URL should directly download when accessed (typically these URLs end with image file extensions, such as `.png`, `.jpg`)\\n- In image-to-image / image editing scenarios, the reference images themselves also incur additional image input token consumption\\n- With `markup_url`, markup applies to the first image and the others serve as references; the first image must have width × height ≤ `16,777,216` px\",\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"example\":[\"https://example.com/image1.png\",\"https://example.com/image2.png\"]},\"mask_url\":{\"type\":\"string\",\"format\":\"uri\",\"description\":\"Inpainting mask URL — marks the region of the reference image to regenerate. **Only valid in image edit mode** (must be combined with `image_urls`); the mask is silently ignored in pure text-to-image requests.\\n\\n**Format requirements:**\\n- **Must be a PNG with an alpha channel**: transparent pixels (`alpha < 255`) = regions to regenerate; opaque pixels = preserved\\n- **Mask dimensions must exactly match the reference image dimensions** (width × height in pixels)\\n- Single mask per request\\n\\n**Note:**\\n- At least one reference image is required in `image_urls`; a mask sent alone has no effect\\n- Cannot be combined with `markup_url`\\n- Common errors:\\n - `Invalid mask image format - mask image missing alpha channel`: the uploaded image has no alpha channel (JPEG, opaque PNG, etc.). Re-export the mask as a PNG with transparent regions.\\n - `Invalid mask image format - mask size does not match image size`: the mask dimensions don't match the reference image. Resize the mask to the same pixel dimensions as your reference image.\",\"example\":\"https://example.com/mask.png\"},\"markup_url\":{\"type\":\"string\",\"format\":\"uri\",\"description\":\"Public URL of a markup layer. Use circles, arrows or freehand marks to indicate what to change in the reference image, and describe the changes in `prompt`. **Only valid in image editing mode** (requires `image_urls`).\\n\\n**Format requirements:**\\n- **Must be a PNG with transparent pixels**: draw only the annotations and leave the rest transparent. Do not draw directly on the original image\\n- **Dimensions must exactly match the first reference image** (width × height in pixels)\\n- The first reference image and the markup layer must each have width × height ≤ `16,777,216` px\\n- File size: no more than `50MB`\\n\\n**Note:**\\n- Markup applies to the first image in `image_urls`; the remaining images serve as references\\n- Cannot be combined with `mask_url`\\n- Supports standard image and GIF editing\\n- Can also be supplied as `model_params.markup_url`; the top-level value takes precedence when both are present\\n- In `prompt`, also specify what to preserve, for example, \\\"keep everything else unchanged and remove the red circle\\\"\",\"example\":\"https://example.com/markup.png\"},\"size\":{\"type\":\"string\",\"description\":\"Generated image dimensions. Defaults to `auto`. Standard images use the following rules; GIF uses the separate rules in section ④.\\n\\n**① Standard images: ratio format (15 options)**\\n\\n- `1:1`: Square\\n- `1:2` / `2:1`: Extreme portrait / landscape\\n- `1:3` / `3:1`: Ultra portrait / landscape (3:1 limit)\\n- `2:3` / `3:2`: Standard portrait / landscape\\n- `3:4` / `4:3`: Classic portrait / landscape\\n- `4:5` / `5:4`: Common social media\\n- `9:16` / `16:9`: Mobile / desktop widescreen\\n- `9:21` / `21:9`: Ultra-wide\\n\\n**② Standard images: explicit pixel format**: `WxH` (or `W×H`), e.g. `1024x1024`, `1536x1024`, `3840×2160`\\n\\n- Both width and height must be multiples of `16`\\n- Each edge range: `[16, 3840]`\\n- Pixel budget: `655,360 ≤ width × height ≤ 8,294,400` (about 0.65 MP ~ 8.29 MP)\\n- Aspect ratio: `≤ 3:1`\\n\\n**③ Standard images: `auto`**: The model decides the size automatically (`resolution` does not apply in this mode)\\n\\n**④ GIF output**: `size` specifies the dimensions of each frame. Only `auto` and explicit pixel dimensions are supported, not ratios.\\n\\n- With `auto`, each frame is `512×512`\\n- Explicit frame width and height must be positive multiples of `16`\\n- The `655,360` minimum pixel count for standard images does not apply to individual GIF frames; for example, `512x512` is valid\\n- The image combining all frames must satisfy the edge, total pixel and aspect ratio limits; see `model_params.frame_count` for grid layouts and per-frame limits\\n- `resolution` does not apply\\n\\n**Out-of-range handling:**\\n- For standard images, a ratio + `resolution` combination that exceeds the budget is automatically scaled down proportionally (e.g. 4K 2:1 → 3840×1920)\\n- Explicit GIF frame dimensions that exceed the limits return HTTP 400 and are not automatically scaled down\",\"default\":\"auto\",\"example\":\"auto\"},\"resolution\":{\"type\":\"string\",\"description\":\"Resolution tier shortcut, only effective when `size` is a ratio; ignored in explicit pixel mode and for GIF output\\n\\n**Pixel budget rules** (dimensions are derived from the target pixel count and the `size` ratio, aligned to multiples of 16):\\n\\n- `1K`: ~1 MP (1024² = 1,048,576 pixels)\\n- `2K`: ~4 MP (2048² = 4,194,304 pixels)\\n- `4K`: ~8.29 MP (3840×2160 = 8,294,400 pixels, the maximum)\\n\\n**Landscape / square output dimensions** (portrait dimensions are the landscape width/height swapped, e.g. `2:3` = `3:2` reversed):\\n\\n| Ratio | 1K | 2K | 4K |\\n|---|---|---|---|\\n| `1:1` | 1024×1024 | 2048×2048 | 2880×2880 |\\n| `2:1` | 1456×720 | 2896×1456 | 3840×1920 \\\\* |\\n| `3:1` | 1776×592 | 3552×1184 | 3840×1280 \\\\* |\\n| `3:2` | 1248×832 | 2512×1680 | 3520×2352 |\\n| `4:3` | 1184×880 | 2368×1776 | 3312×2480 \\\\* |\\n| `5:4` | 1152×912 | 2288×1824 | 3216×2576 |\\n| `16:9` | 1360×768 | 2736×1536 | 3840×2160 (UHD) |\\n| `21:9` | 1568×672 | 3136×1344 | 3840×1648 \\\\* |\\n\\n\\\\* Marks combinations that are auto-downscaled to fit the pixel budget. Values are case-insensitive.\",\"enum\":[\"1K\",\"2K\",\"4K\"],\"default\":\"1K\",\"example\":\"1K\"},\"quality\":{\"type\":\"string\",\"description\":\"Rendering quality, which directly affects output token count and cost. Defaults to `medium`\\n\\n| Value | Output tokens (1024²) | Relative image output cost (1024²) |\\n|---|---|---|\\n| `low` | 824 | ~0.57× |\\n| `medium` | 1,449 | 1.0× |\\n| `high` | 1,756 | ~1.21× |\\n| `xhigh` | 3,122 | ~2.15× |\\n| `max` | 7,024 | ~4.85× |\\n\\n**Note:**\\n- This table compares image output costs only, excluding input costs\\n- Calculated for `1024×1024`; output tokens vary with total pixels and aspect ratio. Use the returned `usage` for actual consumption\\n- For GIF output, tokens are calculated for the combined image containing all frames\\n- Use `low` for quick drafts. For final assets, compare tiers to balance detail, latency and cost\",\"enum\":[\"low\",\"medium\",\"high\",\"xhigh\",\"max\"],\"default\":\"medium\",\"example\":\"medium\"},\"complexity\":{\"type\":\"string\",\"description\":\"Planning depth before image generation, independent of `quality`. Defaults to `high`\\n\\n- `low`: Suitable for local changes such as replacing a background or changing sign text\\n- `medium`: Balanced\\n- `high`: Suitable for text-heavy images, complex layouts or complex relationships between objects\\n\\n**Note:**\\n- Higher levels take longer and may introduce unwanted changes; compare results for your task\\n- Changing `complexity` does not incur an additional charge\\n- Can also be supplied as `model_params.complexity`; the top-level value takes precedence when both are present\",\"enum\":[\"low\",\"medium\",\"high\"],\"default\":\"high\",\"example\":\"high\"},\"background\":{\"type\":\"string\",\"description\":\"Alpha channel of the output image. Defaults to `opaque`\\n\\n- `opaque`: Flat background, no alpha channel\\n- `transparent`: Keeps the alpha channel\\n\\n**Note:**\\n- `transparent` is a Preview feature and results may be unstable\\n- When using `transparent`, `output_format` must be `png` or `webp`\\n- When `output_format` is `gif`, only `opaque` is supported\",\"enum\":[\"opaque\",\"transparent\"],\"default\":\"opaque\",\"example\":\"opaque\"},\"output_format\":{\"type\":\"string\",\"description\":\"Output file format. Defaults to `png`\\n\\n- `png`: Lossless, supports transparent backgrounds\\n- `jpeg`: Lossy compression with smaller files\\n- `webp`: Balances file size and quality; also supports transparency\\n- `gif`: Animated GIF; see `model_params` for frame count and frame duration\\n\\n**Note:**\\n- When `background` is `transparent`, only `png` or `webp` is allowed\\n- `gif` supports both text-to-image and image editing\\n- For `gif`, `n` must be `1`\",\"enum\":[\"png\",\"jpeg\",\"webp\",\"gif\"],\"default\":\"png\",\"example\":\"png\"},\"n\":{\"type\":\"integer\",\"description\":\"Number of images to generate, each billed independently\\n\\n**Note:**\\n- Text input tokens scale linearly with `n`\\n- Support for `n > 1` is currently unreliable: even with a value greater than 1, only one image is often returned. The actual count is whatever `results` holds in the response, and billing follows the returned `usage`. If you need several images, send multiple single-image requests instead\\n- When `output_format` is `gif`, this must be `1`\",\"minimum\":1,\"maximum\":10,\"default\":1,\"example\":1},\"model_params\":{\"type\":\"object\",\"description\":\"Model-specific parameters. GIF frame parameters must be supplied in this object.\\n\\n- `frame_count` and `frame_duration_ms` are only allowed with `output_format=gif`\\n- Parameters incompatible with the output format return HTTP 400; they are not silently ignored\",\"properties\":{\"frame_count\":{\"type\":\"integer\",\"description\":\"Number of GIF frames. Only available when `output_format` is `gif`. Defaults to `9`.\\n\\nAll frames are generated together as one combined image. Explicit frame width and height must be positive multiples of `16`; individual frames are not subject to the minimum pixel count for standard images. Edge lengths below are in pixels.\\n\\n| Frames | Per-frame limits | Example size |\\n|---|---|---|\\n| `2`~`8` | ≤ 1,036,800 pixels; one edge ≤ 960, the other ≤ 1920 | `960x1072` |\\n| `9` | ≤ 921,600 pixels; both edges ≤ 1280 | `1280x720` |\\n| `10`~`12` | ≤ 691,200 pixels; one edge ≤ 1280, the other ≤ 960 | `960x720` |\\n| `13`~`16` | ≤ 518,400 pixels; both edges ≤ 960 | `720x720` |\\n\\n**Grid layout (columns × rows):**\\n- `2`~`8` frames: `4×2` or `2×4`\\n- `9` frames: `3×3`\\n- `10`~`12` frames: `3×4` or `4×3`, with `4×4` tried if necessary\\n- `13`~`16` frames: `4×4`\\n\\n**All of the following must also hold:**\\n- At least one layout must keep each edge of the combined image ≤ `3840` px, total pixels ≤ `8,294,400` and aspect ratio ≤ `3:1`\\n- When using a `4×4` layout, each frame must satisfy the area and edge limits listed for `13`~`16` frames\\n- If no available layout fits, the request returns HTTP 400; the area and edge limits in the table are not the only constraints\\n\\nWith `size=auto`, each frame is `512×512`, which works for every supported frame count. Output tokens are calculated for the combined image, not by adding up individual frames.\",\"minimum\":2,\"maximum\":16,\"default\":9,\"example\":9},\"frame_duration_ms\":{\"type\":\"integer\",\"description\":\"Duration of each GIF frame in milliseconds. Only available when `output_format` is `gif`. Defaults to `200`, rounded to 10-millisecond increments\",\"minimum\":20,\"maximum\":2000,\"default\":200,\"example\":200}}}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"responseSchema\":{\"schema\":{\"$ref\":\"#/$defs/ImageGenerationResponse\",\"$defs\":{\"ImageGenerationResponse\":{\"type\":\"object\",\"properties\":{\"created\":{\"type\":\"integer\",\"description\":\"Task creation timestamp\",\"example\":1757156493},\"id\":{\"type\":\"string\",\"description\":\"Task ID\",\"example\":\"task-unified-1757156493-imcg5zqt\"},\"model\":{\"type\":\"string\",\"description\":\"Actual model name used\",\"example\":\"gpt-image-2.6-sunburst\"},\"object\":{\"type\":\"string\",\"enum\":[\"image.generation.task\"],\"description\":\"Specific task type\"},\"progress\":{\"type\":\"integer\",\"description\":\"Task progress percentage (0-100)\",\"minimum\":0,\"maximum\":100,\"example\":1},\"status\":{\"type\":\"string\",\"description\":\"Task status. Queued and running tasks both return `processing`; the final status is `completed` or `failed`.\",\"enum\":[\"processing\",\"completed\",\"failed\"],\"example\":\"processing\"},\"task_info\":{\"$ref\":\"#/$defs/TaskInfo\",\"description\":\"Asynchronous task information\"},\"type\":{\"type\":\"string\",\"enum\":[\"text\",\"image\",\"audio\",\"video\"],\"description\":\"Task output type\",\"example\":\"image\"},\"usage\":{\"$ref\":\"#/$defs/Usage\",\"description\":\"Usage and billing information\"}}},\"TaskInfo\":{\"type\":\"object\",\"properties\":{\"estimated_time\":{\"type\":\"integer\",\"description\":\"Estimated completion time (seconds)\",\"minimum\":0,\"example\":100}}},\"Usage\":{\"type\":\"object\",\"description\":\"Reserved credits at task creation. Query the task after completion for actual consumption and token details.\",\"properties\":{\"billing_rule\":{\"type\":\"string\",\"description\":\"Billing rule. GPT Image 2.6 is billed per 1,000 tokens. Image usage and text input are charged separately at their respective rates.\",\"enum\":[\"per_1k_tokens\"],\"example\":\"per_1k_tokens\"},\"credits_reserved\":{\"type\":\"number\",\"description\":\"Estimated credits consumed\",\"minimum\":0,\"example\":2.5},\"user_group\":{\"type\":\"string\",\"description\":\"User group category\",\"example\":\"default\"}}}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"example\":{\"prompt\":\"A beautiful colorful sunset over the ocean\"}},\"gpt-image-2.6-sunburst\":{\"model\":\"gpt-image-2.6-sunburst\",\"kind\":\"image\",\"path\":\"/v1/images/generations\",\"title\":\"gpt-image-2.6 API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/image-series/gpt-image-2.6/gpt-image-2.6-image-generation\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the image to generate or how to edit the input image Length limits (both must be met): Up to 32,000 characters (counted as Unicode code points); The prompt text itself must not exceed 60,000 bytes when encoded in UTF-8 Different characters use different numbers of UTF-8 bytes. Use the actual encoded byte count. If either limit is exceeded, shorten the prompt before resubmitting. Recommendation: If the prompt exceeds 8000 tokens, the generated image may not match expectations; shortening the prompt is recommended.\",\"maxLength\":32000,\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference images as public URLs, for image-to-image and image editing Note: Number of input images per request: 1~16; Size of a single image: not exceeding 50MB; Pixels of a single image: width × height not exceeding 178,956,970 px; Side length of a single image: width / height each not exceeding 23170 px; exceeding this may cause errors; Supported file formats: .jpeg, .jpg, .png, .webp; Image URLs must be directly accessible by the server, or the image URL should directly download when accessed (typically these URLs end with image file extensions, such as .png, .jpg); In image-to-image / ima…\",\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"mask_url\":{\"type\":\"string\",\"description\":\"Inpainting mask URL — marks the region of the reference image to regenerate. Only valid in image edit mode (must be combined with image_urls); the mask is silently ignored in pure text-to-image requests. Format requirements: Must be a PNG with an alpha channel: transparent pixels (alpha < 255) = regions to regenerate; opaque pixels = preserved; Mask dimensions must exactly match the reference image dimensions (width × height in pixels); Single mask per request Note: At least one reference image is required in image_urls; a mask sent alone has no effect; Cannot be combined with markup_url; Com…\",\"format\":\"uri\"},\"markup_url\":{\"type\":\"string\",\"description\":\"Public URL of a markup layer. Use circles, arrows or freehand marks to indicate what to change in the reference image, and describe the changes in prompt. Only valid in image editing mode (requires image_urls). Format requirements: Must be a PNG with transparent pixels: draw only the annotations and leave the rest transparent. Do not draw directly on the original image; Dimensions must exactly match the first reference image (width × height in pixels); The first reference image and the markup layer must each have width × height ≤ 16,777,216 px; File size: no more than 50MB Note: Markup applie…\",\"format\":\"uri\"},\"size\":{\"type\":\"string\",\"description\":\"Generated image dimensions. Defaults to auto. Standard images use the following rules; GIF uses the separate rules in section ④. ① Standard images: ratio format (15 options); 1:1: Square; 1:2 / 2:1: Extreme portrait / landscape; 1:3 / 3:1: Ultra portrait / landscape (3:1 limit); 2:3 / 3:2: Standard portrait / landscape; 3:4 / 4:3: Classic portrait / landscape; 4:5 / 5:4: Common social media; 9:16 / 16:9: Mobile / desktop widescreen; 9:21 / 21:9: Ultra-wide ② Standard images: explicit pixel format: WxH (or W×H), e.g. 1024x1024, 1536x1024, 3840×2160; Both width and height must be multiples of 1…\",\"default\":\"auto\"},\"resolution\":{\"type\":\"string\",\"description\":\"Resolution tier shortcut, only effective when size is a ratio; ignored in explicit pixel mode and for GIF output Pixel budget rules (dimensions are derived from the target pixel count and the size ratio, aligned to multiples of 16): 1K: ~1 MP (1024² = 1,048,576 pixels); 2K: ~4 MP (2048² = 4,194,304 pixels); 4K: ~8.29 MP (3840×2160 = 8,294,400 pixels, the maximum) Landscape / square output dimensions (portrait dimensions are the landscape width/height swapped, e.g. 2:3 = 3:2 reversed): | Ratio | 1K | 2K | 4K | |---|---|---|---| | 1:1 | 1024×1024 | 2048×2048 | 2880×2880 | | 2:1 | 1456×720 | 289…\",\"enum\":[\"1K\",\"2K\",\"4K\"],\"default\":\"1K\"},\"quality\":{\"type\":\"string\",\"description\":\"Rendering quality, which directly affects output token count and cost. Defaults to medium | Value | Output tokens (1024²) | Relative image output cost (1024²) | |---|---|---| | low | 824 | ~0.57× | | medium | 1,449 | 1.0× | | high | 1,756 | ~1.21× | | xhigh | 3,122 | ~2.15× | | max | 7,024 | ~4.85× | Note: This table compares image output costs only, excluding input costs; Calculated for 1024×1024; output tokens vary with total pixels and aspect ratio. Use the returned usage for actual consumption; For GIF output, tokens are calculated for the combined image containing all frames; Use low for…\",\"enum\":[\"low\",\"medium\",\"high\",\"xhigh\",\"max\"],\"default\":\"medium\"},\"complexity\":{\"type\":\"string\",\"description\":\"Planning depth before image generation, independent of quality. Defaults to high; low: Suitable for local changes such as replacing a background or changing sign text; medium: Balanced; high: Suitable for text-heavy images, complex layouts or complex relationships between objects Note: Higher levels take longer and may introduce unwanted changes; compare results for your task; Changing complexity does not incur an additional charge; Can also be supplied as model_params.complexity; the top-level value takes precedence when both are present\",\"enum\":[\"low\",\"medium\",\"high\"],\"default\":\"high\"},\"background\":{\"type\":\"string\",\"description\":\"Alpha channel of the output image. Defaults to opaque; opaque: Flat background, no alpha channel; transparent: Keeps the alpha channel Note: transparent is a Preview feature and results may be unstable; When using transparent, output_format must be png or webp; When output_format is gif, only opaque is supported\",\"enum\":[\"opaque\",\"transparent\"],\"default\":\"opaque\"},\"output_format\":{\"type\":\"string\",\"description\":\"Output file format. Defaults to png; png: Lossless, supports transparent backgrounds; jpeg: Lossy compression with smaller files; webp: Balances file size and quality; also supports transparency; gif: Animated GIF; see model_params for frame count and frame duration Note: When background is transparent, only png or webp is allowed; gif supports both text-to-image and image editing; For gif, n must be 1\",\"enum\":[\"png\",\"jpeg\",\"webp\",\"gif\"],\"default\":\"png\"},\"n\":{\"type\":\"integer\",\"description\":\"Number of images to generate, each billed independently Note: Text input tokens scale linearly with n; Support for n > 1 is currently unreliable: even with a value greater than 1, only one image is often returned. The actual count is whatever results holds in the response, and billing follows the returned usage. If you need several images, send multiple single-image requests instead; When output_format is gif, this must be 1\",\"default\":1,\"minimum\":1,\"maximum\":10},\"model_params\":{\"type\":\"object\",\"description\":\"Model-specific parameters. GIF frame parameters must be supplied in this object.; frame_count and frame_duration_ms are only allowed with output_format=gif; Parameters incompatible with the output format return HTTP 400; they are not silently ignored\",\"properties\":{\"frame_count\":{\"type\":\"integer\",\"description\":\"Number of GIF frames. Only available when output_format is gif. Defaults to 9. All frames are generated together as one combined image. Explicit frame width and height must be positive multiples of 16; individual frames are not subject to the minimum pixel count for standard images. Edge lengths below are in pixels. | Frames | Per-frame limits | Example size | |---|---|---| | 2~8 | ≤ 1,036,800 pixels; one edge ≤ 960, the other ≤ 1920 | 960x1072 | | 9 | ≤ 921,600 pixels; both edges ≤ 1280 | 1280x720 | | 10~12 | ≤ 691,200 pixels; one edge ≤ 1280, the other ≤ 960 | 960x720 | | 13~16 | ≤ 518,400…\",\"default\":9,\"minimum\":2,\"maximum\":16},\"frame_duration_ms\":{\"type\":\"integer\",\"description\":\"Duration of each GIF frame in milliseconds. Only available when output_format is gif. Defaults to 200, rounded to 10-millisecond increments\",\"default\":200,\"minimum\":20,\"maximum\":2000}}}},\"inputSchema\":{\"schema\":{\"type\":\"object\",\"required\":[\"prompt\"],\"properties\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the image to generate or how to edit the input image\\n\\n**Length limits (both must be met):**\\n- Up to `32,000` characters (counted as Unicode code points)\\n- The `prompt` text itself must not exceed `60,000` bytes when encoded in UTF-8\\n\\nDifferent characters use different numbers of UTF-8 bytes. Use the actual encoded byte count.\\n\\nIf either limit is exceeded, shorten the prompt before resubmitting.\\n\\n**Recommendation:** If the prompt exceeds `8000` tokens, the generated image may not match expectations; shortening the prompt is recommended.\",\"example\":\"A beautiful colorful sunset over the ocean\",\"maxLength\":32000},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference images as public URLs, for image-to-image and image editing\\n\\n**Note:**\\n- Number of input images per request: `1~16`\\n- Size of a single image: not exceeding `50MB`\\n- Pixels of a single image: width × height not exceeding `178,956,970` px\\n- Side length of a single image: width / height each not exceeding `23170` px; exceeding this may cause errors\\n- Supported file formats: `.jpeg`, `.jpg`, `.png`, `.webp`\\n- Image URLs must be directly accessible by the server, or the image URL should directly download when accessed (typically these URLs end with image file extensions, such as `.png`, `.jpg`)\\n- In image-to-image / image editing scenarios, the reference images themselves also incur additional image input token consumption\\n- With `markup_url`, markup applies to the first image and the others serve as references; the first image must have width × height ≤ `16,777,216` px\",\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"example\":[\"https://example.com/image1.png\",\"https://example.com/image2.png\"]},\"mask_url\":{\"type\":\"string\",\"format\":\"uri\",\"description\":\"Inpainting mask URL — marks the region of the reference image to regenerate. **Only valid in image edit mode** (must be combined with `image_urls`); the mask is silently ignored in pure text-to-image requests.\\n\\n**Format requirements:**\\n- **Must be a PNG with an alpha channel**: transparent pixels (`alpha < 255`) = regions to regenerate; opaque pixels = preserved\\n- **Mask dimensions must exactly match the reference image dimensions** (width × height in pixels)\\n- Single mask per request\\n\\n**Note:**\\n- At least one reference image is required in `image_urls`; a mask sent alone has no effect\\n- Cannot be combined with `markup_url`\\n- Common errors:\\n - `Invalid mask image format - mask image missing alpha channel`: the uploaded image has no alpha channel (JPEG, opaque PNG, etc.). Re-export the mask as a PNG with transparent regions.\\n - `Invalid mask image format - mask size does not match image size`: the mask dimensions don't match the reference image. Resize the mask to the same pixel dimensions as your reference image.\",\"example\":\"https://example.com/mask.png\"},\"markup_url\":{\"type\":\"string\",\"format\":\"uri\",\"description\":\"Public URL of a markup layer. Use circles, arrows or freehand marks to indicate what to change in the reference image, and describe the changes in `prompt`. **Only valid in image editing mode** (requires `image_urls`).\\n\\n**Format requirements:**\\n- **Must be a PNG with transparent pixels**: draw only the annotations and leave the rest transparent. Do not draw directly on the original image\\n- **Dimensions must exactly match the first reference image** (width × height in pixels)\\n- The first reference image and the markup layer must each have width × height ≤ `16,777,216` px\\n- File size: no more than `50MB`\\n\\n**Note:**\\n- Markup applies to the first image in `image_urls`; the remaining images serve as references\\n- Cannot be combined with `mask_url`\\n- Supports standard image and GIF editing\\n- Can also be supplied as `model_params.markup_url`; the top-level value takes precedence when both are present\\n- In `prompt`, also specify what to preserve, for example, \\\"keep everything else unchanged and remove the red circle\\\"\",\"example\":\"https://example.com/markup.png\"},\"size\":{\"type\":\"string\",\"description\":\"Generated image dimensions. Defaults to `auto`. Standard images use the following rules; GIF uses the separate rules in section ④.\\n\\n**① Standard images: ratio format (15 options)**\\n\\n- `1:1`: Square\\n- `1:2` / `2:1`: Extreme portrait / landscape\\n- `1:3` / `3:1`: Ultra portrait / landscape (3:1 limit)\\n- `2:3` / `3:2`: Standard portrait / landscape\\n- `3:4` / `4:3`: Classic portrait / landscape\\n- `4:5` / `5:4`: Common social media\\n- `9:16` / `16:9`: Mobile / desktop widescreen\\n- `9:21` / `21:9`: Ultra-wide\\n\\n**② Standard images: explicit pixel format**: `WxH` (or `W×H`), e.g. `1024x1024`, `1536x1024`, `3840×2160`\\n\\n- Both width and height must be multiples of `16`\\n- Each edge range: `[16, 3840]`\\n- Pixel budget: `655,360 ≤ width × height ≤ 8,294,400` (about 0.65 MP ~ 8.29 MP)\\n- Aspect ratio: `≤ 3:1`\\n\\n**③ Standard images: `auto`**: The model decides the size automatically (`resolution` does not apply in this mode)\\n\\n**④ GIF output**: `size` specifies the dimensions of each frame. Only `auto` and explicit pixel dimensions are supported, not ratios.\\n\\n- With `auto`, each frame is `512×512`\\n- Explicit frame width and height must be positive multiples of `16`\\n- The `655,360` minimum pixel count for standard images does not apply to individual GIF frames; for example, `512x512` is valid\\n- The image combining all frames must satisfy the edge, total pixel and aspect ratio limits; see `model_params.frame_count` for grid layouts and per-frame limits\\n- `resolution` does not apply\\n\\n**Out-of-range handling:**\\n- For standard images, a ratio + `resolution` combination that exceeds the budget is automatically scaled down proportionally (e.g. 4K 2:1 → 3840×1920)\\n- Explicit GIF frame dimensions that exceed the limits return HTTP 400 and are not automatically scaled down\",\"default\":\"auto\",\"example\":\"auto\"},\"resolution\":{\"type\":\"string\",\"description\":\"Resolution tier shortcut, only effective when `size` is a ratio; ignored in explicit pixel mode and for GIF output\\n\\n**Pixel budget rules** (dimensions are derived from the target pixel count and the `size` ratio, aligned to multiples of 16):\\n\\n- `1K`: ~1 MP (1024² = 1,048,576 pixels)\\n- `2K`: ~4 MP (2048² = 4,194,304 pixels)\\n- `4K`: ~8.29 MP (3840×2160 = 8,294,400 pixels, the maximum)\\n\\n**Landscape / square output dimensions** (portrait dimensions are the landscape width/height swapped, e.g. `2:3` = `3:2` reversed):\\n\\n| Ratio | 1K | 2K | 4K |\\n|---|---|---|---|\\n| `1:1` | 1024×1024 | 2048×2048 | 2880×2880 |\\n| `2:1` | 1456×720 | 2896×1456 | 3840×1920 \\\\* |\\n| `3:1` | 1776×592 | 3552×1184 | 3840×1280 \\\\* |\\n| `3:2` | 1248×832 | 2512×1680 | 3520×2352 |\\n| `4:3` | 1184×880 | 2368×1776 | 3312×2480 \\\\* |\\n| `5:4` | 1152×912 | 2288×1824 | 3216×2576 |\\n| `16:9` | 1360×768 | 2736×1536 | 3840×2160 (UHD) |\\n| `21:9` | 1568×672 | 3136×1344 | 3840×1648 \\\\* |\\n\\n\\\\* Marks combinations that are auto-downscaled to fit the pixel budget. Values are case-insensitive.\",\"enum\":[\"1K\",\"2K\",\"4K\"],\"default\":\"1K\",\"example\":\"1K\"},\"quality\":{\"type\":\"string\",\"description\":\"Rendering quality, which directly affects output token count and cost. Defaults to `medium`\\n\\n| Value | Output tokens (1024²) | Relative image output cost (1024²) |\\n|---|---|---|\\n| `low` | 824 | ~0.57× |\\n| `medium` | 1,449 | 1.0× |\\n| `high` | 1,756 | ~1.21× |\\n| `xhigh` | 3,122 | ~2.15× |\\n| `max` | 7,024 | ~4.85× |\\n\\n**Note:**\\n- This table compares image output costs only, excluding input costs\\n- Calculated for `1024×1024`; output tokens vary with total pixels and aspect ratio. Use the returned `usage` for actual consumption\\n- For GIF output, tokens are calculated for the combined image containing all frames\\n- Use `low` for quick drafts. For final assets, compare tiers to balance detail, latency and cost\",\"enum\":[\"low\",\"medium\",\"high\",\"xhigh\",\"max\"],\"default\":\"medium\",\"example\":\"medium\"},\"complexity\":{\"type\":\"string\",\"description\":\"Planning depth before image generation, independent of `quality`. Defaults to `high`\\n\\n- `low`: Suitable for local changes such as replacing a background or changing sign text\\n- `medium`: Balanced\\n- `high`: Suitable for text-heavy images, complex layouts or complex relationships between objects\\n\\n**Note:**\\n- Higher levels take longer and may introduce unwanted changes; compare results for your task\\n- Changing `complexity` does not incur an additional charge\\n- Can also be supplied as `model_params.complexity`; the top-level value takes precedence when both are present\",\"enum\":[\"low\",\"medium\",\"high\"],\"default\":\"high\",\"example\":\"high\"},\"background\":{\"type\":\"string\",\"description\":\"Alpha channel of the output image. Defaults to `opaque`\\n\\n- `opaque`: Flat background, no alpha channel\\n- `transparent`: Keeps the alpha channel\\n\\n**Note:**\\n- `transparent` is a Preview feature and results may be unstable\\n- When using `transparent`, `output_format` must be `png` or `webp`\\n- When `output_format` is `gif`, only `opaque` is supported\",\"enum\":[\"opaque\",\"transparent\"],\"default\":\"opaque\",\"example\":\"opaque\"},\"output_format\":{\"type\":\"string\",\"description\":\"Output file format. Defaults to `png`\\n\\n- `png`: Lossless, supports transparent backgrounds\\n- `jpeg`: Lossy compression with smaller files\\n- `webp`: Balances file size and quality; also supports transparency\\n- `gif`: Animated GIF; see `model_params` for frame count and frame duration\\n\\n**Note:**\\n- When `background` is `transparent`, only `png` or `webp` is allowed\\n- `gif` supports both text-to-image and image editing\\n- For `gif`, `n` must be `1`\",\"enum\":[\"png\",\"jpeg\",\"webp\",\"gif\"],\"default\":\"png\",\"example\":\"png\"},\"n\":{\"type\":\"integer\",\"description\":\"Number of images to generate, each billed independently\\n\\n**Note:**\\n- Text input tokens scale linearly with `n`\\n- Support for `n > 1` is currently unreliable: even with a value greater than 1, only one image is often returned. The actual count is whatever `results` holds in the response, and billing follows the returned `usage`. If you need several images, send multiple single-image requests instead\\n- When `output_format` is `gif`, this must be `1`\",\"minimum\":1,\"maximum\":10,\"default\":1,\"example\":1},\"model_params\":{\"type\":\"object\",\"description\":\"Model-specific parameters. GIF frame parameters must be supplied in this object.\\n\\n- `frame_count` and `frame_duration_ms` are only allowed with `output_format=gif`\\n- Parameters incompatible with the output format return HTTP 400; they are not silently ignored\",\"properties\":{\"frame_count\":{\"type\":\"integer\",\"description\":\"Number of GIF frames. Only available when `output_format` is `gif`. Defaults to `9`.\\n\\nAll frames are generated together as one combined image. Explicit frame width and height must be positive multiples of `16`; individual frames are not subject to the minimum pixel count for standard images. Edge lengths below are in pixels.\\n\\n| Frames | Per-frame limits | Example size |\\n|---|---|---|\\n| `2`~`8` | ≤ 1,036,800 pixels; one edge ≤ 960, the other ≤ 1920 | `960x1072` |\\n| `9` | ≤ 921,600 pixels; both edges ≤ 1280 | `1280x720` |\\n| `10`~`12` | ≤ 691,200 pixels; one edge ≤ 1280, the other ≤ 960 | `960x720` |\\n| `13`~`16` | ≤ 518,400 pixels; both edges ≤ 960 | `720x720` |\\n\\n**Grid layout (columns × rows):**\\n- `2`~`8` frames: `4×2` or `2×4`\\n- `9` frames: `3×3`\\n- `10`~`12` frames: `3×4` or `4×3`, with `4×4` tried if necessary\\n- `13`~`16` frames: `4×4`\\n\\n**All of the following must also hold:**\\n- At least one layout must keep each edge of the combined image ≤ `3840` px, total pixels ≤ `8,294,400` and aspect ratio ≤ `3:1`\\n- When using a `4×4` layout, each frame must satisfy the area and edge limits listed for `13`~`16` frames\\n- If no available layout fits, the request returns HTTP 400; the area and edge limits in the table are not the only constraints\\n\\nWith `size=auto`, each frame is `512×512`, which works for every supported frame count. Output tokens are calculated for the combined image, not by adding up individual frames.\",\"minimum\":2,\"maximum\":16,\"default\":9,\"example\":9},\"frame_duration_ms\":{\"type\":\"integer\",\"description\":\"Duration of each GIF frame in milliseconds. Only available when `output_format` is `gif`. Defaults to `200`, rounded to 10-millisecond increments\",\"minimum\":20,\"maximum\":2000,\"default\":200,\"example\":200}}}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"responseSchema\":{\"schema\":{\"$ref\":\"#/$defs/ImageGenerationResponse\",\"$defs\":{\"ImageGenerationResponse\":{\"type\":\"object\",\"properties\":{\"created\":{\"type\":\"integer\",\"description\":\"Task creation timestamp\",\"example\":1757156493},\"id\":{\"type\":\"string\",\"description\":\"Task ID\",\"example\":\"task-unified-1757156493-imcg5zqt\"},\"model\":{\"type\":\"string\",\"description\":\"Actual model name used\",\"example\":\"gpt-image-2.6-sunburst\"},\"object\":{\"type\":\"string\",\"enum\":[\"image.generation.task\"],\"description\":\"Specific task type\"},\"progress\":{\"type\":\"integer\",\"description\":\"Task progress percentage (0-100)\",\"minimum\":0,\"maximum\":100,\"example\":1},\"status\":{\"type\":\"string\",\"description\":\"Task status. Queued and running tasks both return `processing`; the final status is `completed` or `failed`.\",\"enum\":[\"processing\",\"completed\",\"failed\"],\"example\":\"processing\"},\"task_info\":{\"$ref\":\"#/$defs/TaskInfo\",\"description\":\"Asynchronous task information\"},\"type\":{\"type\":\"string\",\"enum\":[\"text\",\"image\",\"audio\",\"video\"],\"description\":\"Task output type\",\"example\":\"image\"},\"usage\":{\"$ref\":\"#/$defs/Usage\",\"description\":\"Usage and billing information\"}}},\"TaskInfo\":{\"type\":\"object\",\"properties\":{\"estimated_time\":{\"type\":\"integer\",\"description\":\"Estimated completion time (seconds)\",\"minimum\":0,\"example\":100}}},\"Usage\":{\"type\":\"object\",\"description\":\"Reserved credits at task creation. Query the task after completion for actual consumption and token details.\",\"properties\":{\"billing_rule\":{\"type\":\"string\",\"description\":\"Billing rule. GPT Image 2.6 is billed per 1,000 tokens. Image usage and text input are charged separately at their respective rates.\",\"enum\":[\"per_1k_tokens\"],\"example\":\"per_1k_tokens\"},\"credits_reserved\":{\"type\":\"number\",\"description\":\"Estimated credits consumed\",\"minimum\":0,\"example\":2.5},\"user_group\":{\"type\":\"string\",\"description\":\"User group category\",\"example\":\"default\"}}}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"example\":{\"prompt\":\"A beautiful colorful sunset over the ocean\"}},\"grok-imagine-video-1.5-lite\":{\"model\":\"grok-imagine-video-1.5-lite\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"grok-imagine-video-1.5-lite Interface\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/grok/grok-imagine-video-1.5-lite\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Video description prompt (required, cannot be empty) EvoLink platform length limit: Up to 2000 tokens (counted with the cl100k tokenizer, so CJK prompts hit the cap at far fewer characters than Latin ones). The platform also enforces a limit of 60000 UTF-8 bytes.\",\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Input image URL (optional). One image switches the request to image-to-video. Mode selection: 0 images (omit the field): text-to-video, no image charge; 1 image: image-to-video, used as the first frame; input images are billed separately (see the [pricing section](https://evolink.ai/grok-imagine-video-1-5-lite#pricing)); 2 or more images are rejected — reference-to-video is not supported on Lite Requirements: Playground local uploads: up to 10MiB (10485760 bytes) per image. Image URLs sent directly to the API are validated upstream and do not use this local upload check.; Supported formats: J…\",\"minItems\":0,\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds), any integer between 1 and 15 seconds\",\"default\":6,\"minimum\":1,\"maximum\":15},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution, default is 480p Description: 480p: Standard definition (default); 720p: High definition; 1080p: Upscaled from 720p, billed at a higher per-second rate See the [pricing section](https://evolink.ai/grok-imagine-video-1-5-lite#pricing) for the per-resolution rates.\",\"enum\":[\"480p\",\"720p\",\"1080p\"],\"default\":\"480p\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Output aspect ratio, default is auto Applies to: text-to-video (0 images). With an input image the output follows that image's dimensions and this parameter is ignored. Description: auto: No ratio is sent upstream and the upstream channel decides the framing (text-to-video currently renders 16:9); this is the default value; 16:9: Landscape; 9:16: Portrait; 1:1: Square; 4:3: Landscape, classic TV ratio; 3:4: Portrait, classic TV ratio; 3:2: Landscape, classic photo ratio; 2:3: Portrait, classic photo ratio\",\"enum\":[\"auto\",\"16:9\",\"9:16\",\"1:1\",\"4:3\",\"3:4\",\"3:2\",\"2:3\"],\"default\":\"auto\"}},\"inputSchema\":{\"schema\":{\"type\":\"object\",\"required\":[\"prompt\"],\"properties\":{\"prompt\":{\"type\":\"string\",\"description\":\"Video description prompt (required, cannot be empty)\\n\\n**EvoLink platform length limit:** Up to `2000` tokens (counted with the cl100k tokenizer, so CJK prompts hit the cap at far fewer characters than Latin ones). The platform also enforces a limit of 60000 UTF-8 bytes.\",\"example\":\"The person starts dancing\"},\"image_urls\":{\"type\":\"array\",\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"description\":\"Input image URL (optional). One image switches the request to image-to-video.\\n\\n**Mode selection:**\\n- `0` images (omit the field): text-to-video, no image charge\\n- `1` image: image-to-video, used as the first frame; input images are billed separately (see the [pricing section](https://evolink.ai/grok-imagine-video-1-5-lite#pricing))\\n- `2` or more images are rejected — reference-to-video is not supported on Lite\\n\\n**Requirements:**\\n- Playground local uploads: up to `10MiB` (10485760 bytes) per image. Image URLs sent directly to the API are validated upstream and do not use this local upload check.\\n- Supported formats: JPEG, PNG, WebP\",\"minItems\":0,\"maxItems\":1,\"example\":[\"https://example.com/image.jpg\"]},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds), any integer between `1` and `15` seconds\",\"minimum\":1,\"maximum\":15,\"default\":6,\"example\":6},\"quality\":{\"type\":\"string\",\"description\":\"Video resolution, default is `480p`\\n\\n**Description:**\\n- `480p`: Standard definition (default)\\n- `720p`: High definition\\n- `1080p`: Upscaled from 720p, billed at a higher per-second rate\\n\\nSee the [pricing section](https://evolink.ai/grok-imagine-video-1-5-lite#pricing) for the per-resolution rates.\",\"enum\":[\"480p\",\"720p\",\"1080p\"],\"default\":\"480p\",\"example\":\"480p\"},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Output aspect ratio, default is `auto`\\n\\n**Applies to:** text-to-video (`0` images). With an input image the output follows that image's dimensions and this parameter is ignored.\\n\\n**Description:**\\n- `auto`: No ratio is sent upstream and the upstream channel decides the framing (text-to-video currently renders 16:9); this is the default value\\n- `16:9`: Landscape\\n- `9:16`: Portrait\\n- `1:1`: Square\\n- `4:3`: Landscape, classic TV ratio\\n- `3:4`: Portrait, classic TV ratio\\n- `3:2`: Landscape, classic photo ratio\\n- `2:3`: Portrait, classic photo ratio\",\"enum\":[\"auto\",\"16:9\",\"9:16\",\"1:1\",\"4:3\",\"3:4\",\"3:2\",\"2:3\"],\"default\":\"auto\",\"example\":\"16:9\"}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"responseSchema\":{\"schema\":{\"$ref\":\"#/$defs/VideoGenerationResponse\",\"$defs\":{\"VideoGenerationResponse\":{\"type\":\"object\",\"properties\":{\"created\":{\"type\":\"integer\",\"description\":\"Task creation timestamp\",\"example\":1757169743},\"id\":{\"type\":\"string\",\"description\":\"Task ID\",\"example\":\"task-unified-1757169743-7cvnl5zw\"},\"model\":{\"type\":\"string\",\"description\":\"Actual model name used\",\"example\":\"grok-imagine-video-1.5-lite\"},\"object\":{\"type\":\"string\",\"enum\":[\"video.generation.task\"],\"description\":\"Specific task type\"},\"progress\":{\"type\":\"integer\",\"description\":\"Task progress percentage (0-100)\",\"minimum\":0,\"maximum\":100,\"example\":0},\"status\":{\"type\":\"string\",\"description\":\"Task status\",\"enum\":[\"pending\",\"processing\",\"completed\",\"failed\"],\"example\":\"pending\"},\"task_info\":{\"$ref\":\"#/$defs/VideoTaskInfo\",\"description\":\"Video task detailed information\"},\"type\":{\"type\":\"string\",\"enum\":[\"text\",\"image\",\"audio\",\"video\"],\"description\":\"Task output type\",\"example\":\"video\"},\"usage\":{\"$ref\":\"#/$defs/Usage\",\"description\":\"Usage and billing information\"}}},\"VideoTaskInfo\":{\"type\":\"object\",\"properties\":{\"estimated_time\":{\"type\":\"integer\",\"description\":\"Estimated completion time (seconds)\",\"minimum\":0,\"example\":120},\"video_duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds)\",\"example\":6}}},\"Usage\":{\"type\":\"object\",\"description\":\"Usage and billing information\",\"properties\":{\"billing_rule\":{\"type\":\"string\",\"description\":\"Billing rule\",\"enum\":[\"per_call\",\"per_token\",\"per_second\"],\"example\":\"per_second\"},\"credits_reserved\":{\"type\":\"number\",\"description\":\"Estimated credits consumed\",\"minimum\":0,\"example\":5.712},\"user_group\":{\"type\":\"string\",\"description\":\"User group category\",\"example\":\"default\"}}}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"example\":{\"prompt\":\"A neon-lit street at night, slow dolly forward through the rain\",\"duration\":6,\"quality\":\"480p\",\"aspect_ratio\":\"16:9\"}},\"kling-v4-flash-image-to-video\":{\"model\":\"kling-v4-flash-image-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"kling-v4-flash-image-to-video API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/kling/kling-v4-flash-image-to-video\",\"required\":[\"image_start\",\"prompt\"],\"params\":{\"image_start\":{\"type\":\"string\",\"description\":\"First frame image URL for image-to-video generation (required) Note: Image size: up to 10MB; Supported formats: .jpg, .jpeg, .png; Image dimensions: width and height >= 300px, aspect ratio between 1:2.5 and 2.5:1; Image URL must be directly accessible by the server or trigger a direct download when accessed\",\"format\":\"uri\",\"required\":true},\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing the video to generate Note: Maximum 2500 characters\",\"maxLength\":2500,\"required\":true},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds. Defaults to 5 seconds Range: Integer from 3 to 20\",\"default\":5,\"minimum\":3,\"maximum\":20},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier Options: Only 720p is supported\",\"enum\":[\"720p\"],\"default\":\"720p\"}},\"inputSchema\":{\"schema\":{\"type\":\"object\",\"required\":[\"image_start\",\"prompt\"],\"properties\":{\"image_start\":{\"type\":\"string\",\"format\":\"uri\",\"description\":\"First frame image URL for image-to-video generation (**required**)\\n\\n**Note:**\\n- Image size: up to `10MB`\\n- Supported formats: `.jpg`, `.jpeg`, `.png`\\n- Image dimensions: width and height >= `300px`, aspect ratio between `1:2.5` and `2.5:1`\\n- Image URL must be directly accessible by the server or trigger a direct download when accessed\",\"example\":\"https://example.com/portrait.jpg\"},\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing the video to generate\\n\\n**Note:**\\n- Maximum `2500` characters\",\"example\":\"The person in the image slowly turns their head and smiles\",\"maxLength\":2500},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds. Defaults to `5` seconds\\n\\n**Range:**\\n- Integer from `3` to `20`\",\"minimum\":3,\"maximum\":20,\"default\":5,\"example\":5},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier\\n\\n**Options:**\\n- Only `720p` is supported\",\"enum\":[\"720p\"],\"default\":\"720p\",\"example\":\"720p\"}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"responseSchema\":{\"schema\":{\"$ref\":\"#/$defs/VideoGenerationResponse\",\"$defs\":{\"VideoGenerationResponse\":{\"type\":\"object\",\"properties\":{\"created\":{\"type\":\"integer\",\"description\":\"Task creation timestamp\",\"example\":1757169743},\"id\":{\"type\":\"string\",\"description\":\"Task ID\",\"example\":\"task-unified-1757169743-7cvnl5zw\"},\"model\":{\"type\":\"string\",\"description\":\"Actual model name used\",\"example\":\"kling-v4-flash-image-to-video\"},\"object\":{\"type\":\"string\",\"enum\":[\"video.generation.task\"],\"description\":\"Task type\"},\"progress\":{\"type\":\"integer\",\"description\":\"Task progress percentage (0-100)\",\"minimum\":0,\"maximum\":100,\"example\":0},\"status\":{\"type\":\"string\",\"description\":\"Task status\",\"enum\":[\"pending\",\"processing\",\"completed\",\"failed\"],\"example\":\"pending\"},\"task_info\":{\"$ref\":\"#/$defs/VideoTaskInfo\",\"description\":\"Video task details\"},\"type\":{\"type\":\"string\",\"enum\":[\"text\",\"image\",\"audio\",\"video\"],\"description\":\"Task output type\",\"example\":\"video\"},\"usage\":{\"$ref\":\"#/$defs/VideoUsage\",\"description\":\"Usage and billing information\"}}},\"VideoTaskInfo\":{\"type\":\"object\",\"properties\":{\"estimated_time\":{\"type\":\"integer\",\"description\":\"Estimated completion time (seconds)\",\"minimum\":0,\"example\":300},\"video_duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds)\",\"example\":5}}},\"VideoUsage\":{\"type\":\"object\",\"description\":\"Usage and billing information\",\"properties\":{\"billing_rule\":{\"type\":\"string\",\"description\":\"Billing rule\",\"enum\":[\"per_call\",\"per_token\",\"per_second\"],\"example\":\"per_second\"},\"credits_reserved\":{\"type\":\"number\",\"description\":\"Estimated credits consumed\",\"minimum\":0,\"example\":31.96},\"user_group\":{\"type\":\"string\",\"description\":\"User group category\",\"example\":\"default\"}}}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"example\":{\"prompt\":\"The person in the image slowly turns their head and smiles\",\"image_start\":\"https://example.com/portrait.jpg\",\"duration\":5,\"quality\":\"720p\"}},\"kling-v4-flash-reference-to-video\":{\"model\":\"kling-v4-flash-reference-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"kling-v4-flash-reference-to-video API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/kling/kling-v4-flash-reference-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt, up to 2500 characters Reference syntax: Use <<<xxx>>> in the prompt to reference images and videos, for example: The person from <<<image_1>>> walks down the street following the camera movement in <<<video_1>>>\",\"maxLength\":2500,\"required\":true},\"video_urls\":{\"type\":\"array\",\"description\":\"Reference video URL array, up to 5 clips, corresponding in order to <<<video_1>>>, <<<video_2>>>, etc. in the prompt Video requirements: Formats: MP4 / MOV; Size: ≤ 200MB per clip; Duration: ≥ 3 seconds per clip, ≤ 20 seconds in total; Dimensions: width and height from 720px to 2160px; Frame rate: 24fps to 60fps; Video URLs must be directly accessible by the server\",\"maxItems\":5,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL array (style, scene, or subject references), corresponding in order to <<<image_1>>>, <<<image_2>>>, etc. in the prompt Constraints: Up to 10 images Note: Image URLs must be directly accessible by the server or trigger a direct download when accessed\",\"maxItems\":10,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds. Defaults to 5 seconds Range: Integer from 3 to 20\",\"default\":5,\"minimum\":3,\"maximum\":20},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio Options: 16:9: Landscape; 9:16: Portrait; 1:1: Square; 21:9: Ultrawide\",\"enum\":[\"16:9\",\"9:16\",\"1:1\",\"21:9\"],\"default\":\"16:9\"},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier Options: Only 720p is supported\",\"enum\":[\"720p\"],\"default\":\"720p\"}},\"inputSchema\":{\"schema\":{\"type\":\"object\",\"required\":[\"prompt\"],\"properties\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt, up to 2500 characters\\n\\n**Reference syntax:** Use `<<<xxx>>>` in the prompt to reference images and videos, for example: `The person from <<<image_1>>> walks down the street following the camera movement in <<<video_1>>>`\",\"example\":\"The person from <<<image_1>>> walks down the street following the camera movement in <<<video_1>>>\",\"maxLength\":2500},\"video_urls\":{\"type\":\"array\",\"description\":\"Reference video URL array, up to `5` clips, corresponding in order to `<<<video_1>>>`, `<<<video_2>>>`, etc. in the prompt\\n\\n**Video requirements:**\\n- Formats: MP4 / MOV\\n- Size: ≤ 200MB per clip\\n- Duration: ≥ 3 seconds per clip, ≤ 20 seconds in total\\n- Dimensions: width and height from 720px to 2160px\\n- Frame rate: 24fps to 60fps\\n- Video URLs must be directly accessible by the server\",\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"maxItems\":5,\"example\":[\"https://example.com/reference.mp4\"]},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL array (style, scene, or subject references), corresponding in order to `<<<image_1>>>`, `<<<image_2>>>`, etc. in the prompt\\n\\n**Constraints:** Up to `10` images\\n**Note:** Image URLs must be directly accessible by the server or trigger a direct download when accessed\",\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"example\":[\"https://example.com/character.jpg\"],\"maxItems\":10},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds. Defaults to `5` seconds\\n\\n**Range:**\\n- Integer from `3` to `20`\",\"minimum\":3,\"maximum\":20,\"default\":5,\"example\":5},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio\\n\\n**Options:**\\n- `16:9`: Landscape\\n- `9:16`: Portrait\\n- `1:1`: Square\\n- `21:9`: Ultrawide\",\"enum\":[\"16:9\",\"9:16\",\"1:1\",\"21:9\"],\"example\":\"16:9\",\"default\":\"16:9\"},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier\\n\\n**Options:**\\n- Only `720p` is supported\",\"enum\":[\"720p\"],\"default\":\"720p\",\"example\":\"720p\"}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"responseSchema\":{\"schema\":{\"$ref\":\"#/$defs/VideoGenerationResponse\",\"$defs\":{\"VideoGenerationResponse\":{\"type\":\"object\",\"properties\":{\"created\":{\"type\":\"integer\",\"description\":\"Task creation timestamp\",\"example\":1757169743},\"id\":{\"type\":\"string\",\"description\":\"Task ID\",\"example\":\"task-unified-1757169743-7cvnl5zw\"},\"model\":{\"type\":\"string\",\"description\":\"Actual model name used\",\"example\":\"kling-v4-flash-reference-to-video\"},\"object\":{\"type\":\"string\",\"enum\":[\"video.generation.task\"],\"description\":\"Task type\"},\"progress\":{\"type\":\"integer\",\"description\":\"Task progress percentage (0-100)\",\"minimum\":0,\"maximum\":100,\"example\":0},\"status\":{\"type\":\"string\",\"description\":\"Task status\",\"enum\":[\"pending\",\"processing\",\"completed\",\"failed\"],\"example\":\"pending\"},\"task_info\":{\"$ref\":\"#/$defs/VideoTaskInfo\",\"description\":\"Video task details\"},\"type\":{\"type\":\"string\",\"enum\":[\"text\",\"image\",\"audio\",\"video\"],\"description\":\"Task output type\",\"example\":\"video\"},\"usage\":{\"$ref\":\"#/$defs/VideoUsage\",\"description\":\"Usage and billing information\"}}},\"VideoTaskInfo\":{\"type\":\"object\",\"properties\":{\"estimated_time\":{\"type\":\"integer\",\"description\":\"Estimated completion time (seconds)\",\"minimum\":0,\"example\":300},\"video_duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds)\",\"example\":5}}},\"VideoUsage\":{\"type\":\"object\",\"description\":\"Usage and billing information\",\"properties\":{\"billing_rule\":{\"type\":\"string\",\"description\":\"Billing rule\",\"enum\":[\"per_call\",\"per_token\",\"per_second\"],\"example\":\"per_second\"},\"credits_reserved\":{\"type\":\"number\",\"description\":\"Estimated credits consumed\",\"minimum\":0,\"example\":42.84},\"user_group\":{\"type\":\"string\",\"description\":\"User group category\",\"example\":\"default\"}}}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"example\":{\"prompt\":\"Keep the same motion style as <<<video_1>>> and replace the background with a snowy scene\",\"video_urls\":[\"https://example.com/reference.mp4\"],\"duration\":5,\"aspect_ratio\":\"16:9\",\"quality\":\"720p\"}},\"kling-v4-flash-text-to-video\":{\"model\":\"kling-v4-flash-text-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"kling-v4-flash-text-to-video API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/kling/kling-v4-flash-text-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing the video to generate Note: Maximum 2500 characters\",\"maxLength\":2500,\"required\":true},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds. Defaults to 5 seconds Range: Integer from 3 to 20\",\"default\":5,\"minimum\":3,\"maximum\":20},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio Options: 16:9: Landscape; 9:16: Portrait; 1:1: Square; 21:9: Ultrawide\",\"enum\":[\"16:9\",\"9:16\",\"1:1\",\"21:9\"],\"default\":\"16:9\"},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier Options: Only 720p is supported\",\"enum\":[\"720p\"],\"default\":\"720p\"}},\"inputSchema\":{\"schema\":{\"type\":\"object\",\"required\":[\"prompt\"],\"properties\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing the video to generate\\n\\n**Note:**\\n- Maximum `2500` characters\",\"example\":\"A cat running on a grassy field under bright sunshine\",\"maxLength\":2500},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds. Defaults to `5` seconds\\n\\n**Range:**\\n- Integer from `3` to `20`\",\"minimum\":3,\"maximum\":20,\"default\":5,\"example\":5},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio\\n\\n**Options:**\\n- `16:9`: Landscape\\n- `9:16`: Portrait\\n- `1:1`: Square\\n- `21:9`: Ultrawide\",\"enum\":[\"16:9\",\"9:16\",\"1:1\",\"21:9\"],\"example\":\"16:9\",\"default\":\"16:9\"},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier\\n\\n**Options:**\\n- Only `720p` is supported\",\"enum\":[\"720p\"],\"default\":\"720p\",\"example\":\"720p\"}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"responseSchema\":{\"schema\":{\"$ref\":\"#/$defs/VideoGenerationResponse\",\"$defs\":{\"VideoGenerationResponse\":{\"type\":\"object\",\"properties\":{\"created\":{\"type\":\"integer\",\"description\":\"Task creation timestamp\",\"example\":1757169743},\"id\":{\"type\":\"string\",\"description\":\"Task ID\",\"example\":\"task-unified-1757169743-7cvnl5zw\"},\"model\":{\"type\":\"string\",\"description\":\"Actual model name used\",\"example\":\"kling-v4-flash-text-to-video\"},\"object\":{\"type\":\"string\",\"enum\":[\"video.generation.task\"],\"description\":\"Task type\"},\"progress\":{\"type\":\"integer\",\"description\":\"Task progress percentage (0-100)\",\"minimum\":0,\"maximum\":100,\"example\":0},\"status\":{\"type\":\"string\",\"description\":\"Task status\",\"enum\":[\"pending\",\"processing\",\"completed\",\"failed\"],\"example\":\"pending\"},\"task_info\":{\"$ref\":\"#/$defs/VideoTaskInfo\",\"description\":\"Video task details\"},\"type\":{\"type\":\"string\",\"enum\":[\"text\",\"image\",\"audio\",\"video\"],\"description\":\"Task output type\",\"example\":\"video\"},\"usage\":{\"$ref\":\"#/$defs/VideoUsage\",\"description\":\"Usage and billing information\"}}},\"VideoTaskInfo\":{\"type\":\"object\",\"properties\":{\"estimated_time\":{\"type\":\"integer\",\"description\":\"Estimated completion time (seconds)\",\"minimum\":0,\"example\":300},\"video_duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds)\",\"example\":5}}},\"VideoUsage\":{\"type\":\"object\",\"description\":\"Usage and billing information\",\"properties\":{\"billing_rule\":{\"type\":\"string\",\"description\":\"Billing rule\",\"enum\":[\"per_call\",\"per_token\",\"per_second\"],\"example\":\"per_second\"},\"credits_reserved\":{\"type\":\"number\",\"description\":\"Estimated credits consumed\",\"minimum\":0,\"example\":31.96},\"user_group\":{\"type\":\"string\",\"description\":\"User group category\",\"example\":\"default\"}}}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"example\":{\"prompt\":\"A cat running on a grassy field under bright sunshine\",\"duration\":5,\"aspect_ratio\":\"16:9\",\"quality\":\"720p\"}},\"kling-v4-flash-video-edit\":{\"model\":\"kling-v4-flash-video-edit\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"kling-v4-flash-video-edit API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/kling/kling-v4-flash-video-edit\",\"required\":[\"prompt\",\"video_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Editing instructions, up to 2500 characters Reference syntax: Use <<<xxx>>> in the prompt to reference images and videos, for example: Replace the coat worn by the person in <<<video_1>>> with the style in <<<image_1>>>\",\"maxLength\":2500,\"required\":true},\"video_urls\":{\"type\":\"array\",\"description\":\"Video URL array for editing. Exactly 1 clip is supported, referenced as <<<video_1>>> in the prompt Video requirements: Formats: MP4 / MOV; Size: ≤ 200MB; Duration: 3 to 20 seconds; Dimensions: width and height from 720px to 2160px; Frame rate: 24fps to 60fps; The video URL must be directly accessible by the server\",\"minItems\":1,\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL array (style references) Constraints: Up to 10 images Note: Image URLs must be directly accessible by the server or trigger a direct download when accessed\",\"maxItems\":10,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"duration\":{\"type\":\"integer|string\",\"description\":\"Output video duration in seconds. Defaults to auto Values: Integer: 3 to 20 seconds; auto: Match the original video duration\",\"default\":\"auto\",\"minimum\":3,\"maximum\":20},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier Options: Only 720p is supported\",\"enum\":[\"720p\"],\"default\":\"720p\"}},\"inputSchema\":{\"schema\":{\"type\":\"object\",\"required\":[\"prompt\",\"video_urls\"],\"properties\":{\"prompt\":{\"type\":\"string\",\"description\":\"Editing instructions, up to 2500 characters\\n\\n**Reference syntax:** Use `<<<xxx>>>` in the prompt to reference images and videos, for example: `Replace the coat worn by the person in <<<video_1>>> with the style in <<<image_1>>>`\",\"example\":\"Adjust the color to warm tones and add a cinematic feel\",\"maxLength\":2500},\"video_urls\":{\"type\":\"array\",\"description\":\"Video URL array for editing. Exactly `1` clip is supported, referenced as `<<<video_1>>>` in the prompt\\n\\n**Video requirements:**\\n- Formats: MP4 / MOV\\n- Size: ≤ 200MB\\n- Duration: 3 to 20 seconds\\n- Dimensions: width and height from 720px to 2160px\\n- Frame rate: 24fps to 60fps\\n- The video URL must be directly accessible by the server\",\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"minItems\":1,\"maxItems\":1,\"example\":[\"https://example.com/original.mp4\"]},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL array (style references)\\n\\n**Constraints:** Up to `10` images\\n**Note:** Image URLs must be directly accessible by the server or trigger a direct download when accessed\",\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"example\":[\"https://example.com/style_ref.jpg\"],\"maxItems\":10},\"duration\":{\"description\":\"Output video duration in seconds. Defaults to `auto`\\n\\n**Values:**\\n- Integer: `3` to `20` seconds\\n- `auto`: Match the original video duration\",\"oneOf\":[{\"type\":\"integer\",\"minimum\":3,\"maximum\":20},{\"type\":\"string\",\"enum\":[\"auto\"]}],\"default\":\"auto\",\"example\":\"auto\"},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier\\n\\n**Options:**\\n- Only `720p` is supported\",\"enum\":[\"720p\"],\"default\":\"720p\",\"example\":\"720p\"}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"responseSchema\":{\"schema\":{\"$ref\":\"#/$defs/VideoGenerationResponse\",\"$defs\":{\"VideoGenerationResponse\":{\"type\":\"object\",\"properties\":{\"created\":{\"type\":\"integer\",\"description\":\"Task creation timestamp\",\"example\":1757169743},\"id\":{\"type\":\"string\",\"description\":\"Task ID\",\"example\":\"task-unified-1757169743-7cvnl5zw\"},\"model\":{\"type\":\"string\",\"description\":\"Actual model name used\",\"example\":\"kling-v4-flash-video-edit\"},\"object\":{\"type\":\"string\",\"enum\":[\"video.generation.task\"],\"description\":\"Task type\"},\"progress\":{\"type\":\"integer\",\"description\":\"Task progress percentage (0-100)\",\"minimum\":0,\"maximum\":100,\"example\":0},\"status\":{\"type\":\"string\",\"description\":\"Task status\",\"enum\":[\"pending\",\"processing\",\"completed\",\"failed\"],\"example\":\"pending\"},\"task_info\":{\"$ref\":\"#/$defs/VideoTaskInfo\",\"description\":\"Video task details\"},\"type\":{\"type\":\"string\",\"enum\":[\"text\",\"image\",\"audio\",\"video\"],\"description\":\"Task output type\",\"example\":\"video\"},\"usage\":{\"$ref\":\"#/$defs/VideoUsage\",\"description\":\"Usage and billing information\"}}},\"VideoTaskInfo\":{\"type\":\"object\",\"properties\":{\"estimated_time\":{\"type\":\"integer\",\"description\":\"Estimated completion time (seconds)\",\"minimum\":0,\"example\":300},\"video_duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds)\",\"example\":5}}},\"VideoUsage\":{\"type\":\"object\",\"description\":\"Usage and billing information\",\"properties\":{\"billing_rule\":{\"type\":\"string\",\"description\":\"Billing rule\",\"enum\":[\"per_call\",\"per_token\",\"per_second\"],\"example\":\"per_second\"},\"credits_reserved\":{\"type\":\"number\",\"description\":\"Estimated credits consumed\",\"minimum\":0,\"example\":42.84},\"user_group\":{\"type\":\"string\",\"description\":\"User group category\",\"example\":\"default\"}}}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"example\":{\"prompt\":\"Adjust the color to warm tones and add a cinematic feel\",\"video_urls\":[\"https://example.com/original.mp4\"],\"quality\":\"720p\"}},\"kling-v4-image-to-video\":{\"model\":\"kling-v4-image-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"kling-v4-image-to-video API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/kling/kling-v4-image-to-video\",\"required\":[\"image_start\",\"prompt\"],\"params\":{\"image_start\":{\"type\":\"string\",\"description\":\"First frame image URL for image-to-video generation (required) Note: Image size: up to 10MB; Supported formats: .jpg, .jpeg, .png; Image dimensions: width and height >= 300px, aspect ratio between 1:2.5 and 2.5:1; Image URL must be directly accessible by the server or trigger a direct download when accessed\",\"format\":\"uri\",\"required\":true},\"image_end\":{\"type\":\"string\",\"description\":\"Last frame image URL Note: image_start (first frame) must be provided when using last frame; Supported formats: .jpg, .jpeg, .png; Image size: up to 10MB; Image URL must be directly accessible by the server or trigger a direct download when accessed\",\"format\":\"uri\"},\"keyframes\":{\"type\":\"array\",\"description\":\"Intermediate frame images, evenly spaced in order between the first and last frames Note: Count: 1 to 8 images; The first frame, intermediate frames, and last frame combined must not exceed 10 images or duration + 1 (for example, up to 4 images for 3 seconds or 6 images for 5 seconds); The last frame is optional. If omitted, the model generates the ending frame; Image size: up to 10MB; Supported formats: .jpg, .jpeg, .png; Image dimensions: width and height >= 300px, aspect ratio between 1:2.5 and 2.5:1; Image URL must be directly accessible by the server or trigger a direct download when acc…\",\"minItems\":0,\"maxItems\":8,\"items\":{\"type\":\"object\",\"properties\":{\"image_url\":{\"type\":\"string\",\"description\":\"Intermediate frame image URL\",\"format\":\"uri\",\"required\":true}}}},\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing the video to generate Note: Maximum 2500 characters\",\"maxLength\":2500,\"required\":true},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds. Defaults to 5 seconds Range: Integer from 3 to 30\",\"default\":5,\"minimum\":3,\"maximum\":30},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier Options: 720p: Standard 720P; 1080p: High quality 1080P\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\"}},\"inputSchema\":{\"schema\":{\"type\":\"object\",\"required\":[\"image_start\",\"prompt\"],\"properties\":{\"image_start\":{\"type\":\"string\",\"format\":\"uri\",\"description\":\"First frame image URL for image-to-video generation (**required**)\\n\\n**Note:**\\n- Image size: up to `10MB`\\n- Supported formats: `.jpg`, `.jpeg`, `.png`\\n- Image dimensions: width and height >= `300px`, aspect ratio between `1:2.5` and `2.5:1`\\n- Image URL must be directly accessible by the server or trigger a direct download when accessed\",\"example\":\"https://example.com/portrait.jpg\"},\"image_end\":{\"type\":\"string\",\"format\":\"uri\",\"description\":\"Last frame image URL\\n\\n**Note:**\\n- `image_start` (first frame) must be provided when using last frame\\n- Supported formats: `.jpg`, `.jpeg`, `.png`\\n- Image size: up to `10MB`\\n- Image URL must be directly accessible by the server or trigger a direct download when accessed\",\"example\":\"https://example.com/night.jpg\"},\"keyframes\":{\"type\":\"array\",\"description\":\"Intermediate frame images, evenly spaced in order between the first and last frames\\n\\n**Note:**\\n- Count: `1` to `8` images\\n- The first frame, intermediate frames, and last frame combined must not exceed `10` images or `duration` + 1 (for example, up to `4` images for `3` seconds or `6` images for `5` seconds)\\n- The last frame is optional. If omitted, the model generates the ending frame\\n- Image size: up to `10MB`\\n- Supported formats: `.jpg`, `.jpeg`, `.png`\\n- Image dimensions: width and height >= `300px`, aspect ratio between `1:2.5` and `2.5:1`\\n- Image URL must be directly accessible by the server or trigger a direct download when accessed\",\"items\":{\"type\":\"object\",\"properties\":{\"image_url\":{\"type\":\"string\",\"format\":\"uri\",\"description\":\"Intermediate frame image URL\"}},\"required\":[\"image_url\"],\"additionalProperties\":false},\"minItems\":0,\"maxItems\":8,\"example\":[{\"image_url\":\"https://example.com/half-open.jpg\"},{\"image_url\":\"https://example.com/open.jpg\"}]},\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing the video to generate\\n\\n**Note:**\\n- Maximum `2500` characters\",\"example\":\"The person in the image slowly turns their head and smiles\",\"maxLength\":2500},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds. Defaults to `5` seconds\\n\\n**Range:**\\n- Integer from `3` to `30`\",\"minimum\":3,\"maximum\":30,\"default\":5,\"example\":5},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier\\n\\n**Options:**\\n- `720p`: Standard 720P\\n- `1080p`: High quality 1080P\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\",\"example\":\"720p\"}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"responseSchema\":{\"schema\":{\"$ref\":\"#/$defs/VideoGenerationResponse\",\"$defs\":{\"VideoGenerationResponse\":{\"type\":\"object\",\"properties\":{\"created\":{\"type\":\"integer\",\"description\":\"Task creation timestamp\",\"example\":1757169743},\"id\":{\"type\":\"string\",\"description\":\"Task ID\",\"example\":\"task-unified-1757169743-7cvnl5zw\"},\"model\":{\"type\":\"string\",\"description\":\"Actual model name used\",\"example\":\"kling-v4-image-to-video\"},\"object\":{\"type\":\"string\",\"enum\":[\"video.generation.task\"],\"description\":\"Task type\"},\"progress\":{\"type\":\"integer\",\"description\":\"Task progress percentage (0-100)\",\"minimum\":0,\"maximum\":100,\"example\":0},\"status\":{\"type\":\"string\",\"description\":\"Task status\",\"enum\":[\"pending\",\"processing\",\"completed\",\"failed\"],\"example\":\"pending\"},\"task_info\":{\"$ref\":\"#/$defs/VideoTaskInfo\",\"description\":\"Video task details\"},\"type\":{\"type\":\"string\",\"enum\":[\"text\",\"image\",\"audio\",\"video\"],\"description\":\"Task output type\",\"example\":\"video\"},\"usage\":{\"$ref\":\"#/$defs/VideoUsage\",\"description\":\"Usage and billing information\"}}},\"VideoTaskInfo\":{\"type\":\"object\",\"properties\":{\"estimated_time\":{\"type\":\"integer\",\"description\":\"Estimated completion time (seconds)\",\"minimum\":0,\"example\":300},\"video_duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds)\",\"example\":5}}},\"VideoUsage\":{\"type\":\"object\",\"description\":\"Usage and billing information\",\"properties\":{\"billing_rule\":{\"type\":\"string\",\"description\":\"Billing rule\",\"enum\":[\"per_call\",\"per_token\",\"per_second\"],\"example\":\"per_second\"},\"credits_reserved\":{\"type\":\"number\",\"description\":\"Estimated credits consumed\",\"minimum\":0,\"example\":53.38},\"user_group\":{\"type\":\"string\",\"description\":\"User group category\",\"example\":\"default\"}}}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"example\":{\"prompt\":\"The person in the image slowly turns their head and smiles\",\"image_start\":\"https://example.com/portrait.jpg\",\"duration\":5,\"quality\":\"720p\"}},\"kling-v4-reference-to-video\":{\"model\":\"kling-v4-reference-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"kling-v4-reference-to-video API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/kling/kling-v4-reference-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt, up to 2500 characters Reference syntax: Use <<<xxx>>> in the prompt to reference images and videos, for example: The person from <<<image_1>>> walks down the street following the camera movement in <<<video_1>>>\",\"maxLength\":2500,\"required\":true},\"video_urls\":{\"type\":\"array\",\"description\":\"Reference video URL array, up to 5 clips, corresponding in order to <<<video_1>>>, <<<video_2>>>, etc. in the prompt Video requirements: Formats: MP4 / MOV; Size: ≤ 200MB per clip; Duration: ≥ 3 seconds per clip, ≤ 30 seconds in total; Dimensions: width and height from 720px to 2160px; Frame rate: 24fps to 60fps; Video URLs must be directly accessible by the server\",\"maxItems\":5,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL array (style, scene, or subject references), corresponding in order to <<<image_1>>>, <<<image_2>>>, etc. in the prompt Constraints: Up to 10 images Note: Image URLs must be directly accessible by the server or trigger a direct download when accessed\",\"maxItems\":10,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds, from 3 to 30\",\"default\":5,\"minimum\":3,\"maximum\":30},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio Options: 16:9: Landscape; 9:16: Portrait; 1:1: Square; 21:9: Ultrawide\",\"enum\":[\"16:9\",\"9:16\",\"1:1\",\"21:9\"],\"default\":\"16:9\"},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier Options: 720p: Standard 720P; 1080p: High quality 1080P\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\"}},\"inputSchema\":{\"schema\":{\"type\":\"object\",\"required\":[\"prompt\"],\"properties\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt, up to 2500 characters\\n\\n**Reference syntax:** Use `<<<xxx>>>` in the prompt to reference images and videos, for example: `The person from <<<image_1>>> walks down the street following the camera movement in <<<video_1>>>`\",\"example\":\"The person from <<<image_1>>> walks down the street following the camera movement in <<<video_1>>>\",\"maxLength\":2500},\"video_urls\":{\"type\":\"array\",\"description\":\"Reference video URL array, up to `5` clips, corresponding in order to `<<<video_1>>>`, `<<<video_2>>>`, etc. in the prompt\\n\\n**Video requirements:**\\n- Formats: MP4 / MOV\\n- Size: ≤ 200MB per clip\\n- Duration: ≥ 3 seconds per clip, ≤ 30 seconds in total\\n- Dimensions: width and height from 720px to 2160px\\n- Frame rate: 24fps to 60fps\\n- Video URLs must be directly accessible by the server\",\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"maxItems\":5,\"example\":[\"https://example.com/reference.mp4\"]},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL array (style, scene, or subject references), corresponding in order to `<<<image_1>>>`, `<<<image_2>>>`, etc. in the prompt\\n\\n**Constraints:** Up to `10` images\\n**Note:** Image URLs must be directly accessible by the server or trigger a direct download when accessed\",\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"example\":[\"https://example.com/character.jpg\"],\"maxItems\":10},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds, from 3 to 30\",\"minimum\":3,\"maximum\":30,\"default\":5,\"example\":5},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio\\n\\n**Options:**\\n- `16:9`: Landscape\\n- `9:16`: Portrait\\n- `1:1`: Square\\n- `21:9`: Ultrawide\",\"enum\":[\"16:9\",\"9:16\",\"1:1\",\"21:9\"],\"example\":\"16:9\",\"default\":\"16:9\"},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier\\n\\n**Options:**\\n- `720p`: Standard 720P\\n- `1080p`: High quality 1080P\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\",\"example\":\"720p\"}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"responseSchema\":{\"schema\":{\"$ref\":\"#/$defs/VideoGenerationResponse\",\"$defs\":{\"VideoGenerationResponse\":{\"type\":\"object\",\"properties\":{\"created\":{\"type\":\"integer\",\"description\":\"Task creation timestamp\",\"example\":1757169743},\"id\":{\"type\":\"string\",\"description\":\"Task ID\",\"example\":\"task-unified-1757169743-7cvnl5zw\"},\"model\":{\"type\":\"string\",\"description\":\"Actual model name used\",\"example\":\"kling-v4-reference-to-video\"},\"object\":{\"type\":\"string\",\"enum\":[\"video.generation.task\"],\"description\":\"Task type\"},\"progress\":{\"type\":\"integer\",\"description\":\"Task progress percentage (0-100)\",\"minimum\":0,\"maximum\":100,\"example\":0},\"status\":{\"type\":\"string\",\"description\":\"Task status\",\"enum\":[\"pending\",\"processing\",\"completed\",\"failed\"],\"example\":\"pending\"},\"task_info\":{\"$ref\":\"#/$defs/VideoTaskInfo\",\"description\":\"Video task details\"},\"type\":{\"type\":\"string\",\"enum\":[\"text\",\"image\",\"audio\",\"video\"],\"description\":\"Task output type\",\"example\":\"video\"},\"usage\":{\"$ref\":\"#/$defs/VideoUsage\",\"description\":\"Usage and billing information\"}}},\"VideoTaskInfo\":{\"type\":\"object\",\"properties\":{\"estimated_time\":{\"type\":\"integer\",\"description\":\"Estimated completion time (seconds)\",\"minimum\":0,\"example\":300},\"video_duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds)\",\"example\":9}}},\"VideoUsage\":{\"type\":\"object\",\"description\":\"Usage and billing information\",\"properties\":{\"billing_rule\":{\"type\":\"string\",\"description\":\"Billing rule\",\"enum\":[\"per_call\",\"per_token\",\"per_second\"],\"example\":\"per_second\"},\"credits_reserved\":{\"type\":\"number\",\"description\":\"Estimated credits consumed\",\"minimum\":0,\"example\":53.38},\"user_group\":{\"type\":\"string\",\"description\":\"User group category\",\"example\":\"default\"}}}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"example\":{\"prompt\":\"Keep the same motion style as <<<video_1>>> and replace the background with a snowy scene\",\"video_urls\":[\"https://example.com/reference.mp4\"],\"duration\":5,\"aspect_ratio\":\"16:9\",\"quality\":\"720p\"}},\"kling-v4-text-to-video\":{\"model\":\"kling-v4-text-to-video\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"kling-v4-text-to-video API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/kling/kling-v4-text-to-video\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing the video to generate Note: Maximum 2500 characters\",\"maxLength\":2500,\"required\":true},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds. Defaults to 5 seconds Range: Integer from 3 to 30\",\"default\":5,\"minimum\":3,\"maximum\":30},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio Options: 16:9: Landscape; 9:16: Portrait; 1:1: Square; 21:9: Ultrawide\",\"enum\":[\"16:9\",\"9:16\",\"1:1\",\"21:9\"],\"default\":\"16:9\"},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier Options: 720p: Standard 720P; 1080p: High quality 1080P\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\"}},\"inputSchema\":{\"schema\":{\"type\":\"object\",\"required\":[\"prompt\"],\"properties\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text prompt describing the video to generate\\n\\n**Note:**\\n- Maximum `2500` characters\",\"example\":\"A cat running on a grassy field under bright sunshine\",\"maxLength\":2500},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds. Defaults to `5` seconds\\n\\n**Range:**\\n- Integer from `3` to `30`\",\"minimum\":3,\"maximum\":30,\"default\":5,\"example\":5},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio\\n\\n**Options:**\\n- `16:9`: Landscape\\n- `9:16`: Portrait\\n- `1:1`: Square\\n- `21:9`: Ultrawide\",\"enum\":[\"16:9\",\"9:16\",\"1:1\",\"21:9\"],\"example\":\"16:9\",\"default\":\"16:9\"},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier\\n\\n**Options:**\\n- `720p`: Standard 720P\\n- `1080p`: High quality 1080P\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\",\"example\":\"720p\"}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"responseSchema\":{\"schema\":{\"$ref\":\"#/$defs/VideoGenerationResponse\",\"$defs\":{\"VideoGenerationResponse\":{\"type\":\"object\",\"properties\":{\"created\":{\"type\":\"integer\",\"description\":\"Task creation timestamp\",\"example\":1757169743},\"id\":{\"type\":\"string\",\"description\":\"Task ID\",\"example\":\"task-unified-1757169743-7cvnl5zw\"},\"model\":{\"type\":\"string\",\"description\":\"Actual model name used\",\"example\":\"kling-v4-text-to-video\"},\"object\":{\"type\":\"string\",\"enum\":[\"video.generation.task\"],\"description\":\"Task type\"},\"progress\":{\"type\":\"integer\",\"description\":\"Task progress percentage (0-100)\",\"minimum\":0,\"maximum\":100,\"example\":0},\"status\":{\"type\":\"string\",\"description\":\"Task status\",\"enum\":[\"pending\",\"processing\",\"completed\",\"failed\"],\"example\":\"pending\"},\"task_info\":{\"$ref\":\"#/$defs/VideoTaskInfo\",\"description\":\"Video task details\"},\"type\":{\"type\":\"string\",\"enum\":[\"text\",\"image\",\"audio\",\"video\"],\"description\":\"Task output type\",\"example\":\"video\"},\"usage\":{\"$ref\":\"#/$defs/VideoUsage\",\"description\":\"Usage and billing information\"}}},\"VideoTaskInfo\":{\"type\":\"object\",\"properties\":{\"estimated_time\":{\"type\":\"integer\",\"description\":\"Estimated completion time (seconds)\",\"minimum\":0,\"example\":300},\"video_duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds)\",\"example\":5}}},\"VideoUsage\":{\"type\":\"object\",\"description\":\"Usage and billing information\",\"properties\":{\"billing_rule\":{\"type\":\"string\",\"description\":\"Billing rule\",\"enum\":[\"per_call\",\"per_token\",\"per_second\"],\"example\":\"per_second\"},\"credits_reserved\":{\"type\":\"number\",\"description\":\"Estimated credits consumed\",\"minimum\":0,\"example\":53.38},\"user_group\":{\"type\":\"string\",\"description\":\"User group category\",\"example\":\"default\"}}}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"example\":{\"prompt\":\"A cat running on a grassy field under bright sunshine\",\"duration\":5,\"aspect_ratio\":\"16:9\",\"quality\":\"720p\"}},\"kling-v4-video-edit\":{\"model\":\"kling-v4-video-edit\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"kling-v4-video-edit API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/kling/kling-v4-video-edit\",\"required\":[\"prompt\",\"video_urls\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Editing instructions, up to 2500 characters Reference syntax: Use <<<xxx>>> in the prompt to reference images and videos, for example: Replace the coat worn by the person in <<<video_1>>> with the style in <<<image_1>>>\",\"maxLength\":2500,\"required\":true},\"video_urls\":{\"type\":\"array\",\"description\":\"Video URL array for editing. Exactly 1 clip is supported, referenced as <<<video_1>>> in the prompt Video requirements: Formats: MP4 / MOV; Size: ≤ 200MB; Duration: 3 to 30 seconds; Dimensions: width and height from 720px to 2160px; Frame rate: 24fps to 60fps; The video URL must be directly accessible by the server\",\"minItems\":1,\"maxItems\":1,\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL array (style references) Constraints: Up to 10 images Note: Image URLs must be directly accessible by the server or trigger a direct download when accessed\",\"maxItems\":10,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"duration\":{\"type\":\"integer|string\",\"description\":\"Output video duration in seconds. Defaults to auto Values: Integer: 3 to 30 seconds; auto: Match the original video duration\",\"default\":\"auto\",\"minimum\":3,\"maximum\":30},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier Options: 720p: Standard 720P; 1080p: High quality 1080P\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\"}},\"inputSchema\":{\"schema\":{\"type\":\"object\",\"required\":[\"prompt\",\"video_urls\"],\"properties\":{\"prompt\":{\"type\":\"string\",\"description\":\"Editing instructions, up to 2500 characters\\n\\n**Reference syntax:** Use `<<<xxx>>>` in the prompt to reference images and videos, for example: `Replace the coat worn by the person in <<<video_1>>> with the style in <<<image_1>>>`\",\"example\":\"Adjust the color to warm tones and add a cinematic feel\",\"maxLength\":2500},\"video_urls\":{\"type\":\"array\",\"description\":\"Video URL array for editing. Exactly `1` clip is supported, referenced as `<<<video_1>>>` in the prompt\\n\\n**Video requirements:**\\n- Formats: MP4 / MOV\\n- Size: ≤ 200MB\\n- Duration: 3 to 30 seconds\\n- Dimensions: width and height from 720px to 2160px\\n- Frame rate: 24fps to 60fps\\n- The video URL must be directly accessible by the server\",\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"minItems\":1,\"maxItems\":1,\"example\":[\"https://example.com/original.mp4\"]},\"image_urls\":{\"type\":\"array\",\"description\":\"Reference image URL array (style references)\\n\\n**Constraints:** Up to `10` images\\n**Note:** Image URLs must be directly accessible by the server or trigger a direct download when accessed\",\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"example\":[\"https://example.com/style_ref.jpg\"],\"maxItems\":10},\"duration\":{\"description\":\"Output video duration in seconds. Defaults to `auto`\\n\\n**Values:**\\n- Integer: `3` to `30` seconds\\n- `auto`: Match the original video duration\",\"oneOf\":[{\"type\":\"integer\",\"minimum\":3,\"maximum\":30},{\"type\":\"string\",\"enum\":[\"auto\"]}],\"default\":\"auto\",\"example\":\"auto\"},\"quality\":{\"type\":\"string\",\"description\":\"Resolution tier\\n\\n**Options:**\\n- `720p`: Standard 720P\\n- `1080p`: High quality 1080P\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\",\"example\":\"720p\"}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"responseSchema\":{\"schema\":{\"$ref\":\"#/$defs/VideoGenerationResponse\",\"$defs\":{\"VideoGenerationResponse\":{\"type\":\"object\",\"properties\":{\"created\":{\"type\":\"integer\",\"description\":\"Task creation timestamp\",\"example\":1757169743},\"id\":{\"type\":\"string\",\"description\":\"Task ID\",\"example\":\"task-unified-1757169743-7cvnl5zw\"},\"model\":{\"type\":\"string\",\"description\":\"Actual model name used\",\"example\":\"kling-v4-video-edit\"},\"object\":{\"type\":\"string\",\"enum\":[\"video.generation.task\"],\"description\":\"Task type\"},\"progress\":{\"type\":\"integer\",\"description\":\"Task progress percentage (0-100)\",\"minimum\":0,\"maximum\":100,\"example\":0},\"status\":{\"type\":\"string\",\"description\":\"Task status\",\"enum\":[\"pending\",\"processing\",\"completed\",\"failed\"],\"example\":\"pending\"},\"task_info\":{\"$ref\":\"#/$defs/VideoTaskInfo\",\"description\":\"Video task details\"},\"type\":{\"type\":\"string\",\"enum\":[\"text\",\"image\",\"audio\",\"video\"],\"description\":\"Task output type\",\"example\":\"video\"},\"usage\":{\"$ref\":\"#/$defs/VideoUsage\",\"description\":\"Usage and billing information\"}}},\"VideoTaskInfo\":{\"type\":\"object\",\"properties\":{\"estimated_time\":{\"type\":\"integer\",\"description\":\"Estimated completion time (seconds)\",\"minimum\":0,\"example\":300},\"video_duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds)\",\"example\":9}}},\"VideoUsage\":{\"type\":\"object\",\"description\":\"Usage and billing information\",\"properties\":{\"billing_rule\":{\"type\":\"string\",\"description\":\"Billing rule\",\"enum\":[\"per_call\",\"per_token\",\"per_second\"],\"example\":\"per_second\"},\"credits_reserved\":{\"type\":\"number\",\"description\":\"Estimated credits consumed\",\"minimum\":0,\"example\":63.92},\"user_group\":{\"type\":\"string\",\"description\":\"User group category\",\"example\":\"default\"}}}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"example\":{\"prompt\":\"Adjust the color to warm tones and add a cinematic feel\",\"video_urls\":[\"https://example.com/original.mp4\"],\"quality\":\"720p\"}},\"qwen-audio-3.1-tts-flash\":{\"model\":\"qwen-audio-3.1-tts-flash\",\"kind\":\"audio\",\"path\":\"/v1/audios/generations\",\"title\":\"Qwen Audio 3.1 TTS Flash Speech Synthesis\",\"docs\":\"https://evolink.ai/docs/en/api-manual/audio-series/qwen-audio-tts/qwen-audio-3.1-tts-flash\",\"required\":[],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text to synthesize Constraints: Maximum 5000 characters; Keep punctuation in long text: long continuous passages without sentence breaks may be truncated upstream at about 1500 output tokens (about 120 seconds of audio). The task still reports success and is billed for the tokens actually generated; the gateway cannot detect this truncation; You can also use input. At least one non-empty text field is required; supplying just one is recommended. Different contents in both fields return 400 (parameter_conflict); Text must be in a language supported by the selected voice; otherwise pronunciatio…\",\"maxLength\":5000},\"input\":{\"type\":\"string\",\"description\":\"Alias for prompt, with the same length limits and usage rules; Provide at least one non-empty text field, prompt or input; If both are supplied, their contents must match; otherwise 400 (parameter_conflict) is returned\",\"maxLength\":5000},\"voice\":{\"type\":\"string\",\"description\":\"Voice name, case-sensitive; 68 system voices; see the [voice list](/en/api-manual/audio-series/qwen-audio-tts/qwen-audio-3.1-tts-flash-voices) for names, gender, and use cases; Defaults to longanhuan_v3.1 if omitted; You can also supply a voice you created with [Voice Enrollment](/en/api-manual/audio-series/qwen-audio-tts/voice-enrollment): cloned voices follow qwen-audio-3.1-tts-flash-{prefix}-{32-character-id}, and designed voices follow qwen-audio-3.1-tts-flash-vd-{prefix}-{32-character-id}. Only the account that created the voice can use it. Voices from other models, such as qwen-tts-vd-……\",\"default\":\"longanhuan_v3.1\"},\"response_format\":{\"type\":\"string\",\"description\":\"Output audio format: mp3, wav, or opus; defaults to mp3; opus uses an Ogg Opus container; You can also use format. Supplying just one field is recommended; conflicting values return 400 (parameter_conflict)\",\"enum\":[\"mp3\",\"wav\",\"opus\"],\"default\":\"mp3\"},\"format\":{\"type\":\"string\",\"description\":\"Alias for response_format; supports mp3, wav, and opus; Defaults to mp3 when neither field is supplied; If both fields are supplied, their values must match; otherwise 400 (parameter_conflict) is returned\",\"enum\":[\"mp3\",\"wav\",\"opus\"]},\"sample_rate\":{\"type\":\"integer\",\"description\":\"Output sample rate (Hz); 22050 and 44100 are not supported when response_format is opus; Omitted or null uses the default; 0 or a value outside the list returns 400\",\"enum\":[8000,12000,16000,22050,24000,44100,48000,null],\"default\":24000},\"volume\":{\"type\":\"integer\",\"description\":\"Volume, from 0 to 100\",\"default\":50,\"minimum\":0,\"maximum\":100},\"speech_rate\":{\"type\":\"number\",\"description\":\"Speech rate multiplier; 1.0: normal speed (default); 2.0: double speed; 0.5: half speed Range: 0.5 to 2.0. Adjusting speech rate does not change output token count\",\"default\":1,\"minimum\":0.5,\"maximum\":2},\"pitch\":{\"type\":\"number\",\"description\":\"Pitch multiplier; 1.0: default pitch; Above 1.0 raises pitch; below 1.0 lowers it Range: 0.5 to 2.0 Changing pitch also changes speech rate and audio duration; Higher pitch speeds up speech and shortens audio; lower pitch slows it down and lengthens audio. Duration varies approximately inversely with the square of the pitch value; For a sentence lasting about 2.8 seconds at 1.0: 0.8 is about 4.3 seconds, 1.2 about 2.1 seconds, 0.5 about 10.9 seconds, and 2.0 about 0.7 seconds; Small adjustments between 0.8 and 1.2 are recommended; values near 0.5 or 2.0 make speech noticeably too slow or too…\",\"default\":1,\"minimum\":0.5,\"maximum\":2},\"instruction\":{\"type\":\"string\",\"description\":\"Natural-language instructions to control emotion, tone, character, dialect, and other delivery choices Constraints: Maximum 100 billing characters: Han characters (including Japanese kanji and Korean hanja) count as 2; other characters count as 1, including kana and Hangul (about 50 Han characters or 100 English characters). Exceeding the limit returns 400 Examples: 用欢快、热情的语气说 (speak cheerfully and enthusiastically); 请用上海话表达 (use Shanghainese; multilingual and dialect voices); Speak slowly in a calm and gentle tone Instructions do not count toward input tokens, but can change the generated au…\"},\"language\":{\"type\":\"string\",\"description\":\"Target-language hint to improve the reading of numbers, abbreviations, and symbols, and synthesis in less common languages For example, with zh, 110 in hello, this is 110 is read as “yao yao ling” in Chinese | Value | Language | Value | Language | |---|---|---|---| | zh | Chinese | th | Thai | | en | English | id | Indonesian | | fr | French | vi | Vietnamese | | de | German | es | Spanish | | ja | Japanese | it | Italian | | ko | Korean | ms | Malay | | ru | Russian | fil | Filipino | | pt | Portuguese | ar | Arabic | The model detects the language if omitted; this parameter does not transla…\",\"enum\":[\"zh\",\"en\",\"fr\",\"de\",\"ja\",\"ko\",\"ru\",\"pt\",\"th\",\"id\",\"vi\",\"es\",\"it\",\"ms\",\"fil\",\"ar\"]},\"enable_ssml\":{\"type\":\"boolean\",\"description\":\"Parse prompt as SSML When enabled, SSML tags can be used, such as <break time=\\\"1s\\\"/> for a pause: <speak>欢迎收听今天的节目。<break time=\\\"1s\\\"/>我们马上开始。</speak> Pauses inserted with SSML do not count toward output tokens\",\"default\":false},\"hot_fix\":{\"type\":\"object\",\"description\":\"Custom pronunciation and text replacement to correct polyphonic characters, proper names, and other pronunciations; pronunciation: annotate words with pinyin (separate syllables with spaces and mark tones with digits, such as tian1 qi4) to override the default pronunciation; replace: replace specified words before synthesis. Synthesis and billing use the replaced text, which must also stay within 5000 characters; exceeding the limit returns 400 (prompt_too_long) The two lists may contain at most 200 entries in total, counted as key-value pairs within the objects. Exceeding the limit returns 4…\",\"properties\":{\"pronunciation\":{\"type\":\"array\",\"description\":\"Custom pronunciation list; each item is an object such as {\\\"word\\\": \\\"pinyin\\\"}\",\"items\":{\"type\":\"object\"}},\"replace\":{\"type\":\"array\",\"description\":\"Text replacement list; each item is an object such as {\\\"original word\\\": \\\"replacement text\\\"}\",\"items\":{\"type\":\"object\"}}}},\"enable_aigc_tag\":{\"type\":\"boolean\",\"description\":\"Embed an invisible AIGC marker in generated audio (applies to wav / mp3 / opus)\",\"default\":false}},\"inputSchema\":{\"schema\":{\"type\":\"object\",\"required\":[],\"description\":\"Provide at least one non-empty text field, `prompt` or `input`; if both are supplied, their contents must match. If both `response_format` and `format` are supplied, their values must match.\",\"anyOf\":[{\"required\":[\"prompt\"],\"properties\":{\"prompt\":{\"pattern\":\"\\\\S\"}}},{\"required\":[\"input\"],\"properties\":{\"input\":{\"pattern\":\"\\\\S\"}}}],\"properties\":{\"prompt\":{\"type\":\"string\",\"description\":\"Text to synthesize\\n\\n**Constraints:**\\n- Maximum `5000` characters\\n- Keep punctuation in long text: long continuous passages without sentence breaks may be truncated upstream at about `1500` output tokens (about 120 seconds of audio). The task still reports success and is billed for the tokens actually generated; the gateway cannot detect this truncation\\n- You can also use `input`. At least one non-empty text field is required; supplying just one is recommended. Different contents in both fields return `400` (`parameter_conflict`)\\n- Text must be in a language supported by the selected voice; otherwise pronunciation may be incorrect\\n\\n**Emotion and paralinguistic tags:** Embed tags directly in the text without extra parameters; tag text counts toward billing characters\\n- **Control tags**: Set the emotion or style of the following text until the next control tag. `[sad]` sad, `[amazed]` amazed, `[deep and loud shouting]` deep, loud shouting, `[trembling]` trembling, `[angry]` angry, `[excited]` excited, `[sarcastic]` sarcastic, `[curious]` curious, `[like dracula]` low and eerie, `[bored]` bored, `[tired]` tired, `[scornful]` scornful, `[shouting]` shouting, `[asmr]` soft ASMR whispers, `[panicked]` panicked, `[mischievously]` mischievous, `[empathetic]` empathetic, `[whispers]` whispering, `[reluctantly]` reluctant, `[crying]` crying, `[serious]` serious, `[very slowly]` very slowly, `[very fast]` very fast\\n- **Paralinguistic tags**: Insert a vocal effect at this position without changing the emotion of the surrounding text. `[gasp]` gasp, `[sighing]` sigh, `[clears throat]` clear the throat, `[giggles]` giggle, `[laughing]` laugh, `[cough]` cough, `[snorts]` snort\\n\\n**Example:** `[excited]今天的天气真不错![laughing]我们一起出去玩吧!`\\n\\nWhen `enable_ssml` is `true`, this field is parsed as SSML\",\"maxLength\":5000,\"example\":\"我家的后面有一个很大的花园。\"},\"input\":{\"type\":\"string\",\"description\":\"Alias for `prompt`, with the same length limits and usage rules\\n\\n- Provide at least one non-empty text field, `prompt` or `input`\\n- If both are supplied, their contents must match; otherwise `400` (`parameter_conflict`) is returned\",\"maxLength\":5000,\"example\":\"我家的后面有一个很大的花园。\"},\"voice\":{\"type\":\"string\",\"description\":\"Voice name, case-sensitive\\n\\n- 68 system voices; see the [voice list](/en/api-manual/audio-series/qwen-audio-tts/qwen-audio-3.1-tts-flash-voices) for names, gender, and use cases\\n- Defaults to `longanhuan_v3.1` if omitted\\n- You can also supply a voice you created with [Voice Enrollment](/en/api-manual/audio-series/qwen-audio-tts/voice-enrollment): cloned voices follow `qwen-audio-3.1-tts-flash-{prefix}-{32-character-id}`, and designed voices follow `qwen-audio-3.1-tts-flash-vd-{prefix}-{32-character-id}`. Only the account that created the voice can use it. Voices from other models, such as `qwen-tts-vd-…` from `qwen-voice-design`, return `400` (`invalid_voice`). Missing voices or voices owned by another account return `404` (`voice_not_found`)\\n- Custom voices expire by default `6 hours` after the creation task completes; synthesis after expiry returns `404` (`voice_expired`). Create a new voice with Voice Enrollment\",\"default\":\"longanhuan_v3.1\",\"example\":\"longanhuan_v3.1\"},\"response_format\":{\"type\":\"string\",\"description\":\"Output audio format: `mp3`, `wav`, or `opus`; defaults to `mp3`\\n\\n- `opus` uses an Ogg Opus container\\n- You can also use `format`. Supplying just one field is recommended; conflicting values return `400` (`parameter_conflict`)\",\"enum\":[\"mp3\",\"wav\",\"opus\"],\"default\":\"mp3\",\"example\":\"mp3\"},\"format\":{\"type\":\"string\",\"description\":\"Alias for `response_format`; supports `mp3`, `wav`, and `opus`\\n\\n- Defaults to `mp3` when neither field is supplied\\n- If both fields are supplied, their values must match; otherwise `400` (`parameter_conflict`) is returned\",\"enum\":[\"mp3\",\"wav\",\"opus\"],\"example\":\"mp3\"},\"sample_rate\":{\"type\":[\"integer\",\"null\"],\"description\":\"Output sample rate (Hz)\\n\\n- `22050` and `44100` are not supported when `response_format` is `opus`\\n- Omitted or `null` uses the default; `0` or a value outside the list returns `400`\",\"enum\":[8000,12000,16000,22050,24000,44100,48000,null],\"default\":24000,\"example\":24000},\"volume\":{\"type\":\"integer\",\"description\":\"Volume, from `0` to `100`\",\"minimum\":0,\"maximum\":100,\"default\":50,\"example\":50},\"speech_rate\":{\"type\":\"number\",\"description\":\"Speech rate multiplier\\n\\n- `1.0`: normal speed (default)\\n- `2.0`: double speed; `0.5`: half speed\\n\\nRange: `0.5` to `2.0`. Adjusting speech rate does not change output token count\",\"minimum\":0.5,\"maximum\":2,\"default\":1,\"example\":1},\"pitch\":{\"type\":\"number\",\"description\":\"Pitch multiplier\\n\\n- `1.0`: default pitch\\n- Above `1.0` raises pitch; below `1.0` lowers it\\n\\nRange: `0.5` to `2.0`\\n\\n**Changing pitch also changes speech rate and audio duration**\\n- Higher pitch speeds up speech and shortens audio; lower pitch slows it down and lengthens audio. Duration varies approximately inversely with the square of the pitch value\\n- For a sentence lasting about 2.8 seconds at `1.0`: `0.8` is about 4.3 seconds, `1.2` about 2.1 seconds, `0.5` about 10.9 seconds, and `2.0` about 0.7 seconds\\n- Small adjustments between `0.8` and `1.2` are recommended; values near `0.5` or `2.0` make speech noticeably too slow or too fast\\n- If `speech_rate` is also supplied with a value other than `1.0`, `pitch` has no effect; the two cannot be combined\\n- Adjusting pitch does not change output token count\",\"minimum\":0.5,\"maximum\":2,\"default\":1,\"example\":1},\"instruction\":{\"type\":\"string\",\"description\":\"Natural-language instructions to control emotion, tone, character, dialect, and other delivery choices\\n\\n**Constraints:**\\n- Maximum `100` billing characters: Han characters (including Japanese kanji and Korean hanja) count as 2; other characters count as 1, including kana and Hangul (about 50 Han characters or 100 English characters). Exceeding the limit returns `400`\\n\\n**Examples:**\\n- `用欢快、热情的语气说` (speak cheerfully and enthusiastically)\\n- `请用上海话表达` (use Shanghainese; multilingual and dialect voices)\\n- `Speak slowly in a calm and gentle tone`\\n\\nInstructions do not count toward input tokens, but can change the generated audio duration and therefore output tokens\\n\\n> The parameter is `instruction` (singular); `instructions` returns `400`\",\"example\":\"用欢快、热情的语气说\"},\"language\":{\"type\":\"string\",\"description\":\"Target-language hint to improve the reading of numbers, abbreviations, and symbols, and synthesis in less common languages\\n\\nFor example, with `zh`, `110` in `hello, this is 110` is read as “yao yao ling” in Chinese\\n\\n| Value | Language | Value | Language |\\n|---|---|---|---|\\n| `zh` | Chinese | `th` | Thai |\\n| `en` | English | `id` | Indonesian |\\n| `fr` | French | `vi` | Vietnamese |\\n| `de` | German | `es` | Spanish |\\n| `ja` | Japanese | `it` | Italian |\\n| `ko` | Korean | `ms` | Malay |\\n| `ru` | Russian | `fil` | Filipino |\\n| `pt` | Portuguese | `ar` | Arabic |\\n\\nThe model detects the language if omitted; this parameter does not translate text\",\"enum\":[\"zh\",\"en\",\"fr\",\"de\",\"ja\",\"ko\",\"ru\",\"pt\",\"th\",\"id\",\"vi\",\"es\",\"it\",\"ms\",\"fil\",\"ar\"],\"example\":\"zh\"},\"enable_ssml\":{\"type\":\"boolean\",\"description\":\"Parse `prompt` as SSML\\n\\nWhen enabled, SSML tags can be used, such as `<break time=\\\"1s\\\"/>` for a pause:\\n`<speak>欢迎收听今天的节目。<break time=\\\"1s\\\"/>我们马上开始。</speak>`\\n\\nPauses inserted with SSML do not count toward output tokens\",\"default\":false,\"example\":false},\"hot_fix\":{\"type\":\"object\",\"description\":\"Custom pronunciation and text replacement to correct polyphonic characters, proper names, and other pronunciations\\n\\n- `pronunciation`: annotate words with pinyin (separate syllables with spaces and mark tones with digits, such as `tian1 qi4`) to override the default pronunciation\\n- `replace`: replace specified words before synthesis. Synthesis and billing use the replaced text, which must also stay within `5000` characters; exceeding the limit returns `400` (`prompt_too_long`)\\n\\nThe two lists may contain at most `200` entries in total, counted as key-value pairs within the objects. Exceeding the limit returns `400` (`invalid_parameter`)\\n\\nProvide at least one list. Each provided list must be a non-empty array of objects in `{\\\"word\\\": \\\"value\\\"}` form\\n\\n**Example:**\\n```json\\n{\\n \\\"pronunciation\\\": [{\\\"天气\\\": \\\"tian1 qi4\\\"}],\\n \\\"replace\\\": [{\\\"今天\\\": \\\"金天\\\"}]\\n}\\n```\",\"properties\":{\"pronunciation\":{\"type\":\"array\",\"description\":\"Custom pronunciation list; each item is an object such as `{\\\"word\\\": \\\"pinyin\\\"}`\",\"items\":{\"type\":\"object\",\"additionalProperties\":{\"type\":\"string\"}},\"example\":[{\"天气\":\"tian1 qi4\"}]},\"replace\":{\"type\":\"array\",\"description\":\"Text replacement list; each item is an object such as `{\\\"original word\\\": \\\"replacement text\\\"}`\",\"items\":{\"type\":\"object\",\"additionalProperties\":{\"type\":\"string\"}},\"example\":[{\"今天\":\"金天\"}]}}},\"enable_aigc_tag\":{\"type\":\"boolean\",\"description\":\"Embed an invisible AIGC marker in generated audio (applies to `wav` / `mp3` / `opus`)\",\"default\":false,\"example\":false}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"responseSchema\":{\"schema\":{\"$ref\":\"#/$defs/QwenAudioTtsResponse\",\"$defs\":{\"QwenAudioTtsResponse\":{\"type\":\"object\",\"properties\":{\"created\":{\"type\":\"integer\",\"description\":\"Task creation timestamp\",\"example\":1790000000},\"id\":{\"type\":\"string\",\"description\":\"Task ID\",\"example\":\"task-unified-1790000000-abcd1234\"},\"model\":{\"type\":\"string\",\"description\":\"Model actually used\",\"example\":\"qwen-audio-3.1-tts-flash\"},\"object\":{\"type\":\"string\",\"enum\":[\"audio.generation.task\"],\"description\":\"Specific task object type\"},\"progress\":{\"type\":\"integer\",\"description\":\"Task progress percentage (0–100)\",\"minimum\":0,\"maximum\":100,\"example\":0},\"status\":{\"type\":\"string\",\"description\":\"Task status\",\"enum\":[\"pending\",\"processing\",\"completed\",\"failed\"],\"example\":\"pending\"},\"task_info\":{\"$ref\":\"#/$defs/AudioTaskInfo\",\"description\":\"Audio task details\"},\"type\":{\"type\":\"string\",\"enum\":[\"audio\"],\"description\":\"Task output type\",\"example\":\"audio\"},\"usage\":{\"$ref\":\"#/$defs/AudioUsage\",\"description\":\"Usage and billing information\"}}},\"AudioTaskInfo\":{\"type\":\"object\",\"properties\":{\"estimated_time\":{\"type\":\"integer\",\"description\":\"Estimated completion time in seconds; increases with text length, up to about `90` seconds\",\"minimum\":0,\"example\":3},\"audio_type\":{\"type\":\"string\",\"description\":\"Audio task type\",\"example\":\"tts\"}}},\"AudioUsage\":{\"type\":\"object\",\"description\":\"Usage information\",\"properties\":{\"credits_reserved\":{\"type\":\"number\",\"description\":\"Credits reserved based on text length; settled against actual token usage on completion, with excess refunded or shortfall charged\",\"minimum\":0,\"example\":0.0144}}}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"example\":{\"prompt\":\"我家的后面有一个很大的花园。\"}},\"veo-3.1-lite-generate-preview\":{\"model\":\"veo-3.1-lite-generate-preview\",\"kind\":\"video\",\"path\":\"/v1/videos/generations\",\"title\":\"Veo-3.1-Lite-Generate-Preview API\",\"docs\":\"https://evolink.ai/docs/en/api-manual/video-series/veo3.1/veo-3.1-lite-generate-preview-generate\",\"required\":[\"prompt\"],\"params\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the video, up to 2000 tokens. Counted with cl100k; tokens are not characters. Google lists English as the supported prompt language. EvoLink does not reject requests based on prompt language; results in other languages are not guaranteed.\",\"required\":true},\"image_urls\":{\"type\":\"array\",\"description\":\"Input image URLs for image-to-video Notes: Up to 2 images per request: 1 image is used as the first frame, 2 images are used as the first and last frames; Image size: no larger than 10 MB; Supported file formats: .jpg, .jpeg, .png\",\"maxItems\":2,\"items\":{\"type\":\"string\",\"format\":\"uri\"}},\"generation_type\":{\"type\":\"string\",\"description\":\"Generation mode. When omitted it is inferred from the number of images: TEXT: Text-to-video (input images, if any, are not used); FIRST&LAST: First-last frame, 1-2 images REFERENCE (reference images) is not supported by this model and returns 400\",\"enum\":[\"TEXT\",\"FIRST&LAST\"]},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio. auto is the same as omitting aspect_ratio: no ratio is specified and the model decides\",\"enum\":[\"auto\",\"16:9\",\"9:16\"]},\"generate_audio\":{\"type\":\"boolean\",\"description\":\"Whether to generate audio, default true. Generating audio increases the per-second rate\",\"default\":true},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds, default 4. Longer videos cost more\",\"enum\":[4,6,8],\"default\":4},\"n\":{\"type\":\"integer\",\"description\":\"Number of videos to generate, default 1. Each video is billed separately\",\"default\":1,\"minimum\":1,\"maximum\":4},\"quality\":{\"type\":\"string\",\"description\":\"Output resolution, default 720p. 1080p has a higher per-second rate; 4k is not supported by this model\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\"},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed used to reproduce generation results\",\"minimum\":1,\"maximum\":4294967295},\"negative_prompt\":{\"type\":\"string\",\"description\":\"Negative prompt describing content to exclude from the video\"},\"person_generation\":{\"type\":\"string\",\"description\":\"Person generation control. When omitted, the upstream default is allow_adult. allow_adult: allow adults only; dont_allow: do not generate videos containing people or faces\",\"enum\":[\"allow_adult\",\"dont_allow\"]},\"resize_mode\":{\"type\":\"string\",\"description\":\"Image resize mode for image-to-video. When omitted, the upstream default is pad. pad: add padding to fit the output aspect ratio; crop: center-crop to fit the output aspect ratio. Requires an input image; providing this parameter without an image returns 400\",\"enum\":[\"pad\",\"crop\"]}},\"inputSchema\":{\"schema\":{\"type\":\"object\",\"required\":[\"prompt\"],\"properties\":{\"prompt\":{\"type\":\"string\",\"description\":\"Prompt describing the video, up to `2000` tokens. Counted with cl100k; tokens are not characters. Google lists English as the supported prompt language. EvoLink does not reject requests based on prompt language; results in other languages are not guaranteed.\",\"example\":\"A golden retriever puppy running through a sunlit meadow, slow motion, cinematic lighting\"},\"image_urls\":{\"type\":\"array\",\"description\":\"Input image URLs for image-to-video\\n\\n**Notes:**\\n- Up to `2` images per request: `1` image is used as the first frame, `2` images are used as the first and last frames\\n- Image size: no larger than `10 MB`\\n- Supported file formats: `.jpg`, `.jpeg`, `.png`\",\"items\":{\"type\":\"string\",\"format\":\"uri\"},\"maxItems\":2,\"example\":[\"https://example.com/first-frame.jpg\"]},\"generation_type\":{\"type\":\"string\",\"description\":\"Generation mode. When omitted it is inferred from the number of images:\\n- `TEXT`: Text-to-video (input images, if any, are not used)\\n- `FIRST&LAST`: First-last frame, 1-2 images\\n\\n`REFERENCE` (reference images) is not supported by this model and returns `400`\",\"enum\":[\"TEXT\",\"FIRST&LAST\"]},\"aspect_ratio\":{\"type\":\"string\",\"description\":\"Video aspect ratio. `auto` is the same as omitting `aspect_ratio`: no ratio is specified and the model decides\",\"enum\":[\"auto\",\"16:9\",\"9:16\"]},\"generate_audio\":{\"type\":\"boolean\",\"description\":\"Whether to generate audio, default `true`. Generating audio increases the per-second rate\",\"default\":true},\"duration\":{\"type\":\"integer\",\"description\":\"Video duration in seconds, default `4`. Longer videos cost more\",\"enum\":[4,6,8],\"default\":4},\"n\":{\"type\":\"integer\",\"description\":\"Number of videos to generate, default `1`. Each video is billed separately\",\"minimum\":1,\"maximum\":4,\"default\":1},\"quality\":{\"type\":\"string\",\"description\":\"Output resolution, default `720p`. `1080p` has a higher per-second rate; `4k` is not supported by this model\",\"enum\":[\"720p\",\"1080p\"],\"default\":\"720p\"},\"seed\":{\"type\":\"integer\",\"description\":\"Random seed used to reproduce generation results\",\"minimum\":1,\"maximum\":4294967295},\"negative_prompt\":{\"type\":\"string\",\"description\":\"Negative prompt describing content to exclude from the video\"},\"person_generation\":{\"type\":\"string\",\"description\":\"Person generation control. When omitted, the upstream default is `allow_adult`. `allow_adult`: allow adults only; `dont_allow`: do not generate videos containing people or faces\",\"enum\":[\"allow_adult\",\"dont_allow\"]},\"resize_mode\":{\"type\":\"string\",\"description\":\"Image resize mode for image-to-video. When omitted, the upstream default is `pad`. `pad`: add padding to fit the output aspect ratio; `crop`: center-crop to fit the output aspect ratio. Requires an input image; providing this parameter without an image returns `400`\",\"enum\":[\"pad\",\"crop\"]}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"responseSchema\":{\"schema\":{\"$ref\":\"#/$defs/VideoGenerationResponse\",\"$defs\":{\"VideoGenerationResponse\":{\"type\":\"object\",\"properties\":{\"created\":{\"type\":\"integer\",\"description\":\"Task creation timestamp\",\"example\":1757169743},\"id\":{\"type\":\"string\",\"description\":\"Task ID\",\"example\":\"task-unified-1757169743-7cvnl5zw\"},\"model\":{\"type\":\"string\",\"description\":\"Actual model name used\",\"example\":\"veo-3.1-lite-generate-preview\"},\"object\":{\"type\":\"string\",\"enum\":[\"video.generation.task\"],\"description\":\"Specific type of the task\"},\"progress\":{\"type\":\"integer\",\"description\":\"Task progress percentage (0-100)\",\"minimum\":0,\"maximum\":100,\"example\":0},\"status\":{\"type\":\"string\",\"description\":\"Task status\",\"enum\":[\"pending\",\"processing\",\"completed\",\"failed\"],\"example\":\"processing\"},\"task_info\":{\"$ref\":\"#/$defs/VideoTaskInfo\",\"description\":\"Video task details\"},\"type\":{\"type\":\"string\",\"enum\":[\"text\",\"image\",\"audio\",\"video\"],\"description\":\"Output type of the task\",\"example\":\"video\"},\"usage\":{\"$ref\":\"#/$defs/VideoUsage\",\"description\":\"Usage and billing information\"}}},\"VideoTaskInfo\":{\"type\":\"object\",\"properties\":{\"estimated_time\":{\"type\":\"integer\",\"description\":\"Estimated completion time (seconds)\",\"minimum\":0,\"example\":600},\"video_duration\":{\"type\":\"integer\",\"description\":\"Video duration (seconds)\",\"example\":4}}},\"VideoUsage\":{\"type\":\"object\",\"description\":\"Usage and billing information\",\"properties\":{\"billing_rule\":{\"type\":\"string\",\"description\":\"Billing rule\",\"enum\":[\"per_call\",\"per_token\",\"per_second\"],\"example\":\"per_call\"},\"credits_reserved\":{\"type\":\"number\",\"description\":\"Estimated credits consumed\",\"minimum\":0,\"example\":12.24},\"user_group\":{\"type\":\"string\",\"description\":\"User group category\",\"example\":\"default\"}}}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"example\":{\"prompt\":\"A golden retriever puppy running through a sunlit meadow, slow motion, cinematic lighting\"}},\"voice-enrollment\":{\"model\":\"voice-enrollment\",\"kind\":\"audio\",\"path\":\"/v1/audios/generations\",\"title\":\"Voice Enrollment: Create a Custom Voice\",\"docs\":\"https://evolink.ai/docs/en/api-manual/audio-series/qwen-audio-tts/voice-enrollment\",\"required\":[\"preferred_name\"],\"params\":{\"audio_url\":{\"type\":\"string\",\"description\":\"URL of the recording to clone. This field selects voice cloning and cannot be supplied together with voice_prompt URL requirements: HTTP or HTTPS, publicly accessible without authentication; Local or private-network addresses return 400 (invalid_media_url); Maximum 2048 characters; Non-HTTP(S) protocols such as FTP return 400 (invalid_media_url); URLs only, not Base64; a Base64 data URI returns 400 (invalid_parameter) Audio requirements (the task may fail if unmet): WAV, MP3, or M4A; At most 60 seconds; insufficient voiced content can also fail (a 2-second recording failed in testing); File s…\",\"maxLength\":2048,\"format\":\"uri\"},\"preferred_name\":{\"type\":\"string\",\"description\":\"Voice name prefix Constraints: 1–10 English letters or digits; underscores and other symbols are not supported; Uppercase letters are converted to lowercase; Does not need to be unique Full generated name: qwen-audio-3.1-tts-flash-{preferred_name}-{32-character-id} for cloning, or qwen-audio-3.1-tts-flash-vd-{preferred_name}-{32-character-id} for design For example, myvoice produces a cloned name such as qwen-audio-3.1-tts-flash-myvoice-5996beec833d41f4982158347ba97fae\",\"maxLength\":10,\"required\":true},\"language\":{\"type\":\"string\",\"description\":\"For cloning, the spoken language of the recording helps the model extract the voice more accurately. For design, this sets the voice's language preference; use the same language as preview_text Defaults to zh if omitted\",\"enum\":[\"zh\",\"en\",\"ja\",\"ko\",\"de\",\"fr\",\"it\",\"ru\",\"pt\",\"es\"]},\"target_model\":{\"type\":\"string\",\"description\":\"TTS model that will use the voice. Only one value is currently supported, and it is used if omitted; other values return 400 | Value | Description | |-----|------| | qwen-audio-3.1-tts-flash | Qwen Audio 3.1 TTS Flash, non-streaming (default and only value) |\",\"enum\":[\"qwen-audio-3.1-tts-flash\"],\"default\":\"qwen-audio-3.1-tts-flash\"},\"voice_prompt\":{\"type\":\"string\",\"description\":\"Description of the voice characteristics. This field selects voice design and cannot be supplied together with audio_url Constraints: Maximum 500 characters; Chinese and English characters each count as 1; Chinese or English descriptions are recommended Suggested dimensions: gender, age, pitch, speech rate, emotion, qualities (resonant, crisp, raspy, rounded, sweet, deep), and use case (news, advertising, audiobooks, animated characters, voice assistants) Suggested descriptions: A calm middle-aged man with a slow pace and a deep, resonant voice, suitable for news or documentary narration; A g…\",\"maxLength\":500},\"preview_text\":{\"type\":\"string\",\"description\":\"Preview text; the entire text is synthesized as preview audio Constraints: 15–200 characters; Chinese and English characters each count as 1; Longer text takes longer: about 12 seconds for 30 characters and 49 seconds for 200 characters; Use the same language as language\",\"minLength\":15,\"maxLength\":200},\"sample_rate\":{\"type\":\"integer\",\"description\":\"Preview audio sample rate (Hz), fixed at 24000; Omitted, 0, or null is treated as omitted and uses the default 24000; Other sample rates return 400 (invalid_parameter)\",\"enum\":[24000,0,null],\"default\":24000},\"response_format\":{\"type\":\"string\",\"description\":\"Preview audio format, fixed at wav; Omitted, an empty string \\\"\\\", or null is treated as omitted and uses the default wav; Other formats return 400 (invalid_parameter)\",\"enum\":[\"wav\",\"\",null],\"default\":\"wav\"}},\"requestShapes\":[{\"required\":[\"audio_url\",\"preferred_name\"],\"params\":[\"audio_url\",\"preferred_name\",\"language\",\"target_model\"]},{\"required\":[\"voice_prompt\",\"preview_text\",\"preferred_name\"],\"params\":[\"voice_prompt\",\"preview_text\",\"sample_rate\",\"response_format\",\"preferred_name\",\"language\",\"target_model\"]}],\"inputSchema\":{\"schema\":{\"type\":\"object\",\"properties\":{\"audio_url\":{\"type\":\"string\",\"format\":\"uri\",\"maxLength\":2048,\"example\":\"https://your-cdn.com/samples/my-voice.wav\",\"description\":\"URL of the recording to clone. This field selects **voice cloning** and cannot be supplied together with `voice_prompt`\\n\\n**URL requirements:**\\n- HTTP or HTTPS, publicly accessible without authentication\\n- Local or private-network addresses return `400` (`invalid_media_url`)\\n- Maximum `2048` characters\\n- Non-HTTP(S) protocols such as FTP return `400` (`invalid_media_url`)\\n- URLs only, not Base64; a Base64 data URI returns `400` (`invalid_parameter`)\\n\\n**Audio requirements** (the task may fail if unmet):\\n- WAV, MP3, or M4A\\n- At most 60 seconds; insufficient voiced content can also fail (a 2-second recording failed in testing)\\n- File size at most `10 MB`\\n- Sample rate of at least `16 kHz`\\n- Must contain clear human speech; silence, music, and other non-speech audio are rejected\\n\\n**Recording recommendations:**\\n- 10–20 seconds, including at least 5 seconds of continuous, clear reading, with pauses no longer than 2 seconds\\n- Mono; for stereo recordings, only the first channel is used\\n- No background music, noise, or other voices; speak normally, do not sing\\n\\nIf audio cannot be downloaded or does not meet the requirements, the task fails and credits are fully refunded\\n\\n**Only clone your own voice or a voice you have explicit permission to clone**\",\"pattern\":\"[^\\\\u0009-\\\\u000D\\\\u0020\\\\u0085\\\\u00A0\\\\u1680\\\\u2000-\\\\u200A\\\\u2028\\\\u2029\\\\u202F\\\\u205F\\\\u3000]\"},\"preferred_name\":{\"type\":\"string\",\"maxLength\":10,\"pattern\":\"^[a-zA-Z0-9]+$\",\"example\":\"myvoice\",\"description\":\"Voice name prefix\\n\\n**Constraints:**\\n- 1–10 English letters or digits; underscores and other symbols are not supported\\n- Uppercase letters are converted to lowercase\\n- Does not need to be unique\\n\\nFull generated name: `qwen-audio-3.1-tts-flash-{preferred_name}-{32-character-id}` for cloning, or `qwen-audio-3.1-tts-flash-vd-{preferred_name}-{32-character-id}` for design\\n\\nFor example, `myvoice` produces a cloned name such as `qwen-audio-3.1-tts-flash-myvoice-5996beec833d41f4982158347ba97fae`\"},\"language\":{\"type\":\"string\",\"enum\":[\"zh\",\"en\",\"ja\",\"ko\",\"de\",\"fr\",\"it\",\"ru\",\"pt\",\"es\"],\"example\":\"zh\",\"description\":\"For cloning, the spoken language of the recording helps the model extract the voice more accurately. For design, this sets the voice's language preference; use the same language as `preview_text`\\n\\nDefaults to `zh` if omitted\"},\"target_model\":{\"type\":\"string\",\"enum\":[\"qwen-audio-3.1-tts-flash\"],\"default\":\"qwen-audio-3.1-tts-flash\",\"example\":\"qwen-audio-3.1-tts-flash\",\"description\":\"TTS model that will use the voice. Only one value is currently supported, and it is used if omitted; other values return `400`\\n\\n| Value | Description |\\n|-----|------|\\n| `qwen-audio-3.1-tts-flash` | Qwen Audio 3.1 TTS Flash, non-streaming (default and only value) |\"},\"voice_prompt\":{\"type\":\"string\",\"maxLength\":500,\"example\":\"沉稳的中年男性播音员,音色低沉浑厚,富有磁性,语速平稳,吐字清晰\",\"description\":\"Description of the voice characteristics. This field selects **voice design** and cannot be supplied together with `audio_url`\\n\\n**Constraints:**\\n- Maximum `500` characters; Chinese and English characters each count as 1\\n- Chinese or English descriptions are recommended\\n\\n**Suggested dimensions:** gender, age, pitch, speech rate, emotion, qualities (resonant, crisp, raspy, rounded, sweet, deep), and use case (news, advertising, audiobooks, animated characters, voice assistants)\\n\\n**Suggested descriptions:**\\n- `A calm middle-aged man with a slow pace and a deep, resonant voice, suitable for news or documentary narration`\\n- `A gentle, articulate woman around 30 years old, with an even tone, suitable for audiobooks`\",\"pattern\":\"[^\\\\u0009-\\\\u000D\\\\u0020\\\\u0085\\\\u00A0\\\\u1680\\\\u2000-\\\\u200A\\\\u2028\\\\u2029\\\\u202F\\\\u205F\\\\u3000]\"},\"preview_text\":{\"type\":\"string\",\"minLength\":15,\"maxLength\":200,\"example\":\"各位听众朋友,大家好,欢迎收听晚间新闻。\",\"description\":\"Preview text; the **entire** text is synthesized as preview audio\\n\\n**Constraints:**\\n- `15`–`200` characters; Chinese and English characters each count as 1\\n- Longer text takes longer: about 12 seconds for 30 characters and 49 seconds for 200 characters\\n- Use the same language as `language`\",\"pattern\":\"[^\\\\u0009-\\\\u000D\\\\u0020\\\\u0085\\\\u00A0\\\\u1680\\\\u2000-\\\\u200A\\\\u2028\\\\u2029\\\\u202F\\\\u205F\\\\u3000]\"},\"sample_rate\":{\"type\":[\"integer\",\"null\"],\"enum\":[24000,0,null],\"default\":24000,\"example\":24000,\"description\":\"Preview audio sample rate (Hz), fixed at `24000`\\n\\n- Omitted, `0`, or `null` is treated as omitted and uses the default `24000`\\n- Other sample rates return `400` (`invalid_parameter`)\"},\"response_format\":{\"type\":[\"string\",\"null\"],\"enum\":[\"wav\",\"\",null],\"default\":\"wav\",\"example\":\"wav\",\"description\":\"Preview audio format, fixed at `wav`\\n\\n- Omitted, an empty string `\\\"\\\"`, or `null` is treated as omitted and uses the default `wav`\\n- Other formats return `400` (`invalid_parameter`)\"}},\"required\":[\"preferred_name\"],\"oneOf\":[{\"required\":[\"audio_url\",\"preferred_name\"]},{\"required\":[\"voice_prompt\",\"preview_text\",\"preferred_name\"]}]},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"responseSchema\":{\"schema\":{\"$ref\":\"#/$defs/VoiceEnrollmentResponse\",\"$defs\":{\"VoiceEnrollmentResponse\":{\"type\":\"object\",\"properties\":{\"created\":{\"type\":\"integer\",\"description\":\"Task creation timestamp\",\"example\":1775123456},\"id\":{\"type\":\"string\",\"description\":\"Task ID\",\"example\":\"task-unified-1775123456-abcd1234\"},\"model\":{\"type\":\"string\",\"description\":\"Model actually used\",\"example\":\"voice-enrollment\"},\"object\":{\"type\":\"string\",\"enum\":[\"audio.generation.task\"],\"description\":\"Specific task object type\"},\"progress\":{\"type\":\"integer\",\"description\":\"Task progress percentage (0–100)\",\"minimum\":0,\"maximum\":100,\"example\":0},\"status\":{\"type\":\"string\",\"description\":\"Task status\",\"enum\":[\"pending\",\"processing\",\"completed\",\"failed\"],\"example\":\"pending\"},\"task_info\":{\"$ref\":\"#/$defs/AudioTaskInfo\",\"description\":\"Audio task details\"},\"type\":{\"type\":\"string\",\"enum\":[\"audio\"],\"description\":\"Task output type\",\"example\":\"audio\"},\"usage\":{\"$ref\":\"#/$defs/AudioUsage\",\"description\":\"Usage and billing information\"}}},\"AudioTaskInfo\":{\"type\":\"object\",\"properties\":{\"estimated_time\":{\"type\":\"integer\",\"description\":\"Estimated completion time in seconds. Conservative estimates: cloning usually takes 15–30 seconds; design takes longer with more preview text, about 12 seconds for 30 characters and 49 seconds for 200 characters\",\"minimum\":0,\"example\":60},\"audio_type\":{\"type\":\"string\",\"description\":\"Request mode: `audio_url` selects `voice_clone`, and `voice_prompt` selects `voice_design`; matches `voice_type` in the task result\",\"example\":\"voice_clone\",\"enum\":[\"voice_clone\",\"voice_design\"]}}},\"AudioUsage\":{\"type\":\"object\",\"description\":\"Usage information\",\"properties\":{\"credits_reserved\":{\"type\":\"number\",\"description\":\"Estimated credits. Charged per request, with the same price for cloning and design; fully refunded if the task fails\",\"minimum\":0,\"example\":0.001}}}}},\"unresolved_refs\":false,\"dialect\":\"3.1.0\"},\"example\":{\"audio_url\":\"https://your-cdn.com/samples/my-voice.wav\",\"preferred_name\":\"myvoice\"}}}}";
|