Veo 3.1 Lite is Google’s Lite member of the Veo 3 video-generation line. It synthesizes a video with audio from a natural-language description or an input image. The output is a generated clip, not a textual analysis of an existing recording. The maker’s Lite model card refers to Veo 3 for the underlying architecture, training material and known limitations, while the Lite-specific documentation defines its own generation features and limits.
The referenced architecture uses latent diffusion over temporal audio representations and spatio-temporal video representations. The base model was trained on audio, video and images, with captions at different levels of detail, and filtered and deduplicated training material. This explains the joined visual-and-audio generation purpose. It does not disclose a Lite-specific parameter count or establish that every generated movement follows physical reality. For a practical scene, decide the visible action and the corresponding sound together.
The exact Lite documentation gives a text-input limit of 1,024 tokens and one output video. The Lite column in the generation guide lists 4-, 6- and 8-second durations, with 720p as the default and 1080p requiring an 8-second clip. Landscape 16:9 is the default aspect ratio and portrait 9:16 is also listed; output is documented at 24 frames per second. Native audio is always on in that flow. These values belong to the producer’s named Lite workflow, not to an unrelated Veo edition or a separately measured application response.
Lite does not support 4K output or video extension. The parameter table also marks the multi-reference referenceImages feature and a video input for extension as unavailable in the Lite column. An initial image can establish the starting frame; the table lists a lastFrame image together with that initial image for a transition. Keep this frame-control path distinct from mixing several style or subject references. The producer’s people-generation settings are mode-specific: the Lite table lists allow_all for text-to-video and allow_adult for image-to-video and interpolation, while regional rules can further restrict that documented profile. Choose the starting image to match the first scene you actually want, with the subject, framing and visible details prepared before asking for motion.
For text-to-video, describe the subject, its action, the environment and the intended style. Add camera position and movement, framing, focus and light when they matter. An original product scene could keep the object centered while the camera approaches one material detail and the surrounding light changes gently. Identify the initial state, the main action and the final moment so the short clip resolves one coherent idea. A lengthy collection of unrelated actions is a different task from a focused shot.
For image-to-video, provide a clear initial frame and explain what should move and what should remain stable. Specify the subject’s motion and any camera movement separately. If using a final-frame constraint, prepare a compatible end composition and describe the transition between them. Inspect the result rather than assuming that a requested identity, position or shape remains identical throughout the clip. The referenced model card identifies complete consistency in complex scenes and complex motion as a continuing challenge.
The prompt guide supports explicit cues for dialogue, sound effects and ambience. Put exact speech in quotation marks, identify the speaker and describe sounds in relation to the visible action. A sound effect and background atmosphere should not be confused with a spoken line. English is documented as fully supported for prompting, while other languages have not been evaluated in that guide. Review the audible words, timing and sound quality as part of the same artifact as the video rather than treating audio as a guaranteed faithful transcript of the prompt.
The producer workflow is asynchronous: a generation request returns an operation, and the completed result is obtained after its status reports completion. Keep the operation identity and inspect the returned clip. The guide describes two-day producer-side retention and SynthID marking, so a retained artifact should include the downloaded result, prompt, source images and selected settings. A seed can improve repeatability but does not guarantee determinism. Check subject continuity, action, framing, sound and the intended endpoint of the scene before using the clip in an edit; processing completion alone is not proof that the creative requirements were met.
", "aboutText": "Veo 3.1 Lite is Google’s Lite member of the Veo 3 video-generation line. It synthesizes a video with audio from a natural-language description or an input image. The output is a generated clip, not a textual analysis of an existing recording. The maker’s Lite model card refers to Veo 3 for the underlying architecture, training material and known limitations, while the Lite-specific documentation defines its own generation features and limits.\n\nThe referenced architecture uses latent diffusion over temporal audio representations and spatio-temporal video representations. The base model was trained on audio, video and images, with captions at different levels of detail, and filtered and deduplicated training material. This explains the joined visual-and-audio generation purpose. It does not disclose a Lite-specific parameter count or establish that every generated movement follows physical reality. For a practical scene, decide the visible action and the corresponding sound together.\n\nThe exact Lite documentation gives a text-input limit of 1,024 tokens and one output video. The Lite column in the generation guide lists 4-, 6- and 8-second durations, with 720p as the default and 1080p requiring an 8-second clip. Landscape 16:9 is the default aspect ratio and portrait 9:16 is also listed; output is documented at 24 frames per second. Native audio is always on in that flow. These values belong to the producer’s named Lite workflow, not to an unrelated Veo edition or a separately measured application response.\n\nLite does not support 4K output or video extension. The parameter table also marks the multi-reference referenceImages feature and a video input for extension as unavailable in the Lite column. An initial image can establish the starting frame; the table lists a lastFrame image together with that initial image for a transition. Keep this frame-control path distinct from mixing several style or subject references. The producer’s people-generation settings are mode-specific: the Lite table lists allow_all for text-to-video and allow_adult for image-to-video and interpolation, while regional rules can further restrict that documented profile. Choose the starting image to match the first scene you actually want, with the subject, framing and visible details prepared before asking for motion.\n\nFor text-to-video, describe the subject, its action, the environment and the intended style. Add camera position and movement, framing, focus and light when they matter. An original product scene could keep the object centered while the camera approaches one material detail and the surrounding light changes gently. Identify the initial state, the main action and the final moment so the short clip resolves one coherent idea. A lengthy collection of unrelated actions is a different task from a focused shot.\n\nFor image-to-video, provide a clear initial frame and explain what should move and what should remain stable. Specify the subject’s motion and any camera movement separately. If using a final-frame constraint, prepare a compatible end composition and describe the transition between them. Inspect the result rather than assuming that a requested identity, position or shape remains identical throughout the clip. The referenced model card identifies complete consistency in complex scenes and complex motion as a continuing challenge.\n\nThe prompt guide supports explicit cues for dialogue, sound effects and ambience. Put exact speech in quotation marks, identify the speaker and describe sounds in relation to the visible action. A sound effect and background atmosphere should not be confused with a spoken line. English is documented as fully supported for prompting, while other languages have not been evaluated in that guide. Review the audible words, timing and sound quality as part of the same artifact as the video rather than treating audio as a guaranteed faithful transcript of the prompt.\n\nThe producer workflow is asynchronous: a generation request returns an operation, and the completed result is obtained after its status reports completion. Keep the operation identity and inspect the returned clip. The guide describes two-day producer-side retention and SynthID marking, so a retained artifact should include the downloaded result, prompt, source images and selected settings. A seed can improve repeatability but does not guarantee determinism. Check subject continuity, action, framing, sound and the intended endpoint of the scene before using the clip in an edit; processing completion alone is not proof that the creative requirements were met.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "47287494994e6ade1f3c698a34d7019dc4b7571fa232d842b5c974605d43ff26", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "google/veo-3.1-liteTurn a scene description into a 4-, 6- or 8-second video at 720p.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Veo 3.1 Lite is Google’s Lite member of the Veo 3 video-generation line. It synthesizes a video with audio from a natural-language description or an input image. The output is a generated clip, not a textual analysis of an existing recording. The maker’s Lite model card refers to Veo 3 for the underlying architecture, training material and known limitations, while the Lite-specific documentation defines its own generation features and limits.
The referenced architecture uses latent diffusion over temporal audio representations and spatio-temporal video representations. The base model was trained on audio, video and images, with captions at different levels of detail, and filtered and deduplicated training material. This explains the joined visual-and-audio generation purpose. It does not disclose a Lite-specific parameter count or establish that every generated movement follows physical reality. For a practical scene, decide the visible action and the corresponding sound together.
The exact Lite documentation gives a text-input limit of 1,024 tokens and one output video. The Lite column in the generation guide lists 4-, 6- and 8-second durations, with 720p as the default and 1080p requiring an 8-second clip. Landscape 16:9 is the default aspect ratio and portrait 9:16 is also listed; output is documented at 24 frames per second. Native audio is always on in that flow. These values belong to the producer’s named Lite workflow, not to an unrelated Veo edition or a separately measured application response.
Lite does not support 4K output or video extension. The parameter table also marks the multi-reference referenceImages feature and a video input for extension as unavailable in the Lite column. An initial image can establish the starting frame; the table lists a lastFrame image together with that initial image for a transition. Keep this frame-control path distinct from mixing several style or subject references. The producer’s people-generation settings are mode-specific: the Lite table lists allow_all for text-to-video and allow_adult for image-to-video and interpolation, while regional rules can further restrict that documented profile. Choose the starting image to match the first scene you actually want, with the subject, framing and visible details prepared before asking for motion.
For text-to-video, describe the subject, its action, the environment and the intended style. Add camera position and movement, framing, focus and light when they matter. An original product scene could keep the object centered while the camera approaches one material detail and the surrounding light changes gently. Identify the initial state, the main action and the final moment so the short clip resolves one coherent idea. A lengthy collection of unrelated actions is a different task from a focused shot.
For image-to-video, provide a clear initial frame and explain what should move and what should remain stable. Specify the subject’s motion and any camera movement separately. If using a final-frame constraint, prepare a compatible end composition and describe the transition between them. Inspect the result rather than assuming that a requested identity, position or shape remains identical throughout the clip. The referenced model card identifies complete consistency in complex scenes and complex motion as a continuing challenge.
The prompt guide supports explicit cues for dialogue, sound effects and ambience. Put exact speech in quotation marks, identify the speaker and describe sounds in relation to the visible action. A sound effect and background atmosphere should not be confused with a spoken line. English is documented as fully supported for prompting, while other languages have not been evaluated in that guide. Review the audible words, timing and sound quality as part of the same artifact as the video rather than treating audio as a guaranteed faithful transcript of the prompt.
The producer workflow is asynchronous: a generation request returns an operation, and the completed result is obtained after its status reports completion. Keep the operation identity and inspect the returned clip. The guide describes two-day producer-side retention and SynthID marking, so a retained artifact should include the downloaded result, prompt, source images and selected settings. A seed can improve repeatability but does not guarantee determinism. Check subject continuity, action, framing, sound and the intended endpoint of the scene before using the clip in an edit; processing completion alone is not proof that the creative requirements were met.
POST /v1/videostext, imagevideo| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits google/veo-3.1-lite | Default— |
Fieldprompt | Typestring | RequirementRequired | Values & limits Minimum length: 1 Maximum bytes: 10,000 Unit: UTF8bytes | Default— |
Fieldduration | Typeinteger | RequirementRequired | Values & limits 4, 6, 8 Unit: seconds | Default— |
Fieldresolution | Typestring | RequirementRequired | Values & limits 720p | Default— |
Fieldaspect_ratio | Typestring | RequirementRequired | Values & limits 16:9, 9:16 | Default— |
Fieldgenerate_audio | Typeboolean | RequirementRequired | Values & limits false | Default— |
Fieldframe_images | Typearray | RequirementOptional | Values & limits Conditions: Omit for text_to_video. When present: exactly one item {"type":"image_url","image_url":{"url":"<actual HTTPS URL>"},"frame_type":"first_frame"}; item has exactly type,image_url,frame_type; image_url has exactly url. No extra or duplicate keys. Only duration=4,resolution="720p",aspect_ratio="16:9",generate_audio=false. URL must parse with scheme https, nonempty hostname, no userinfo and no literal #; signed query and encoded path preserved. Source checks no input MIME, file size or pixel dimensions. | Default— |
Text to video · Required: prompt
Image to video · Required: prompt, frame_images
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, prompt, duration, resolution, aspect_ratio, generate_audio |
Parameterother_options | Contractfalse |
Parameterresolution | Contract720p |
Parameterprompt_max_bytes | Contract10000 |
Parameterduration | Contract4, 6, 8 |
Parameteraspect_ratio | Contract16:9, 9:16 |
Parametergenerate_audio | Contractfalse |
Parametermaterial_types | Contracttext, image |
Parameterparameters | Contract{"name":"model","type":"string","required":true,"default_known":false,"default":null,"enum_known":true,"enum":["google/veo-3.1-lite"],"availability":"source_interface"}, {"name":"prompt","type":"string","required":true,"default_known":false,"default":null,"enum_known":false,"enum":null,"availability":"source_interface","min_length":1,"maximum_bytes":10000,"maximum_length":null,"unit":"UTF8bytes"}, {"name":"duration","type":"integer","required":true,"default_known":false,"default":null,"enum_known":true,"enum":[4,6,8],"availability":"source_interface","unit":"seconds"}, {"name":"resolution","type":"string","required":true,"default_known":false,"default":null,"enum_known":true,"enum":["720p"],"availability":"source_interface"}, {"name":"aspect_ratio","type":"string","required":true,"default_known":false,"default":null,"enum_known":true,"enum":["16:9","9:16"],"availability":"source_interface"}, {"name":"generate_audio","type":"boolean","required":true,"default_known":false,"default":null,"enum_known":true,"enum":[false],"availability":"source_interface"}, {"name":"frame_images","type":"array","required":false,"default_known":false,"default":null,"enum_known":false,"enum":null,"availability":"source_interface","conditions":"Omit for text_to_video. When present: exactly one item {\\"type\\":\\"image_url\\",\\"image_url\\":{\\"url\\":\\"<actual HTTPS URL>\\"},\\"frame_type\\":\\"first_frame\\"}; item has exactly type,image_url,frame_type; image_url has exactly url. No extra or duplicate keys. Only duration=4,resolution=\\"720p\\",aspect_ratio=\\"16:9\\",generate_audio=false. URL must parse with scheme https, nonempty hostname, no userinfo and no literal #; signed query and encoded path preserved. Source checks no input MIME, file size or pixel dimensions."} |
Method aliases: /v1/videos/generations, /videos, /videos/generations
Lifecycle: submit_once_poll_original
GET /v1/videos/{request_id}
GET /v1/videos/generations/{request_id}
GET /v1/videos/{request_id}/content
GET /v1/videos/generations/{request_id}/content
Create once and save returned ID.
Poll original status; retain every completed asset and duration.
The displayed rates estimate the cost before generation. The final charge is calculated from the cost recorded for the original generation. Measured output duration and forecast quantities are not the final billable quantity.
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Forecast quantity | Generate audio | Resolution | Billing unit | Billing conditions | Charge |
|---|---|---|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Forecast quantity— | Generate audio— | Resolution— | Billing unit— | Billing conditions— | Charge Input · Input tokens · Estimate for comparison only — / 1K tokens Output · Output tokens · Estimate for comparison only — / 1K tokens Input · Cache read · Estimate for comparison only — / 1K tokens Input · Cache write · Estimate for comparison only — / 1K tokens Input · Cache write, 1 hour · Estimate for comparison only — / 1K tokens |
| ConfigurationVideo price | Rate schedule— | Forecast quantity— | Generate audio— | Resolution— | Billing unitper video second | Billing conditionsaudio: with_audio | Charge Output · Video price · Estimate for comparison only $0.16 per video second |
| ConfigurationVideo price | Rate schedule— | Forecast quantity— | Generate audio— | Resolution— | Billing unitper video second | Billing conditionsaudio: with_audio; resolution: 720p | Charge Output · Video price · Estimate for comparison only $0.1 per video second |
| ConfigurationVideo price | Rate schedule— | Forecast quantity— | Generate audio— | Resolution— | Billing unitper video second | Billing conditionsaudio: without_audio | Charge Output · Video price · Estimate for comparison only $0.1 per video second |
| ConfigurationUltra | Rate schedule— | Forecast quantityRequested configuration; estimate only. | Generate audioWithout audio | Resolution720p | Billing unitper output video second | Billing conditions— | Charge Output · Estimated output video second · Estimate for comparison only $0.06 per output video second The displayed rate estimates the cost before generation. The final charge is calculated from the cost recorded for the original generation. Physical video duration is not the billable quantity. |
| ConfigurationEstimated generation cost | Rate schedule— | Forecast quantityone generation estimate | Generate audio— | Resolution— | Billing unit— | Billing conditions— | Charge Output · Estimated generation cost · Estimate for comparison only $0.24 estimate before generation This estimate is not an additional charge or a fixed rate for the completed generation. |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Billing conditions | Charge |
|---|---|---|
| ConfigurationVideo price | Billing conditionsaudio: with_audio | Charge Output · Video price $0.16 per video second Published price reference for the configuration shown. Final charges follow the actual billed configuration. |
| ConfigurationVideo price | Billing conditionsaudio: without_audio | Charge Output · Video price $0.1 per video second Published price reference for the configuration shown. Final charges follow the actual billed configuration. |
| ConfigurationVideo price | Billing conditionsaudio: with_audio; resolution: 720p | Charge Output · Video price $0.1 per video second Published price reference for the configuration shown. Final charges follow the actual billed configuration. |
| ConfigurationVideo price | Billing conditionsaudio: without_audio; resolution: 720p | Charge Output · Video price $0.06 per video second Published price reference for the configuration shown. Final charges follow the actual billed configuration. |
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "google/veo-3.1-lite", "prompt": "A cat in a spacesuit walking on the Moon", "duration": 4, "resolution": "720p", "aspect_ratio": "16:9", "generate_audio": false}')\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/videos \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_IMAGE_URL:?Set the actual HTTPS URL of your first-frame image}"\nexport AILOOT_IMAGE_URL\npython3 - <<'PY_REQUEST'\nimport json,os,re\nfrom pathlib import Path\nfrom urllib.parse import urlsplit\nimage=os.environ["AILOOT_IMAGE_URL"]\ntry:\n parsed=urlsplit(image)\n valid=(image.startswith("https://") and parsed.scheme=="https" and bool(parsed.hostname)\n and parsed.username is None and parsed.password is None and "#" not in image\n and not any(ord(c)<32 or ord(c)==127 for c in image)\n and re.search(r"%(?![0-9A-Fa-f]{2})",image) is None)\nexcept ValueError:\n valid=False\nif not valid:\n raise SystemExit("Use your actual HTTPS image URL with a hostname, no userinfo and no fragment")\np={"model":"google/veo-3.1-lite","prompt":"The subject makes a slow, natural movement. Keep the opening composition.","duration":4,"resolution":"720p","aspect_ratio":"16:9","generate_audio":False,"frame_images":[{"type":"image_url","image_url":{"url":image},"frame_type":"first_frame"}]}\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False),encoding="utf-8")\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/videos \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("result.json").read_text())\nprint(json.dumps(r,ensure_ascii=False,indent=2))\nprint("Keep the complete JSON, headers and original returned id. Use the existing GET status tab for that original operation, then save every completed owned output. Never resubmit an unknown generation.")\nPY_RESULT\nmp4
GET /v1/videos/{request_id}GET /v1/videos/generations/{request_id}GET /v1/videos/{request_id}/contentGET /v1/videos/generations/{request_id}/contentset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_OPERATION_ID:?Set the actual Ailoot operation ID returned by creation}"\nexport AILOOT_OPERATION_ID\noperation_id=$(python3 -c 'import os,urllib.parse;print(urllib.parse.quote(os.environ["AILOOT_OPERATION_ID"],safe=""))')\ncurl --fail-with-body --silent --show-error "https://api.ailoot.ai/v1/videos/$operation_id" \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -o status.json\npython3 - <<'PY_STATUS'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("status.json").read_text())\nprint(json.dumps(r))\nif r.get("status")=="completed":\n for x in r.get("data",[]):print(x)\nPY_STATUS\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_STATUS_FILE:?Set the actual completed status JSON file}"\nexport AILOOT_STATUS_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\nfrom urllib.parse import urlsplit,urljoin\nf=Path(os.environ["AILOOT_STATUS_FILE"])\nif not f.is_file():raise SystemExit("Choose the actual completed status file")\nr=json.loads(f.read_text())\nif r.get("status")!="completed" or not isinstance(r.get("data"),list) or not r["data"]:raise SystemExit("Wait for a completed status with asset paths")\nurls=[]\nfor x in r["data"]:\n if not isinstance(x,str) or "\\n" in x or "\\r" in x:raise SystemExit("Invalid asset path")\n u=urljoin("https://api.ailoot.ai",x)\n z=urlsplit(u)\n if z.scheme!="https" or z.netloc!="api.ailoot.ai" or z.username or z.password:raise SystemExit("Use the actual Ailoot asset paths from status")\n urls.append(u)\nPath("asset-urls.txt").write_text("\\n".join(urls)+"\\n")\nPY_REQUEST\nindex=0\nwhile IFS= read -r asset_url; do\n curl --fail-with-body --silent --show-error "$asset_url" \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -o "video-${index}.mp4"\n index=$((index + 1))\ndone < asset-urls.txt\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_OPERATION_ID:?Set the actual Ailoot operation ID returned by creation}"\nexport AILOOT_OPERATION_ID\noperation_id=$(python3 -c 'import os,urllib.parse;print(urllib.parse.quote(os.environ["AILOOT_OPERATION_ID"],safe=""))')\ncurl --fail-with-body --silent --show-error "https://api.ailoot.ai/v1/videos/$operation_id/content" \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -o video.mp4\nSave every completed video or returned file; retrieve every actual returned asset URL.
Completed data[] contains all owned signed content URLs. Fetch each returned URL, or use the content endpoint with index set to an actual output index. A failed original job may return charge_pending_check; check that original job rather than creating it again. A valid AAC audio track can be present even with generate_audio=false; keep the complete original MP4 including that audio.
Read existing original job; never resubmit unknown send.
Maximum outputs: 4.
| Field | Type | Meaning |
|---|---|---|
Fieldid | Typestring | Meaning— |
Fieldobject | Typestring | Meaning— |
Fieldmodel | Typestring | Meaning— |
Fieldstatus | Typestring | Meaning— |
Fielddata[] | Typesigned content URL | Meaning— |
Fieldcharge_pending_check | Typeboolean | Meaning— |
Fielderror.code | Typestring | Meaning— |
Fielderror.message | Typestring | Meaning— |
Fieldoperation_id | Typestring | MeaningHTTP503 result_pending_check original status/content response: same original public video ID as id. |
Fielderror.type | Typestring | Meaningserver_error on HTTP503 result_pending_check. |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Response409 · video_not_ready | ConditionOriginal result content is not yet available | Next stepPoll the original returned ID and respect Retry-After. |
Responseserver_error | ConditionThe returned response says the operation or result requires a check | Next stepKeep the original returned operation/task ID, request headers and response; continue supported reads of that original operation. Do not resubmit the creation request. |
Response503 · result_pending_check | ConditionGET original status/content: task is not published, original job is not failed/cancelled/expired, and local state is unknown or original job status is completed. | Next stepKeep original id and operation_id (same public video ID), response and headers; read only the original status/content. Never submit a new generation request. |
Response422 · price_unavailable | ConditionA supplied frame_images object or its conditional profile fails parsing, or the complete parsed profile has no ready exact price card. | Next stepKeep model, prompt, duration, resolution, aspect_ratio and generate_audio. Add frame_images containing exactly one first_frame item in the specified object format. Set duration=4, resolution="720p", aspect_ratio="16:9" and generate_audio=false. This validation runs before the request is sent. |
Ailoot Ultra google/veo-3.1-lite
/v1/videos/generations, /videos, /videos/generations