Pollo AI

Estimate the generation credits required for the requested output. Returns credit units only and does not submit a generation task.

pollo_estimate_generation_cost

Generate a video. Each successful call submits a new generation task and consumes generation credits. Unless the user names or asks to compare models, use the default brand `bytedance` and model `seedance-2-0` directly; it covers text-to-video, start/end-frame image-to-video, multimodal references, 4-15 second output, and resolutions up to 4K. Call pollo_list_models with the selected model and capability type when the user selects another model, provides reference media, or you need its fields or constraints; use type `text2video`, `image2video`, or `ref2video`. `brand`, `model`, and `numOutputs` are top-level tool arguments; generation parameters go inside `input`. For default text-to-video, `input.prompt` is required, while `input.duration` (default `5`), `input.resolution` (default `480p`), `input.aspectRatio` (default `16:9`), and `input.generateAudio` (default `false`) are optional. For image-to-video, put the start-frame URL in `input.image` and an optional end-frame URL in `input.imageTail`; use the listed fields and constraints before constructing `input.refs` for reference-to-video. Image inputs must be HTTPS URLs. For a ChatGPT attachment, call pollo_upload_attachment first and use its accessURL as the image input. Keep pollo_upload_widget as the interactive fallback. After a successful submission, the returned result updates automatically; do not call any status tool. Each call submits one independent generation task. For multiple models, call this tool once per model. Do not use numOutputs to combine different models; numOutputs only creates multiple outputs from the same model in one task. Videos take a few minutes. If current entitlements are insufficient, explain only that the generation is unavailable.

pollo_generate_video

Generate an image. Each successful call submits a new generation task and consumes generation credits. Unless the user names or asks to compare models, use the default brand `google` and model `nano-banana-pro` directly; it covers general image generation, people and portraits, reference-image editing, and resolutions up to 4K. Call pollo_list_models with the selected model and capability type only when you need its fields or constraints; use type `text2image` or `image2image`. `brand`, `model`, and `numOutputs` are top-level tool arguments; generation parameters go inside `input`. For the default model, `input.prompt` is required, while `input.images` accepts up to 8 HTTPS image URLs and `input.aspectRatio` (default `1:1`) and `input.resolution` (default `1K`, allowed `1K`/`2K`/`4K`) are optional. Image inputs must be HTTPS URLs. For a ChatGPT attachment, call pollo_upload_attachment first and use its accessURL as the image input. Keep pollo_upload_widget as the interactive fallback. After a successful submission, the returned result updates automatically; do not call any status tool. Each call submits one independent generation task. For multiple models, call this tool once per model. Do not use numOutputs to combine different models; numOutputs only creates multiple outputs from the same model in one task. If current entitlements are insufficient, explain only that the generation is unavailable.

pollo_generate_image

Get the available generation credit balance and current subscription entitlements as JSON (data only — renders no UI).

pollo_account_status

Check generation status (data only — renders no UI) with the `taskId` returned by pollo_generate_*. On MCP-Apps hosts you normally do NOT need to call this: task-status UI polls it itself and updates in place.

pollo_get_generation_status

List Pollo models available for generation. Each row contains the brand, model, capability type, accepted fields, and constraints. Filter by capability type and/or model alias.

pollo_list_models

Open an interactive uploader UI so the user can upload one or more local images (multi-select, up to `maxImages`, default 9). Accepted formats are JPG, PNG, WebP, GIF, BMP and TIFF, up to 50 MB per image — these limits are fixed and not configurable. The user can drop an image from the list before confirming. When they finish and click Continue, it sends the resulting public HTTPS URL(s) into the chat for you to use as image input(s) in pollo_generate_*. Use this whenever the user wants to generate from a local/attached image — this remote server cannot read local files, so a plain HTTPS URL or this uploader is required. Pass `maxImages` to cap how many images the user may upload (e.g. a model that takes a single reference image → maxImages: 1). After calling it, just wait for the user to confirm the upload; do not poll or call other tools.

pollo_upload_widget

Validate and display the generation task owned by the current user. The initial result includes status, input, and prompt; unfinished tasks continue updating in the widget until every output succeeds or fails.

pollo_task_status

Upload one image attached directly to the ChatGPT conversation and return a stable HTTPS accessURL for generation input. Accepts raster images up to 50 MiB.

pollo_upload_attachment

Upload an image/video input for a generation. Four modes: (1) pass `browserUpload: true` with `filename` + `contentType` to get { sign, uploadKey } for a browser-direct PUT into the upload inbox — this is what the uploader widget uses (bytes never pass through the MCP channel, so there is no message-size ceiling); (2) pass `uploadKey` (and nothing else) to confirm that direct upload: the server validates it and returns { accessURL }; (3) pass `dataBase64` (a base64 data URL of the file) and the server uploads it for you, returning { accessURL } — no CORS to configure, but the bytes travel through the MCP message, so the gateway caps this at roughly 3.5 MB per file; (4) pass just `filename` to only get a presigned URL for the asset bucket: returns { sign, accessURL }, and you PUT the raw bytes to `sign` yourself (for programmatic/agent callers). Use `accessURL` as the image field in a generate tool. The remote server cannot read your local disk. Note: /file/sign may be limited to certain accounts.

pollo_upload_image