List the Gemini image-generation models available to your API key (Nano Banana / Nano Banana Pro family), and the current default model.

Generate image(s) from a text prompt with a Gemini image model (Nano Banana / Nano Banana Pro). If the result will likely be refined iteratively, prefer gemini_interact (multi-turn) as the entry point.

Edit or compose images: provide one or more input images (paths or base64), plus a text instruction. For a SERIES of successive edits to the same image, prefer gemini_interact (multi-turn) — it keeps edit context and avoids re-processing the full image each round; use gemini_image_edit for one-off edits or composing multiple distinct inputs. Gemini over-preserves the input; there is no edit-strength control — for large structural changes, reroll with a different seed or more forceful wording.

Generate a consistent SET of images: a master image from master_prompt, then one image per scene that references the master so the subject/style stays consistent. Provide scenes (explicit per-image prompts) OR count (variations of the master).

Preferred tool for iterative or multi-step refinement of a single image — multi-turn generation/editing via Gemini's Interactions API. To refine, capture the returned interaction id and pass it as previous_interaction_id on the next call — do NOT start a new interaction or re-upload the image for each tweak. continue_last: true chains from this session's most recent interaction without threading the id. If a call times out on the client side, the generation usually still completes: the image plus a <image>.json sidecar recording its interaction id land in the output dir, and continue_last: true still resumes that interaction — check the output dir before re-issuing (a re-issue is a second billable generation). If a chained call 404s, this tool re-anchors itself on the prior output image and re-issues un-chained: success is reported as chain_recovered (the chain was the problem, and you get your image anyway); a second 404 is reported as the interaction id NOT being the cause (check the model id / files uri instead). Output is JPEG.

Generate a short video via the Gemini omni model (preview): text→video, image→video / reference→video (supply reference image[s]), or edit a prior video (task: "edit" + previous_interaction_id / continue_last). Output is written to disk as MP4 (video has no inline MCP block). Video runs long — use async: true to get a job_id immediately and poll gemini_get_result, or raise timeout_ms. Preview model: needs a funded account.

Generate music from a text prompt (mood, genre, instruments, structure, or lyrics inline) via a Lyria model (preview): lyria-3-clip-preview (~30s clips, default) or lyria-3-pro-preview (longer, WAV-capable). Written to disk as MP3/WAV (or returned inline). Runs long — use async: true + gemini_get_result, or raise timeout_ms. Preview model: needs a funded account.

Retrieve an async generation started with async: true. Pass the returned job_id: while running it reports status "running"; on completion it returns the normal result (image paths / inline images + meta); on failure it raises the recorded error. Jobs belong to your session and expire ~10 min after completion — if a job id is unknown, check the output dir / .json sidecar.

Upload an image (or video/audio) to the Gemini Files API ONCE and get back a reusable files/<id> reference. Use this instead of pasting base64 into a tool call: the reference is a short string, so no image bytes ever enter the conversation, and it can be reused across many generations until it expires (~48h). Provide exactly one of url (the server downloads it), data_base64, or path (a local file).

List the files currently uploaded to the Gemini Files API under this API key, with their files/<id> references, MIME types and expiry times. Retention is ~48h, so an entry that has vanished has expired rather than failed.

Delete an uploaded file from the Gemini Files API before its ~48h expiry. Any tool call still referencing it will then fail with a generic 404, so delete only references you are finished with.