All integrations
GE
Catalogue metadata onlyartificial intelligencev20260902_00

GEMINI

Gemini

Comprehensive Gemini integration supporting Veo 3 video generation, Gemini Flash text generation (Nano Banana), chat completions, and multimodal AI capabilities via the Google Gemini API.

Description is untrusted, display-only upstream metadata. It never becomes policy, OAuth scope authority, or an agent instruction.

Pakkawork boundary

Research catalogue metadata only. No Pakkawork OAuth, credential, host, quota, executor, or verifier is enabled.

No Pakkawork execution adapter is enabled. Hosted account-authorisation availability is workspace-specific and checked separately in the dashboard.Check workspace connection options
Attributed source

8

Action summaries

Display-only definitions

0

Trigger types

Not installed instances

2

Auth modes

Field names, never values

No

Execution

No runtime adapter

Authentication map

What setup is declared?

Only field names, types, and required markers are shown. Secret values, default auth URLs, credential material, and inferred OAuth scopes are excluded.
NO_AUTHAPI_KEY

NO_AUTH

Gemini

Provider setup

Developer setup

No fields declared in this snapshot.

User connection

No fields declared in this snapshot.

API_KEY

gemini_api_key

Provider setup

Developer setup

No fields declared in this snapshot.

User connection

  • API Keygeneric_api_key · stringRequired

Capability index

Actions and trigger definitions

Static summaries are available. Live schemas remain disabled until PROVIDER_HUB_API_KEY is configured server-side.

Showing 1–8 of 8 actions

Count Tokens (Gemini)

GEMINI_COUNT_TOKENS

Counts the number of tokens in text using Gemini tokenization. Useful for estimating costs, checking input limits, and optimizing prompts before making API calls.

Untrusted display-only summary

Embed Content (Gemini)

GEMINI_EMBED_CONTENT

Generates text embeddings using Gemini embedding models. Converts text into numerical vectors for semantic search, similarity comparison, clustering, and classification tasks.

Untrusted display-only summary

Generate Content (Gemini)

GEMINI_GENERATE_CONTENT

Generates text content or speech audio from prompts using Gemini models. Supports text generation models (Gemini Flash, Pro) and text-to-speech models with configurable parameters. Generated text is nested at results[i].response.data.text. Output may be wrapped in markdown fences (e.g., ```html...```) or preceded by e…

Untrusted display-only summary

Generate Image (Nano Banana)

GEMINI_GENERATE_IMAGE

Generates images from text prompts using Gemini models (Nano Banana). Supports models: 'gemini-2.5-flash-image' (GA stable, fast), 'gemini-3-pro-image-preview' (Nano Banana Pro - advanced with 4K resolution, thinking mode, up to 14 reference images), and 'gemini-2.0-flash-exp-image-generation' (2.0 Flash experimental)…

Untrusted display-only summary

Generate Videos (Veo)

GEMINI_GENERATE_VIDEOS

Generates videos from text prompts using Google's Veo models. Returns an operation_name for tracking; pass it verbatim (no edits) to GEMINI_WAIT_FOR_VIDEO or GEMINI_GET_VIDEOS_OPERATION. Jobs take 30–180+ seconds; wait 10s before first poll, then poll every 10–30s (allow up to 12 min). Successful results include data.…

Untrusted display-only summary

Get Videos Operation (Veo) (Deprecated)

GEMINI_GET_VIDEOS_OPERATION

DEPRECATED: Use WaitForVideo instead. Checks status of a Veo video generation operation. Use operation_name from GenerateVideos to track progress. Wait several seconds after starting GenerateVideos before first call to avoid OPERATION_NOT_FOUND. Poll at 10–30s intervals; use exponential backoff on HTTP 429 RESOURCE_EX…

Untrusted display-only summary

List Models (Gemini API)

GEMINI_LIST_MODELS

Lists available Gemini and Veo models with their capabilities and limits. Useful for discovering supported models and their features before making generation requests.

Untrusted display-only summary

Wait and Download Video (Veo)

GEMINI_WAIT_FOR_VIDEO

Polls a Veo video generation operation until completion, then downloads and returns the video file. Generation takes 30–120+ seconds (up to ~10–12 min); long waits are normal, not failures. A done=true response without a video file indicates safety filter rejection (check raiMediaFilteredReasons) or quota exhaustion —…

Untrusted display-only summary

Provenance

Versioned facts, explicit trust.

The detail snapshot comes from an attributed MIT-licensed repository revision. Safe local icons use exact-match CC0 Simple Icons symbols; unmatched brands use monograms.

Repository
https://github.com/provider-directoryHQ/provider-directory
Commit
85e33f6a81dfe987f6fc3637d48d45052cea8ca5
Generated
2026-09-12
Trust policy
untrusted_display_only

Remote text is plain display metadata only. It must never become an agent prompt, execution policy, OAuth grant, or executable instruction.