The request names Gemini, so the answer is Google's Gemini, whose official developer doors are the Gemini API and Google AI Studio 1, with a Gemini CLI SDK and Gemini agent and live API skills indexed for it 110. Gemini models are also reachable through Replicate 2 and OpenRouter-style or unified APIs such as RunAPI 3, but those are alternative routes rather than the source itself.
- 1
Gemini Developer APIgoogle.comverified and signed
Google's official API and Google AI Studio for building with Gemini models, with SDK, repository and skill doors for code, enterprise (Vertex AI) and live use 110.
official:SDK · @google/gemini-clirepository · sec-geminiskill · gemini-agents-apiskill · gemini-apiskill · gemini-interactions-api
for agents: gemini-api · gemini-api-dev · gemini-live-api
- 2
- 3
RunAPIrunapi.aifound in code, not yet checked
A unified API that exposes Gemini alongside other LLMs through one key, with a Gemini-compatible SDK base URL 3.
for agents: get_task · check_pricing
Sources
- 1Gemini Developer API | Gemma open models | Google AI for Developersai.google.dev · read 2026-10-29
- 2Replicate - Run AI with an APIreplicate.com · read 2026-10-29
- 3RunAPI - Unified AI API for Video, Music, Image & LLM Generationrunapi.ai · read 2026-10-29
- 10gemini-api: declares "gemini-api" (the record we read and signed)unfragile.ai · read 2026-10-24
- 11google/gemini-3-pro: declares "google/gemini-3-pro" (the record we read and signed)unfragile.ai · read 2026-10-24
For agents: the 10 actions behind this answer
gemini-api · gemini-api verified and signed
Use when the user asks about using Gemini in an enterprise environment or explicitly mentions Vertex AI, Google Cloud, or Agent Platform. Guides the usage of the Gemini API on Agent Platform with the Google Gen AI SDK. Covers SDK usage (Python, JS/TS, Go, Java, C#), capabilities like multimodal inpu
google/gemini-3-pro · google/gemini-3-pro verified and signed
Google's most advanced reasoning Gemini model
google/gemini-3.5-flash · google/gemini-3.5-flash verified and signed
Google's fast multimodal model with frontier reasoning across agents, coding, and long-context tasks
google/gemini-2.5-flash-image · google/gemini-2.5-flash-image verified and signed
Google's latest image generation model in Gemini 2.5
get_task · RunAPI Gemini TTS MCP Server found in code, not yet checked
ces.projects.locations.apps.examples.list · Gemini Enterprise for Customer Experience API verified and signed
Lists examples in the given app.
get_task · @runapi.ai/gemini-omni-mcp found in code, not yet checked
google/gemini-omni-1.1 · google/gemini-omni-1.1 verified and signed
Google's fast multimodal video generation and editing model with native audio, using the Interactions API
· Model Context Protocol 2 5 Gemini Pro Thinking website read, tools not yet checked
Official SDKs for building with Model Context Protocol
faf_gemini · gemini-faf-mcp found in code, not yet checked
Export and write GEMINI.md from a .faf file (non-destructive). Authors GEMINI.md in Gemini CLI's own convention (hierarchical, @file-importable — setup · verify · key files · stack · confirm-first actions) via faf-python-sdk's authoring tool, in parity with faf-cli's `faf export --gemini`. Injects i
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.