# Google Gemini

**Canonical:** https://apis.io/providers/google-gemini/  
**Website:** https://ai.google.dev/  
**APIs profiled:** 15

Google's multimodal AI model APIs for text, image, audio, and video understanding.

## Kin Score — 42.9 / 100 (developing)

Scored 2026-08-20 under rubric 0.12.0. Trend: flat (+0.0 from 42.9).

| Facet | Score |
|---|---|
| Discoverability | 63.0 |
| Contract Quality | 79.6 |
| Governance | 13.6 |
| Contract Governance | 13.6 |
| Operational Transparency | 26.3 |
| Developer Ergonomics | 21.4 |
| Commercial Clarity | 36.8 |
| Access Clarity | 36.8 |

## Agent readiness — 41.5 (agent-ready)

| Dimension | Value |
|---|---|
| Spec Presence | yes |
| Agentic Access | derived |
| Reversibility Documented | no |
| MCP Server | no |
| Auth Clarity | yes |
| Idempotency | no |
| Error Semantics | verified |
| OpenAPI Examples | no |
| Rate Limit Signal | documented |
| Event Surface Described | derived |
| Agent Skills | yes |
| Well Known Catalog | no |
| Consent Identity | no |
| Agent Card | no |
| Dry Run Mode | no |

## Access

Freemium · Self-serve signup — onboarding: self-serve, pricing: freemium, trial: no (confidence: high).

## APIs (15)

- **Gemini Pro API** — Advanced reasoning and complex task handling.
- **Gemini Pro Vision API** — Multimodal understanding of text and images.
- **Gemini Ultra API** — Most capable model for highly complex tasks.
- **Gemini Embedding API** — Generate text embedding vectors for semantic search, classification, clustering, and retrieval tasks using the gemini-embedding-001 model.
- **Gemini Live API** — Low-latency real-time voice and video interactions with Gemini using WebSockets for streaming multimodal input and output.
- **Gemini Context Caching API** — Cache input tokens for repeated use across multiple requests to reduce costs and improve latency for large context workloads.
- **Gemini Fine-Tuning API** — Customize Gemini model behavior for specific tasks using supervised fine-tuning with your own training data.
- **Gemini Interactions API** — Unified interface for interacting with Gemini models and agents providing a consistent way to manage multi-turn conversations and tool use.
- **Vertex AI Gemini API** — Enterprise-grade access to Gemini models through Google Cloud Vertex AI with advanced features including grounding, safety filters, and regional endpoints.
- **Vertex AI Imagen API** — Generate and edit images using Google Imagen models on Vertex AI for high-quality image creation from text prompts.
- **Vertex AI Gemini Live API** — Enterprise real-time multimodal streaming API on Vertex AI for building low-latency voice and video AI agents.
- **Vertex AI Text Embeddings API** — Generate text embeddings for semantic search and classification tasks using Google embedding models on Vertex AI.
- **Firebase AI Logic API** — Access Gemini API capabilities through Firebase SDKs for mobile and web applications with built-in security and authentication.
- **Google Gemini Content Generation API** — Generate content using Gemini models with text, image, audio, and video inputs. Supports multimodal prompts, function calling, structured output, and configurable safety settings.
- **Google Gemini Embeddings API** — Generate text embedding vectors for semantic search, classification, clustering, and retrieval tasks using Gemini embedding models.

## Agentic access (1)

- **Google Gemini Agentic Access** — 3 operations · 3 acting

## Security (2)

- **Google Gemini Authentication** — apiKey · 1 scheme
- **Google Gemini Domain Security** — TLSv1.3 · HSTS · DMARC

## Plans (1)

- **Google Gemini Plans Pricing**

## Tags

Agentic AI, Artificial Intelligence, Code Generation, Embeddings, Generative AI, Image-Generation, LLM, Machine-Learning, Multi-Modal

---

Profiled by [API Evangelist](https://apievangelist.com) and published on [APIs.io](https://apis.io/providers/google-gemini/). Scores are computed from the provider's own public artifacts under a published rubric.