How AI is applied across API Evangelist and APIs.io. Read my AI disclosure →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC

Gemini Generation API

Generate content from prompts

Gemini Generation API is one of 20 APIs that Gemini publishes on the APIs.io network, described by a machine-readable OpenAPI specification.

Tagged areas include Generation. The published artifact set on APIs.io includes an OpenAPI specification, API documentation, authentication docs, and an API reference.

This API exposes 2 operations across 2 paths, and defines 8 schemas. It is described by OpenAPI 3.1.0, at version v1beta.

Requests are made against a single base URL, https://generativelanguage.googleapis.com.

2 operations 2 paths 8 schemas 2 POST

Metadata

The identity and technical contract details declared by the specification.

Specification
OpenAPI 3.1.0
API Version
v1beta
Base URL
https://generativelanguage.googleapis.com
Authentication
API Key, API Key
Resource Areas
1

Authentication & Security 2

Gemini Generation API declares 2 security schemes for authenticating requests. An API key is passed in the query as key (apiKeyQuery). An API key is passed in the header as x-goog-api-key (apiKeyHeader). By default, every request must be authenticated.

  • apiKeyQuery — Gemini API key from Google AI Studio
  • apiKeyHeader — Gemini API key passed via header

Paths & Operations 2

Across 2 paths, the API surfaces 2 operations — 2 POST. Each is listed below with its method, path, parameters, and response codes.

Generation 2

Generate content from prompts

POST
/v1beta/models/{model}:generateContent
Generate content
generateContent 1 param body → 200
POST
/v1beta/models/{model}:streamGenerateContent
Stream generated content
streamGenerateContent 1 param body → 200

Schemas 8

The contract defines 8 schemas that model the data the API accepts and returns. The most detailed are GenerationConfig (7 properties), GenerateContentRequest (5 properties), Candidate (4 properties), Part (3 properties). Each schema is shown below with its type and property counts.

UsageMetadata
object
3 properties
SafetySetting
object
2 properties
Part
object
3 properties
GenerateContentRequest
object
5 properties 1 required
Content
object
2 properties
Candidate
object
4 properties
GenerateContentResponse
object
2 properties
GenerationConfig
object
7 properties

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

gemini-generation-api-openapi.yml Raw ↑

Other APIs Gemini publishes across the network.

Gemini Python SDK
Gemini Node.js SDK
Gemini Go SDK
Gemini Java SDK
Gemini C# SDK
Gemini Live API
Gemini Interactions API
Gemini Image Generation API
Gemini Video Generation API
Gemini Text-to-Speech API
Gemini Files API
Gemini Embeddings API
Where this information came from

This is an independent, third-party profile of Gemini Generation API, published by API Evangelist. We do not operate, host, resell, or support these APIs, and we are not affiliated with or endorsed by the company unless stated above. Everything here is built from publicly available information — the company's own site, developer portal, documentation, public repositories, and the specifications it publishes for public use. Nothing is obtained by breaching a system, defeating an access control, or using credentials.

The Kin Score and Agent Readiness rating are independently calculated assessments of a company's public API artifacts, scored against a published rubric. They are not certifications, endorsements, security assessments, or audits.

Corrections, re-scores, and removal are free — no partnership or purchase required, and you do not need to justify the request. A removed company is recorded as unrated, never scored zero for having asked. Acknowledgement within one business day; removal within two.

info@apievangelist.com · Read the full data-sourcing policy →
On a security or compliance team? Put security in the subject line and you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.