Google

Generative Language API

Get started with the Gemini API Gemini is Google's latest family of large language models. This site contains all the info you need to start building applications with Gemini. The fastest way to start using Gemini is with Google AI Studio, a web-based tool that lets you prototype and run prompts right in your browser. Check out the Google AI Studio getting started guide to learn more. Start with the Python quickstart when you're ready to begin developing. Gemini supports other programming languages too, including Android (Kotlin), Node.js, and Swift. To learn how to use LLMs safely and responsibly, refer to the safety settings and safety guidance documentation.

Chat
DOC
MakerSuit (Generate Key)

Models

Version: 001
Display Name: PaLM 2 Chat (Legacy)
Input Token Limit: 4096
Output Token Limit: 1024
Supported Generation Methods:
- generateMessage
- countMessageTokens
Temperature: 0.25
Top P: 0.95
Top K: 40

Version: 001
Display Name: PaLM 2 (Legacy)
Input Token Limit: 8196
Output Token Limit: 1024
Supported Generation Methods:
- generateText
- countTextTokens
- createTunedTextModel
Temperature: 0.7
Top P: 0.95
Top K: 40

Version: 001
Display Name: Embedding Gecko
Input Token Limit: 1024
Output Token Limit: 1
Supported Generation Methods:
- embedText
- countTextTokens

Version: 001
Display Name: Gemini 1.0 Pro Vision
Input Token Limit: 12288
Output Token Limit: 4096
Supported Generation Methods:
- generateContent
- countTokens
Temperature: 0.4
Top P: 1
Top K: 32

Version: 001
Display Name: Gemini 1.0 Pro Vision
Input Token Limit: 12288
Output Token Limit: 4096
Supported Generation Methods:
- generateContent
- countTokens
Temperature: 0.4
Top P: 1
Top K: 32

Version: 001
Display Name: Gemini 1.5 Pro Latest
Input Token Limit: 2000000
Output Token Limit: 8192
Supported Generation Methods:
- generateContent
- countTokens
Temperature: 1
Top P: 0.95
Top K: 40

Version: 001
Display Name: Gemini 1.5 Pro 001
Input Token Limit: 2000000
Output Token Limit: 8192
Supported Generation Methods:
- generateContent
- countTokens
- createCachedContent
Temperature: 1
Top P: 0.95
Top K: 64

Version: 002
Display Name: Gemini 1.5 Pro 002
Input Token Limit: 2000000
Output Token Limit: 8192
Supported Generation Methods:
- generateContent
- countTokens
- createCachedContent
Temperature: 1
Top P: 0.95
Top K: 40

Version: 001
Display Name: Gemini 1.5 Pro
Input Token Limit: 2000000
Output Token Limit: 8192
Supported Generation Methods:
- generateContent
- countTokens
Temperature: 1
Top P: 0.95
Top K: 40

Version: 001
Display Name: Gemini 1.5 Flash Latest
Input Token Limit: 1000000
Output Token Limit: 8192
Supported Generation Methods:
- generateContent
- countTokens
Temperature: 1
Top P: 0.95
Top K: 40

Version: 001
Display Name: Gemini 1.5 Flash 001
Input Token Limit: 1000000
Output Token Limit: 8192
Supported Generation Methods:
- generateContent
- countTokens
- createCachedContent
Temperature: 1
Top P: 0.95
Top K: 64

Version: 001
Display Name: Gemini 1.5 Flash 001 Tuning
Input Token Limit: 16384
Output Token Limit: 8192
Supported Generation Methods:
- generateContent
- countTokens
- createTunedModel
Temperature: 1
Top P: 0.95
Top K: 64

Version: 001
Display Name: Gemini 1.5 Flash
Input Token Limit: 1000000
Output Token Limit: 8192
Supported Generation Methods:
- generateContent
- countTokens
Temperature: 1
Top P: 0.95
Top K: 40

Version: 002
Display Name: Gemini 1.5 Flash 002
Input Token Limit: 1000000
Output Token Limit: 8192
Supported Generation Methods:
- generateContent
- countTokens
- createCachedContent
Temperature: 1
Top P: 0.95
Top K: 40

Version: 001
Display Name: Gemini 1.5 Flash-8B
Input Token Limit: 1000000
Output Token Limit: 8192
Supported Generation Methods:
- createCachedContent
- generateContent
- countTokens
Temperature: 1
Top P: 0.95
Top K: 40

Version: 001
Display Name: Gemini 1.5 Flash-8B 001
Input Token Limit: 1000000
Output Token Limit: 8192
Supported Generation Methods:
- createCachedContent
- generateContent
- countTokens
Temperature: 1
Top P: 0.95
Top K: 40

Version: 001
Display Name: Gemini 1.5 Flash-8B Latest
Input Token Limit: 1000000
Output Token Limit: 8192
Supported Generation Methods:
- createCachedContent
- generateContent
- countTokens
Temperature: 1
Top P: 0.95
Top K: 40

Version: 001
Display Name: Gemini 1.5 Flash 8B Experimental 0827
Input Token Limit: 1000000
Output Token Limit: 8192
Supported Generation Methods:
- generateContent
- countTokens
Temperature: 1
Top P: 0.95
Top K: 40

Version: 001
Display Name: Gemini 1.5 Flash 8B Experimental 0924
Input Token Limit: 1000000
Output Token Limit: 8192
Supported Generation Methods:
- generateContent
- countTokens
Temperature: 1
Top P: 0.95
Top K: 40

Version: 2.5-exp-03-25
Display Name: Gemini 2.5 Pro Experimental 03-25
Input Token Limit: 1048576
Output Token Limit: 65536
Supported Generation Methods:
- generateContent
- countTokens
- createCachedContent
Temperature: 1
Top P: 0.95
Top K: 64

Version: 2.5-preview-03-25
Display Name: Gemini 2.5 Pro Preview 03-25
Input Token Limit: 1048576
Output Token Limit: 65536
Supported Generation Methods:
- generateContent
- countTokens
- createCachedContent
Temperature: 1
Top P: 0.95
Top K: 64

Version: 2.5-preview-04-17
Display Name: Gemini 2.5 Flash Preview 04-17
Input Token Limit: 1048576
Output Token Limit: 65536
Supported Generation Methods:
- generateContent
- countTokens
- createCachedContent
Temperature: 1
Top P: 0.95
Top K: 64

Version: 2.0
Display Name: Gemini 2.0 Flash Experimental
Input Token Limit: 1048576
Output Token Limit: 8192
Supported Generation Methods:
- generateContent
- countTokens
- bidiGenerateContent
Temperature: 1
Top P: 0.95
Top K: 40

Version: 2.0
Display Name: Gemini 2.0 Flash
Input Token Limit: 1048576
Output Token Limit: 8192
Supported Generation Methods:
- generateContent
- countTokens
- createCachedContent
Temperature: 1
Top P: 0.95
Top K: 40

Version: 2.0
Display Name: Gemini 2.0 Flash 001
Input Token Limit: 1048576
Output Token Limit: 8192
Supported Generation Methods:
- generateContent
- countTokens
- createCachedContent
Temperature: 1
Top P: 0.95
Top K: 40

Version: 2.0
Display Name: Gemini 2.0 Flash (Image Generation) Experimental
Input Token Limit: 1048576
Output Token Limit: 8192
Supported Generation Methods:
- generateContent
- countTokens
- bidiGenerateContent
Temperature: 1
Top P: 0.95
Top K: 40

Version: 2.0
Display Name: Gemini 2.0 Flash-Lite 001
Input Token Limit: 1048576
Output Token Limit: 8192
Supported Generation Methods:
- generateContent
- countTokens
- createCachedContent
Temperature: 1
Top P: 0.95
Top K: 40

Version: 2.0
Display Name: Gemini 2.0 Flash-Lite
Input Token Limit: 1048576
Output Token Limit: 8192
Supported Generation Methods:
- generateContent
- countTokens
- createCachedContent
Temperature: 1
Top P: 0.95
Top K: 40

Version: preview-02-05
Display Name: Gemini 2.0 Flash-Lite Preview 02-05
Input Token Limit: 1048576
Output Token Limit: 8192
Supported Generation Methods:
- generateContent
- countTokens
- createCachedContent
Temperature: 1
Top P: 0.95
Top K: 40

Version: preview-02-05
Display Name: Gemini 2.0 Flash-Lite Preview
Input Token Limit: 1048576
Output Token Limit: 8192
Supported Generation Methods:
- generateContent
- countTokens
- createCachedContent
Temperature: 1
Top P: 0.95
Top K: 40

Version: 2.5-exp-03-25
Display Name: Gemini 2.0 Pro Experimental
Input Token Limit: 1048576
Output Token Limit: 65536
Supported Generation Methods:
- generateContent
- countTokens
- createCachedContent
Temperature: 1
Top P: 0.95
Top K: 64

Version: 2.5-exp-03-25
Display Name: Gemini 2.0 Pro Experimental 02-05
Input Token Limit: 1048576
Output Token Limit: 65536
Supported Generation Methods:
- generateContent
- countTokens
- createCachedContent
Temperature: 1
Top P: 0.95
Top K: 64

Version: 2.5-exp-03-25
Display Name: Gemini Experimental 1206
Input Token Limit: 1048576
Output Token Limit: 65536
Supported Generation Methods:
- generateContent
- countTokens
- createCachedContent
Temperature: 1
Top P: 0.95
Top K: 64

Version: 2.5-preview-04-17
Display Name: Gemini 2.5 Flash Preview 04-17
Input Token Limit: 1048576
Output Token Limit: 65536
Supported Generation Methods:
- generateContent
- countTokens
- createCachedContent
Temperature: 1
Top P: 0.95
Top K: 64

Version: 2.5-preview-04-17
Display Name: Gemini 2.5 Flash Preview 04-17
Input Token Limit: 1048576
Output Token Limit: 65536
Supported Generation Methods:
- generateContent
- countTokens
- createCachedContent
Temperature: 1
Top P: 0.95
Top K: 64

Version: 2.5-preview-04-17
Display Name: Gemini 2.5 Flash Preview 04-17
Input Token Limit: 1048576
Output Token Limit: 65536
Supported Generation Methods:
- generateContent
- countTokens
- createCachedContent
Temperature: 1
Top P: 0.95
Top K: 64

Version: 001
Display Name: LearnLM 1.5 Pro Experimental
Input Token Limit: 32767
Output Token Limit: 8192
Supported Generation Methods:
- generateContent
- countTokens
Temperature: 1
Top P: 0.95
Top K: 64

Version: 2.0
Display Name: LearnLM 2.0 Flash Experimental
Input Token Limit: 1048576
Output Token Limit: 32768
Supported Generation Methods:
- generateContent
- countTokens
Temperature: 1
Top P: 0.95
Top K: 64

Version: 001
Display Name: Gemma 3 1B
Input Token Limit: 32768
Output Token Limit: 8192
Supported Generation Methods:
- generateContent
- countTokens
Temperature: 1
Top P: 0.95
Top K: 64

Version: 001
Display Name: Gemma 3 4B
Input Token Limit: 32768
Output Token Limit: 8192
Supported Generation Methods:
- generateContent
- countTokens
Temperature: 1
Top P: 0.95
Top K: 64

Version: 001
Display Name: Gemma 3 12B
Input Token Limit: 32768
Output Token Limit: 8192
Supported Generation Methods:
- generateContent
- countTokens
Temperature: 1
Top P: 0.95
Top K: 64

Version: 001
Display Name: Gemma 3 27B
Input Token Limit: 131072
Output Token Limit: 8192
Supported Generation Methods:
- generateContent
- countTokens
Temperature: 1
Top P: 0.95
Top K: 64

Version: 001
Display Name: Embedding 001
Input Token Limit: 2048
Output Token Limit: 1
Supported Generation Methods:
- embedContent

Version: 004
Display Name: Text Embedding 004
Input Token Limit: 2048
Output Token Limit: 1
Supported Generation Methods:
- embedContent

Version: exp-03-07
Display Name: Gemini Embedding Experimental 03-07
Input Token Limit: 8192
Output Token Limit: 1
Supported Generation Methods:
- embedContent
- countTextTokens

Version: exp-03-07
Display Name: Gemini Embedding Experimental
Input Token Limit: 8192
Output Token Limit: 1
Supported Generation Methods:
- embedContent
- countTextTokens

Version: 001
Display Name: Model that performs Attributed Question Answering.
Input Token Limit: 7168
Output Token Limit: 1024
Supported Generation Methods:
- generateAnswer
Temperature: 0.2
Top P: 1
Top K: 40

Version: 002
Display Name: Imagen 3.0 002 model
Input Token Limit: 480
Output Token Limit: 8192
Supported Generation Methods:
- predict

Version: 001
Display Name: Gemini 2.0 Flash 001
Input Token Limit: 131072
Output Token Limit: 8192
Supported Generation Methods:
- bidiGenerateContent
- countTokens
Temperature: 1
Top P: 0.95
Top K: 64

Guiverso

Google

Generative Language API

models/chat-bison-001

models/text-bison-001

models/embedding-gecko-001

models/gemini-1.0-pro-vision-latest

models/gemini-pro-vision

models/gemini-1.5-pro-latest

models/gemini-1.5-pro-001

models/gemini-1.5-pro-002

models/gemini-1.5-pro

models/gemini-1.5-flash-latest

models/gemini-1.5-flash-001

models/gemini-1.5-flash-001-tuning

models/gemini-1.5-flash

models/gemini-1.5-flash-002

models/gemini-1.5-flash-8b

models/gemini-1.5-flash-8b-001

models/gemini-1.5-flash-8b-latest

models/gemini-1.5-flash-8b-exp-0827

models/gemini-1.5-flash-8b-exp-0924

models/gemini-2.5-pro-exp-03-25

models/gemini-2.5-pro-preview-03-25

models/gemini-2.5-flash-preview-04-17

models/gemini-2.0-flash-exp

models/gemini-2.0-flash

models/gemini-2.0-flash-001

models/gemini-2.0-flash-exp-image-generation

models/gemini-2.0-flash-lite-001

models/gemini-2.0-flash-lite

models/gemini-2.0-flash-lite-preview-02-05

models/gemini-2.0-flash-lite-preview

models/gemini-2.0-pro-exp

models/gemini-2.0-pro-exp-02-05

models/gemini-exp-1206

models/gemini-2.0-flash-thinking-exp-01-21

models/gemini-2.0-flash-thinking-exp

models/gemini-2.0-flash-thinking-exp-1219

models/learnlm-1.5-pro-experimental

models/learnlm-2.0-flash-experimental

models/gemma-3-1b-it

models/gemma-3-4b-it

models/gemma-3-12b-it

models/gemma-3-27b-it

models/embedding-001

models/text-embedding-004

models/gemini-embedding-exp-03-07

models/gemini-embedding-exp

models/aqa

models/imagen-3.0-generate-002

models/gemini-2.0-flash-live-001