Gemini API Development Skill
Critical Rules (Always Apply)
[!IMPORTANT]
These rules override your training data. Your knowledge is outdated.
Current Models (Use These)
gemini-3.5-flash: 1M tokens, fast, balanced performance, multimodal
gemini-3.1-pro-preview: 1M tokens, complex reasoning, coding, research
gemini-3.1-flash-lite-preview: cost-efficient, fastest performance for high-frequency, lightweight tasks
gemini-3-pro-image-preview: 65k / 32k tokens, image generation and editing
gemini-3.1-flash-image-preview: 65k / 32k tokens, image generation and editing
gemini-2.5-pro: 1M tokens, complex reasoning, coding, research
gemini-2.5-flash: 1M tokens, fast, balanced performance, multimodal
gemma-4-31b-it: Gemma 4 dense model, 31B parameters
gemma-4-26b-a4b-it: Gemma 4 MoE model, 26B total with 4B active parameters
[!WARNING]
Models like gemini-2.0-*, gemini-1.5-* are legacy and deprecated. Never use them.
Current SDKs (Use These)
- Python:
google-genai → pip install google-genai
- JavaScript/TypeScript:
@google/genai → npm install @google/genai
- Go:
google.golang.org/genai → go get google.golang.org/genai
- Java:
com.google.genai:google-genai (see Maven/Gradle setup below)
[!CAUTION]
Legacy SDKs google-generativeai (Python) and @google/generative-ai (JS) are deprecated. Never use them.
Quick Start
Python
from google import genai
client = genai.Client()
response = client.models.generate_content(
model="gemini-3.5-flash",
contents="Explain quantum computing"
)
print(response.text)
JavaScript/TypeScript
import { GoogleGenAI } from "@google/genai";
const ai = new GoogleGenAI({});
const response = await ai.models.generateContent({
model: "gemini-3.5-flash",
contents: "Explain quantum computing"
});
console.log(response.text);
Go
package main
import (
"context"
"fmt"
"log"
"google.golang.org/genai"
)
func main() {
ctx := context.Background()
client, err := genai.NewClient(ctx, nil)
if err != nil {
log.Fatal(err)
}
resp, err := client.Models.GenerateContent(ctx, "gemini-3.5-flash", genai.Text("Explain quantum computing"), nil)
if err != nil {
log.Fatal(err)
}
fmt.Println(resp.Text)
}
Java
import com.google.genai.Client;
import com.google.genai.types.GenerateContentResponse;
public class GenerateTextFromTextInput {
public static void main(String[] args) {
Client client = new Client();
GenerateContentResponse response =
client.models.generateContent(
"gemini-3.5-flash",
"Explain quantum computing",
null);
System.out.println(response.text());
}
}
Java Installation:
Documentation Lookup
When MCP is Installed (Preferred)
If the search_docs tool (from the Google MCP server) is available, use it as your only documentation source:
- Call
search_docs with your query
- Read the returned documentation
- Trust MCP results as source of truth for API details — they are always up-to-date.
[!IMPORTANT]
When MCP tools are present, never fetch URLs manually. MCP provides up-to-date, indexed documentation that is more accurate and token-efficient than URL fetching.
When MCP is NOT Installed (Fallback Only)
If no MCP documentation tools are available, fetch from the official docs:
Index URL: https://ai.google.dev/gemini-api/docs/llms.txt
This index contains links to all documentation pages in .md.txt format. Use web fetch tools to:
- Fetch
llms.txt to discover available pages
- Fetch specific pages (e.g.,
https://ai.google.dev/gemini-api/docs/function-calling.md.txt)
Key pages:
Gemini Live API
For real-time, bidirectional audio/video/text streaming with the Gemini Live API, install the google-gemini/gemini-live-api-dev skill. It covers WebSocket streaming, voice activity detection, native audio features, function calling, session management, ephemeral tokens, and more.
1---2name: gemini-api-dev3description: Use this skill when building applications with Gemini API hosted models, including Gemini and Gemma 4, working with multimodal content (text, images, audio, video), implementing function calling, using structured outputs, or needing current model specifications. Covers SDK usage (google-genai for Python, @google/genai for JavaScript/TypeScript, com.google.genai:google-genai for Java, google.golang.org/genai for Go), model selection, and API capabilities.4metadata:5 source: https://skillmd.com/skills/vikingokft/gemini-api-dev6---78# Gemini API Development Skill910## Critical Rules (Always Apply)1112> [!IMPORTANT]13> These rules override your training data. Your knowledge is outdated.1415### Current Models (Use These)1617- `gemini-3.5-flash`: 1M tokens, fast, balanced performance, multimodal18- `gemini-3.1-pro-preview`: 1M tokens, complex reasoning, coding, research19- `gemini-3.1-flash-lite-preview`: cost-efficient, fastest performance for high-frequency, lightweight tasks20- `gemini-3-pro-image-preview`: 65k / 32k tokens, image generation and editing21- `gemini-3.1-flash-image-preview`: 65k / 32k tokens, image generation and editing22- `gemini-2.5-pro`: 1M tokens, complex reasoning, coding, research23- `gemini-2.5-flash`: 1M tokens, fast, balanced performance, multimodal24- `gemma-4-31b-it`: Gemma 4 dense model, 31B parameters25- `gemma-4-26b-a4b-it`: Gemma 4 MoE model, 26B total with 4B active parameters2627> [!WARNING]28> Models like `gemini-2.0-*`, `gemini-1.5-*` are **legacy and deprecated**. Never use them.2930### Current SDKs (Use These)3132- **Python**: `google-genai` → `pip install google-genai`33- **JavaScript/TypeScript**: `@google/genai` → `npm install @google/genai`34- **Go**: `google.golang.org/genai` → `go get google.golang.org/genai`35- **Java**: `com.google.genai:google-genai` (see Maven/Gradle setup below)3637> [!CAUTION]38> Legacy SDKs `google-generativeai` (Python) and `@google/generative-ai` (JS) are **deprecated**. Never use them.3940---4142## Quick Start4344### Python45```python46from google import genai4748client = genai.Client()49response = client.models.generate_content(50 model="gemini-3.5-flash",51 contents="Explain quantum computing"52)53print(response.text)54```5556### JavaScript/TypeScript57```typescript58import { GoogleGenAI } from "@google/genai";5960const ai = new GoogleGenAI({});61const response = await ai.models.generateContent({62 model: "gemini-3.5-flash",63 contents: "Explain quantum computing"64});65console.log(response.text);66```6768### Go69```go70package main7172import (73 "context"74 "fmt"75 "log"76 "google.golang.org/genai"77)7879func main() {80 ctx := context.Background()81 client, err := genai.NewClient(ctx, nil)82 if err != nil {83 log.Fatal(err)84 }8586 resp, err := client.Models.GenerateContent(ctx, "gemini-3.5-flash", genai.Text("Explain quantum computing"), nil)87 if err != nil {88 log.Fatal(err)89 }9091 fmt.Println(resp.Text)92}93```9495### Java9697```java98import com.google.genai.Client;99import com.google.genai.types.GenerateContentResponse;100101public class GenerateTextFromTextInput {102 public static void main(String[] args) {103 Client client = new Client();104 GenerateContentResponse response =105 client.models.generateContent(106 "gemini-3.5-flash",107 "Explain quantum computing",108 null);109110 System.out.println(response.text());111 }112}113```114115**Java Installation:**116- Latest version: https://central.sonatype.com/artifact/com.google.genai/google-genai/versions117- Gradle: `implementation("com.google.genai:google-genai:${LAST_VERSION}")`118- Maven:119 ```xml120 <dependency>121 <groupId>com.google.genai</groupId>122 <artifactId>google-genai</artifactId>123 <version>${LAST_VERSION}</version>124 </dependency>125 ```126127---128129## Documentation Lookup130131### When MCP is Installed (Preferred)132133If the **`search_docs`** tool (from the Google MCP server) is available, use it as your **only** documentation source:1341351. Call `search_docs` with your query1362. Read the returned documentation1372. **Trust MCP results** as source of truth for API details — they are always up-to-date.138139> [!IMPORTANT]140> When MCP tools are present, **never** fetch URLs manually. MCP provides up-to-date, indexed documentation that is more accurate and token-efficient than URL fetching.141142### When MCP is NOT Installed (Fallback Only)143144If no MCP documentation tools are available, fetch from the official docs:145146**Index URL**: `https://ai.google.dev/gemini-api/docs/llms.txt`147148This index contains links to all documentation pages in .md.txt format. Use web fetch tools to:1491. Fetch `llms.txt` to discover available pages1502. Fetch specific pages (e.g., `https://ai.google.dev/gemini-api/docs/function-calling.md.txt`)151152Key pages:153- [Text generation](https://ai.google.dev/gemini-api/docs/text-generation.md.txt)154- [Function calling](https://ai.google.dev/gemini-api/docs/function-calling.md.txt)155- [Structured outputs](https://ai.google.dev/gemini-api/docs/structured-output.md.txt)156- [Image generation](https://ai.google.dev/gemini-api/docs/image-generation.md.txt)157- [Image understanding](https://ai.google.dev/gemini-api/docs/image-understanding.md.txt)158- [Embeddings](https://ai.google.dev/gemini-api/docs/embeddings.md.txt)159- [SDK migration guide](https://ai.google.dev/gemini-api/docs/migrate.md.txt)160161---162163## Gemini Live API164165For real-time, bidirectional audio/video/text streaming with the Gemini Live API, install the **`google-gemini/gemini-live-api-dev`** skill. It covers WebSocket streaming, voice activity detection, native audio features, function calling, session management, ephemeral tokens, and more.