Repository Public
1This document provides a high-level overview of the differences between the `v1`2and `v1beta` versions of the Gemini API.34- **v1** : Stable version of the API. Features in the stable version are fully supported over the lifetime of the major version. If there are any breaking changes, a new major version of the API will be created and the existing version will be deprecated after a reasonable period of time. Non-breaking changes may be introduced to the API without changing the major version. The **Interactions API** and its core features are generally available in `v1`.5- **v1beta** : This version includes early features and capabilities that are actively being developed. While features in `v1beta` may be subject to changes as we refine them based on feedback, it lets you try new capabilities before they are promoted to stable.67## Capability and feature support89The following table details the availability of capabilities across `v1` (GA)10and `v1beta` (Beta). Core API capabilities and tools apply to both11the Interactions API and `generateContent` unless specified otherwise:1213> [!NOTE]14> **Note:** All models are supported in both `v1` and `v1beta`. This table tracks the availability of features across the `v1` and `v1beta` **API versions** (endpoint routes and schema parameters).1516| Feature | v1 | v1beta |17|---|---|---|18| **Core API capabilities** | | |19| [Interactions API](https://ai.google.dev/gemini-api/docs/get-started) | Yes | Yes |20| [Function Calling](https://ai.google.dev/gemini-api/docs/function-calling) | Yes | Yes |21| [Structured Output](https://ai.google.dev/gemini-api/docs/structured-output) | Yes | Yes |22| [Thinking / Reasoning](https://ai.google.dev/gemini-api/docs/thinking) | Yes | Yes |23| [System Instructions](https://ai.google.dev/gemini-api/docs/system-instructions) | Yes | Yes |24| [Audio Output (Speech Config)](https://ai.google.dev/gemini-api/docs/audio) | | Yes |25| [Service Tier (Priority / Flex)](https://ai.google.dev/gemini-api/docs/priority-inference) | | Yes |26| **Tools** | | |27| [Code Execution Tool](https://ai.google.dev/gemini-api/docs/code-execution) | Yes | Yes |28| [Google Search Grounding](https://ai.google.dev/gemini-api/docs/google-search) | Yes | Yes |29| [Google Maps Grounding](https://ai.google.dev/gemini-api/docs/maps-grounding) | Yes | Yes |30| [URL Context Tool](https://ai.google.dev/gemini-api/docs/url-context) | Yes | Yes |31| [File Search Tool](https://ai.google.dev/gemini-api/docs/file-search) | Yes | Yes |32| [Computer Use Tool](https://ai.google.dev/gemini-api/docs/computer-use) | | Yes |33| [MCP Servers Tool](https://ai.google.dev/gemini-api/docs/function-calling#mcp) | | Yes |34| **Realtime APIs** | | |35| [Live API (WebSockets)](https://ai.google.dev/gemini-api/docs/live-api) | | Yes |36| [Live Music API](https://ai.google.dev/gemini-api/docs/realtime-music-generation) | | Yes |37| [Ephemeral Tokens (Live API)](https://ai.google.dev/gemini-api/docs/live-api/ephemeral-tokens) | | Yes |38| **Platform APIs** | | |39| [Models API](https://ai.google.dev/gemini-api/docs/models) | Yes | Yes |40| [Files Service Route](https://ai.google.dev/gemini-api/docs/files) | Yes | Yes |41| [File Search Stores Route](https://ai.google.dev/gemini-api/docs/file-search) | Yes | Yes |42| [Agents API](https://ai.google.dev/gemini-api/docs/agents) | | Yes |43| [Webhooks API](https://ai.google.dev/gemini-api/docs/webhooks) | | Yes |44| [Context Caching](https://ai.google.dev/gemini-api/docs/caching) | | Yes |4546- Yes - Supported4748## Configure API version in an SDK4950The Gemini API SDKs default to `v1beta`, but you can explicitly specify versions51by setting the API version as shown in the following code sample:5253> [!NOTE]54> **Note:** The GenAI SDKs use \`v1beta\` by default to enable access to preview features. You can configure the SDK to use the stable \`v1\` version (as shown below) which also supports the Interactions API.5556### Python5758 from google import genai5960 client = genai.Client(http_options={'api_version': 'v1'})6162 interaction = client.interactions.create(63 model='gemini-3.8-flash',64 input="Explain how AI works",65 )6667 print(interaction.output_text)6869### JavaScript7071 import { GoogleGenAI } from "@google/genai";7273 const ai = new GoogleGenAI({74 httpOptions: { apiVersion: "v1" },75 });7677 async function main() {78 const interaction = await ai.interactions.create({79 model: "gemini-3.8-flash",80 input: "Explain how AI works",81 });82 console.log(interaction.output_text);83 }8485 await main();8687### Java8889 import com.google.genai.Client;90 import com.google.genai.gaos.models.interactions.CreateModelInteraction;91 import com.google.genai.gaos.models.interactions.InteractionsInput;92 import com.google.genai.gaos.models.interactions.Model;93 import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;94 import com.google.genai.types.HttpOptions;9596 Client client = Client.builder()97 .httpOptions(HttpOptions.builder().apiVersion("v1").build())98 .build();99100 CreateModelInteraction req = CreateModelInteraction.builder()101 .model(Model.of("gemini-3.6-flash"))102 .input(InteractionsInput.of("Explain how AI works"))103 .build();104 var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();105 System.out.println(interaction.outputText().orElse(""));106107### REST108109 curl -X POST "https://generativelanguage.googleapis.com/v1/interactions" \110 -H "x-goog-api-key: $GEMINI_API_KEY" \111 -H 'Content-Type: application/json' \112 -d '{113 "model": "gemini-3.8-flash",114 "input": "Explain how AI works",115 }'