NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
npm
npm, #2767 most downloaded on npm
[](https://www.npmjs.com/package/@google/genai) [](https://www.npmjs.com/package/@google/genai)
Latest stable
3.2.0
Last release 11 days ago
11 Nov 2026
Ships on a steady schedule
a new release about every 2 weeks
Nearly every release is documented
notes for 60 of the last 60 stable releases
Nothing withdrawn
no release was ever pulled
2 years old
113 releases · first in 2025
Drag across the ruler to compare, or tap a release to open it.
add the Decisions API (client.decisions.create) to the GenAI SDKs
add gemini-omni-1.2-flash and make it the gemini-api video default
gemini-omni-1.2-flash and make it the gemini-api video default (cd31e9f)proactive_video to ProactivityConfig for the Live API. (2164fe7)xhigh thinking level to Interactions ThinkingLevel (eff6729)Your coding agent can read these notes before it upgrades. Set up the MCP server →
Default Gemini Developer API version is now `v1` (was `v1beta`)
Default Gemini Developer API version is now v1 (was v1beta) (3f477bf)
v1 instead of v1beta.vertexai: true are unaffected by this default change and continue to default to v1beta1.v1, notably: the gemini-flash-latest, gemini-flash-lite-latest and gemini-pro-latest aliases, and some -preview models. They exist only on v1beta. To keep using them, use a specific stable model version, or switch back to v1beta as shown below.v1, notably: gemini-flash-latest, gemini-flash-lite-latest and gemini-pro-latest. They exist only on v1beta. To keep using them, use a specific model version, or switch back to v1beta as shown below.GOOGLE_GENAI_API_VERSION (works for both Gemini Developer API and Enterprise / Vertex AI clients when no version is set in code):# Restores the beta default ('v1beta' on Gemini Developer API, 'v1beta1' on Enterprise / Vertex AI)
export GOOGLE_GENAI_API_VERSION=beta
# Or set an explicit API version string on either platform (e.g. 'v1', 'v1beta', 'v1beta1')
export GOOGLE_GENAI_API_VERSION=v1beta
apiVersion (or httpOptions.apiVersion) to GoogleGenAI (takes precedence over GOOGLE_GENAI_API_VERSION):import { GoogleGenAI } from '@google/genai';
const ai = new GoogleGenAI({
apiVersion: 'v1beta',
});
Minimum supported Node.js version is now 22 (was 20) (7b9fbf0)
package.json engines.node now requires >=22.0.0.@google/genai@^2 (or ignore engine checks if supported by their environment).interactions: CodeExecutionResultStep.result is now typed as Array<Content> | string (CodeExecutionResultStepResult) instead of string (b36ce99). The JSON and runtime value for text-only results are still a plain string, but TypeScript code reading step.result as a string may need to narrow the union (typeof step.result === 'string').
source_text to AudioTranscriptionConfig and SmartTranscriptionMode. (ddb5158)Add support for continuation_token and requires_continuation status
Add store to GenerateContentConfig (Gemini Developer API only) and labels to LiveConnectConfig.
store to GenerateContentConfig (Gemini Developer API only) and labels to LiveConnectConfig. (0b52aa5)send_context_update) and types across GenAI SDKs. (177ee68)fixes.openSingleValueEnumsOct2026 across all SDKs (0059474)interactions: add gemini-4-argon to Model enum
concatenate output_text across multi-step model responses in a turn
accumulate streaming continuation usage metadata and expose initialPromptTokenCount
continuation_token to the Interactions interaction.status_update event. (a93776c)Support "allowlist": "disabled" in environment network config.
add lyria-3.5, gemini-omni-1.1-flash, and gemini-omni-flash-preview to Interactions Model enum
support continuation_token in GenerateContent
add gcs_metrics_uri for exporting tuning job metrics.
CreateAgentInteraction for Trigger.interaction and TriggerCreateParams.interaction (c4341e1)add sample_audio to Voice in GAOS SDK
add credential APIs resource to gaos.
Add from_environment support for environment copying
Add Gemini 3.8 Flash model to SDKs and update Flash model descriptions
Add support for the audio/webm MIME type.
Add AudioTranscriptionConfigMode
Add IDLE state to live connection status enum and mark REQUIRES_ACTION as deprecated.
mode enum (VERBATIM, SMART) to AudioTranscriptionConfig and TranscriptionConfig. (4c5208b)## 2.17.1 (2026-08-13) ### Bug Fixes * Add gemini-3.7-flash
Add interaction_status to LiveServerContent
Add the Gemini Robotics ER 2 Preview model
Support GoogleMaps Tool grounding_types places and routing
add deprecation warnings to Imagen generate_images, edit_images, generate_videos (if using prompt/text/image args), LiveConnectConfig.GenerationConfig…
language_codes field to AudioTranscriptionConfig. (cc808eb)A new field custom_vocabulary is added to Live API
Add AntigravityAgentConfig to OpenAPI schema overlays and regenerate SDKs.
Add environment_id in network config
[Interactions] Add ComputerUse.disabled_safety_policies
Add audioOffset to VoiceActivity
Add ServiceTier to UsageMetadata
model field and CodeMenderAgentData response message (688f3a0)Add Agent Platform MCP support to async generate_content
Add Skill Registry ListSkills and DeleteSkill to SDK
add enable_prompt_injection_detection for Computer Use feature for the Gemini API.
Add Gemini 3.5 Flash model to options
support Agent and Environment APIs.
interaction.{output_text,output_image,output_audio,output_video}
Added missing FunctionCallResultDelta type and arguments field to the ArgumentDelta type
Add gemini-3.1-flash-lite to model options
Update response_format field names to snake_case.
Note: The breaking changes are only in interactions. GenerateContent usage in unaffected. Refer to https://ai.google.dev/gemini-api/docs/interactions-…
Note: The breaking changes are only in interactions. GenerateContent usage in unaffected.
Refer to https://ai.google.dev/gemini-api/docs/interactions-breaking-changes-may-2026 for details
[Python] Multimodal file search
[Interactions] Add FileCitation.{custom_metadata,media_id,page_number}
output_info to BatchJob (5327c60)Refactor Webhook types in GenAI SDKs for easier useage
> CRITICAL WARNING: Do not use this version if you are implementing or relying on webhooks. This release contains known issues regarding webhook sdk.
[!CAUTION] CRITICAL WARNING: Do not use this version if you are implementing or relying on webhooks. This release contains known issues regarding webhook sdk. Please use v1.51.0 or later.
Introduce TYPE_L16 audio content and optional fields.
Support dedicated TextAnnotationDelta for streaming tool responses
Add custom_metadata to FileSearchResult.
[Interactions] Breaking change to Interactions API to refactor TextContent annotations to use specific citation types
functionResponses key in LiveClientMessage (9740426)Add inference_generation_config to EvaluationConfig for Tuning
Add gemini-3.1-flash-image-preview model
change interactions media mime type to enum (breaking change for experimental feature)
Support multimodal embedding for Gemini Embedding 2.0 and support MaaS models in Models.embed_content() (Vertex AI API)
Add HTTP retry support to the SDK
## 1.40.0 (2026-02-04) ### Features
Add include_input query parameter to Get Interaction endpoint.
include_input query parameter to Get Interaction endpoint. (84bc7f4)Add ModelArmorConfig support for prompt and response sanitization via the Model Armor service
Support 4:5 and 5:4 aspect ratio in Interactions
Add FileSearchCallContent to Interactions
[Python] add RegisterFiles so gcs files can be used with genai.
Add minimal and medium thinking levels.
One column per month.