3.1.0 (2026-11-10)

Features

• Add gemini-omni-1.2-flash and make it the gemini-api video default (8e9cce3)
• Add proactive_video to ProactivityConfig for the Live API. (97d0678)
• Add xhigh thinking level to Interactions ThinkingLevel (0f29f4d)
• Add usage_metadata (including traffic_type) and truncated to EmbedContentResponse for Gemini Enterprise API (2958fb1)
• interactions: Add gemini-4-carbon and gemini-omni-1.2-flash to Model enum (9610220)

Documentation

• Update documentation links from ai.google.dev to aistudio.google.com. (caf4c4f)

3.0.0 (2026-11-05)

⚠ BREAKING CHANGES

• Default Gemini Developer API version is now v1 (was v1beta) (2d0f947)

  • Clients targeting the Gemini Developer API now default to API version v1 instead of v1beta.
  • No effect on Gemini Enterprise (Vertex AI) defaults: Clients with vertexai=True / enterprise=True are unaffected by this default change and continue to default to v1beta1.
  • Some model aliases are not available on 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.
  • How to configure or restore the previous default via environment variable: Set 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

  • How to set the API version in code: Pass api_version in HttpOptions (takes precedence over GOOGLE_GENAI_API_VERSION):

    from google import genai
    from google.genai import types
    
    client = genai.Client(
        http_options=types.HttpOptions(api_version='v1beta')
    )

• Default HTTP client is now httpx2 (was httpx), and httpx is no longer installed by default (51285c8)

  • httpx is no longer installed by default. httpx2 is now the required dependency and default HTTP client.
  • How to restore the previous httpx default via environment variable: Because httpx2 is installed by default, installing google-genai[httpx] alone only makes import httpx available; to switch the SDK's default client back to httpx without code changes, both install the httpx extra and set GOOGLE_GENAI_HTTP_CLIENT=httpx:

    pip install "google-genai[httpx]"
    export GOOGLE_GENAI_HTTP_CLIENT=httpx

  • How to pass an httpx client in code: After installing google-genai[httpx], you can pass httpx.Client / httpx.AsyncClient directly via HttpOptions:

    import httpx
    from google import genai
    from google.genai import types
    
    client = genai.Client(
        http_options=types.HttpOptions(
            httpx_client=httpx.Client(),
            httpx_async_client=httpx.AsyncClient(),
        )
    )

  • Migrating existing httpx code to httpx2: In most cases, updating your imports with import httpx2 as httpx is sufficient.
  • SSL certificate verification: By default, httpx2 uses the OS certificate trust store (via truststore / httpx2.create_ssl_context()) instead of certifi when SSL_CERT_FILE and SSL_CERT_DIR are not set.
  • When httpx vs. httpx2 types matter: Package-specific objects passed in HttpOptions(client_args=..., async_client_args=...) (such as Timeout, Limits, MockTransport / BaseTransport, or custom Auth subclasses) and unwrapped transport exceptions caught from client.models, client.files, etc. (TimeoutException, ConnectError, HTTPError) must match the active HTTP client. (When GOOGLE_GENAI_HTTP_CLIENT is unset or auto, passing httpx objects in HttpOptions will also auto-select the httpx backend if google-genai[httpx] is installed.)

• interactions: CodeExecutionResultStep.result changes from string to the CodeExecutionResultStepResult union. Code that reads result as a string must now check which variant is present and read the string from it. The JSON for text-only results is unchanged.

Features

• Add source_text to AudioTranscriptionConfig and SmartTranscriptionMode. (1ac3c91)
• Add MALFORMED_RESPONSE to FinishReason (6eb8523), refs #2937
• cli: Use gemini-3.5-transcribe as default model for transcribe command (b18fd3c)
• Default Gemini API version to v1 instead of v1beta across SDKs (2d0f947)
• Disable GenerateVideos for Gemini API, update tests/READMEs (8ddc655)
• interactions: Add Office and OpenDocument MIME types (753cc1c)
• interactions: Support multimodal content in CodeExecutionResultStep.result (a216d95)
• Support GOOGLE_GENAI_API_VERSION environment variable across SDKs (2d0f947)
• Switch default HTTP client to httpx2 and use OS trust store by default (51285c8)
• Update discovery doc (5647e1e)

Bug Fixes

• interactions: Retries = attempts - 1 (0f688a6)
• Preserve unknown fields and open-union variants in Interactions models (2eaf2d8)
• Respect configured and default API version for Gemini API file uploads across SDKs (ddc45d0)

Documentation

• Update embedding examples from gemini-embedding-2-preview to gemini-embedding-2 (d97752a)
• Update remaining documentation links from ai.google.dev to aistudio.google.com. (0e34831)

2.34.0 (2026-10-29)

Features

• Add support for continuation_token and requires_continuation status (daac53e)
• Add support for Python 3.15. (cb1408b)
• Add video upscale task parameter (0456043)
• Drop support for Python 3.10 (2677298)
• interactions: Add automatic_continuation to interactions.create in the Python SDK (c85d5ae)
• interactions: Declare continuation_ids on Interaction (4bdde3a)
• Support base_url, api_version and headers in LiveConnectConfig.http_options (c0e9c54)
• Support video understanding in Gemini Developer API (34b58fd)

Bug Fixes

• interactions: Align SDK User-Agent and x-goog-api-client headers (358d249)
• Resolve PEP 563 string annotations when invoking AFC tools (4650ea1), refs #3156
• Stop per-request Authorization and X-Server-Timeout from leaking into client default headers (0584c96), refs #3158

2.33.0 (2026-10-22)

Features

• Add store to GenerateContentConfig (Gemini Developer API only) and labels to LiveConnectConfig. (16a29c9)
• Add support for Python 3.15. (e1c4fc7)
• Add support for Python 3.15. (1a64450)
• client: Support httpx2 with GOOGLE_GENAI_HTTP_CLIENT configuration (87ddba1)
• Include AudioContent, DocumentContent, and VideoContent in FunctionResultSubContent (adbc79c)

Bug Fixes

• client: Skip mTLS URL rewriting for multi-regional .rep.googleapis.com endpoints and honor GOOGLE_API_USE_MTLS_ENDPOINT in Google Auth sessions (4e44c84)
• Honor an explicit zero in HttpRetryOptions delay fields (419dd89), refs #2026
• Honor HttpRetryOptions for aiohttp connection errors in async requests (ee639c6), refs #3160

Documentation

• Update unenforced JSON Schema keywords on Interactions schema fields. (c97ae02)

2.32.0 (2026-10-21)

Features

• Add base_voice to PromptedVoice in GAOS SDK (5488643)
• Add generation_output_config to GenerateContentConfig (5c008e1)
• Add Live API in-session context updates (send_context_update) and types across GenAI SDKs. (364889a)
• sdks: Enable fixes.openSingleValueEnumsOct2026 across all SDKs (78f6d34)
• Update discovery doc (6cd176e)

Bug Fixes

• Base64-encode inline bytes in Live send_tool_response (a7bbff6), refs #3022
• Don't crash parsing responses with JSON objects in Any-typed fields (4c1abcc)
• interactions: Sync InteractionSseEventInteractionStatus enum with InteractionStatus (ba854b2)

Documentation

• Publish the API reference on each release (1d12358)
• Transition docs workflow to GitHub Actions (3b1256a)

2.31.0 (2026-10-14)

Features

• interactions: Add gemini-4-argon to Model enum (8554b07)

Bug Fixes

• Clear continuation state and preserve prompt feedback when continuation hop returns no candidates (a0d809c)
• Fix the function declaration parser for union types. Fixes #3060 (be32e9e)
• Fix the grounding metadata merging for automatic continuation in generate content and generate content stream (f1499bb)
• Make continuation streams retry dropped hops, stop on prompt_feedback, and keep real errors in generate_content (339a929)
• Match the mTLS endpoint to each transport's SSL context, including plain aiohttp (f8a4693)

2.30.1 (2026-10-13)

Bug Fixes

• Concatenate output_text across multi-step model responses in a turn (180c345)

2.30.0 (2026-10-13)

Features

• Accumulate streaming continuation usage metadata and expose initial_prompt_token_count (b27f3cd)
• Add continuation_token to the Interactions interaction.status_update event. (02db4c5)
• Add a CONTINUATION_REQUIRED Interaction status (bf9d6d7)
• Add billable token counts fields (6a6501c)
• Add startOffset/endOffset to Transcription and interimTranscriptTimestampEnabled to RealtimeInputConfig (c644a94)
• Add usage in InteractionStatusUpdate events (56c3a1a)
• Allow automatic resumption of continuation token for in generate content and generate content stream. Default behavior for this feature is disabled (83e43ea)
• cli: Update Speakeasy generator to v2.948.0, bump CLI to v0.4.2, and apply CLI overlay fixes (cdcd3dd)
• Enable automatic continuation token resumption for chats module. (9ebf714)

Bug Fixes

• Clear intermediate CONTINUATION finish_reason in streaming continuation (8a641d8)
• Do not record incomplete continuation stream turns in curated chat history (b382e01)
• gemini-api-cli: Remove unsupported 2.5 and 1.6 models from Interactions model options and CLI examples (fe5fb10)
• genai: Deduplicate Flash and Omni descriptions in ModelOption (33efaad)
• interactions: Restore super().model_construct in Interaction model validator (ccd5dd3)
• python: Discard stale checkpoint token on non-resumable finish reason (f44e8ee)
• Raise default HTTP timeouts so long-running requests aren't killed client-side (b006b4b)
• Resume streaming generation from the latest checkpoint continuation token on mid-stream errors or cutoffs (90bb32b)
• Update EnvironmentConfig.env schema to map keys to EnvVar or string. (3108d8c)
• Use the mTLS endpoint on the httpx and websocket transports (97d5821)

2.29.0 (2026-10-07)

Features

• Support "allowlist": "disabled" in environment network config. (fa4acc7)
• Update discovery doc (84bf19c)

Bug Fixes

• Only log direct AFC warning when functions are present in the config (6e36aaa)

Documentation

• Refresh docs for 2.28.0 (618f0aa)
• Update code samples to gemini-flash-latest, gemini-3.1-flash-lite-image, and gemini-3.8-flash-tts (5673494)
• Update generated SDK docstring examples to use gemini-flash-latest (28e0915)

2.28.0 (2026-10-02)

Features

• Add lyria-3.5, gemini-omni-1.1-flash, and gemini-omni-flash-preview to Interactions Model enum (1e8c0cc)
• Support continuation_token in Interactions (d40ca70)