v2.6.0

2.6.0 (2026-05-21)

Features

• Add enable_prompt_injection_detection for Computer Use feature for the Gemini API. (b1f632d)
• Add budget_exceeded status (15443c0)
• Add gemini-3.5-flash (15443c0)
• Add new fields (2910346)

Documentation

• Replace vertexai with enterprise in Client instantiation (c1c6df7)

v2.5.0

2.5.0 (2026-05-20)

Features

• Add Gemini 3.5 Flash model to options (706fd02)

v2.4.0

2.4.0 (2026-05-17)

Features

• Support Agent and Environment APIs. (ef20d6b)

Bug Fixes

• Output_text for turns that don't end with text. (2afdeff)
• Pass max_line_length to readline() to prevent LineTooLong on large SSE lines with MTLS. (0e8f7bb)

v2.3.0

2.3.0 (2026-05-15)

Features

• Add content union to UserInputStep (a5059a8)
• Interaction.{output_text,output_image,output_audio,output_video} (975d16a)
• Migrate Agent Engines, Evaluation, Prompt Management, and Skill features to agentplatform (abb1099)

Documentation

• Refresh generated docs for 2.2 (2ce0298)

v2.2.0

2.2.0 (2026-05-12)

Features

• Added missing FunctionCallResultDelta type and arguments field to the ArgumentDelta type (b0131f8)

v2.1.0

2.1.0 (2026-05-12)

Features

• Add gemini-3.1-flash-lite to model options (2d5e0fa)
• Add parameters to video response_format. (4e9d68d)
• Introduce Server Side tools deltas (97d6fe5)
• Support Blocking FunctionCall in Live API in AgentPlatform (Vertex) (955bca6)
• Add support for Vertex-lyria models lyria-3-pro-preview & lyria-3-clip-preview (1bc0536)

Bug Fixes

• Steps is not optional (9ea9633)

v2.0.1

2.0.1 (2026-05-09)

Bug Fixes

• Update response_format field names to snake_case. (97142b1)

v2.0.0

2.0.0 (2026-05-07)

⚠ BREAKING CHANGES - Interactions Only

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

• Add steps for interactions (41d8e5b)
• Rename SSE events to interaction.created and interaction.completed (0549c1c)
• Deprecate legacy response_format and publish new polymorphic field. (7fdc9a1)

Documentation

• Update docs (d3020fd)

v1.75.0

1.75.0 (2026-05-04)

Features

• [Python] Multimodal file search (fe5d69e)

Bug Fixes

• Avoid caching stale token in async mTLS path (4e17a9c)

Documentation

• Fix python docstrings for Image.from_file() to use kwargs (cce5398)
• Update docs (ef26583)

v1.74.0

1.74.0 (2026-04-29)

Features

• [Interactions] Add FileCitation.{custom_metadata,media_id,page_number} (aed41ec)
• Add output_info to BatchJob (7b77ab8)
• Add gemini-3.1-flash-tts-preview model to options (8bdc1c3)
• Add ImageResizeMode for GenerateVideos (317d2af)
• Add new Gemini Deep Research agent models (16fffbd)
• Add one_of support to JSONSchema for Agent Platform (8c00c52)
• Add Vertex Dataset input and output options for batch jobs (d880f92)
• interaction-api: Add grounding tool usage breakdown to Interaction Usage. (b24fb5a)
• Introduce enterprise to Client constructor and GOOGLE_GENAI_USE_ENTERPRISE (693fd9a)
• Replace the more ambiguous rate field with sample_rate. (88d9b4a)

Bug Fixes

• Catch google-auth wrapped errors (48ac850)
• Removing Python 3.9 support due to EOL (8bc2b10)
• retry: Retry on httpx.TimeoutException with HttpRetryOptions (#2345) (0598bab)
• Streaming method doesn't handle multi-line SSE (f8a2e7e)
• Typing in AsyncClient.__aexit__, __exit__. (a74dc65)

Documentation

• Add instruction for custom endpoint (dd79904)
• Fix broken link for rate limits (d22ea99)
• Regenerate docs for 1.73.1 (2fb714b)
• Remove duplicate line in genai client docstring. (b1c6026)
• Replace Vertex AI with Gemini Enterprise Agent Platform (7c1ecd5)
• Update doc string to replace Vertex AI with Gemini Enterprise Agent Platform, update method error message to replace Vertex AI with Gemini Enterprise Agent Platform (previously known as Vertex AI), update converter error message to replace Vertex AI with Gemini Enterprise Agent Platform (413f0f9)
• Update Gemini Enterprise Agent Platform home page url (b02cb95)
• Update README.md with correct Pydantic link (fa97cc6)
• Update README.md with correct Pydantic link (fa97cc6)