On behalf of the Spring AI engineering team and everyone who has contributed, I'm happy to announce that Spring AI 1.0.6, 1.1.5, 2.0.0-M5 have been released and are now available from Maven Central.

These releases deliver important improvements, stability enhancements, bug fixes, documentation updates, and security fixes for CVE-2026-40966, CVE-2026-40967, CVE-2026-40978, CVE-2026-40979 and CVE-2026-40980

Release Summary

See individual release notes: 1.0.6 | 1.1.5 | 2.0.0-M5

Thanks to all those who have contributed with issue reports and pull requests.

Version-Specific Highlights

Spring AI 1.0.6

Overview: Maintenance release with 1 dependency upgrade and 1 build fix.

• Upgraded Spring Boot to 3.5.14
• Renamed JdbcChatMemoryRepositorySchemaInitializerPostgresqlTests to follow the integration test naming convention

View complete release notes →

Spring AI 1.1.5

Overview: 5 bug fixes, 4 documentation updates, 2 dependency upgrades, and 3 build updates.

📢 Noteworthy:

• The Pixtral 12B model has been removed and the Pixtral Large model is now deprecated. Users are encouraged to migrate to the currently recommended Mistral AI vision models. Integration tests have been updated to reflect the recommended models.

Bug Fixes:

• Fixed string-based tool choice parsing in OpenAI SDK chat model
• Fixed non-deterministic streaming token usage in BedrockConverse integration tests
• Fixed incorrect extra_body parameter being included in OpenAI API requests
• Fixed test skip condition when API keys are not configured
• Fixed integration test naming convention (IT suffix)

Dependency Upgrades:

• Upgraded Spring Boot to 3.5.14
• Upgraded Apache Tika to 3.3.0, jsoup to 1.22.1, and Apache PDFBox to 3.0.7

View complete release notes →

Spring AI 2.0.0-M5

Overview: 13 new features, 34 bug fixes, 12 documentation updates, 7 dependency upgrades, and 10 build updates.

⚠️ Breaking Changes:

• The Azure OpenAI modules have been removed from Spring AI. Users relying on Azure OpenAI integrations must migrate to the standard spring-ai-openai module, which now includes Azure OpenAI support via deployment handling.
• Options merging behavior has been moved from the model level to the ChatClient level using a new builder combineWith() method. Existing code that relied on ModelOptionUtils.merge() calls may need to be updated. #5725
• The Vertex AI model and autoconfiguration modules have been removed. Only the spring-ai-vertex-ai-embedding module is retained. #5714
• The ZhipuAI model integration has been removed from the main repository. Users must migrate to the separate ZhipuAI integration repository. #5700
• Oracle Cloud Infrastructure (OCI) GenAI support has been removed from the main repository. Users must migrate to the separate OCI GenAI integration repository. #5695
• The SpringAiTestAutoConfigurations class has been removed. #5684

📢 Noteworthy:

• The spring-ai-openai module now uses the official openai-java SDK across all OpenAI models (Chat, Embedding, Image, Audio, Moderation). The spring-ai-openai-sdk module has been removed and merged in. Existing spring.ai.openai properties, builders, and chat options remain fully compatible with no breaking changes. #5779
• The Pixtral 12B model has been removed and the Pixtral Large model has been deprecated. Users should migrate to the recommended Mistral AI models.

New Features:

• Custom StructuredOutputConverter implementations can now participate in the Native Structured Output pipeline #5659
• MCP Server supports filtering which tools are exposed via spring.ai.mcp.server.expose-mcp-client-tools #5755
• New unified cache usage metrics added to the Usage interface
• New OpenAI SDK-based Audio Transcription and Moderation Model support #5730
• OpenAI SDK models now support extraBody configuration #5734
• Anthropic native web search tool integrated #5689
• Anthropic thinking display setting, service tier, and geographic data residency support added #5666
• ToolCallAdvisor.Builder now exposes a getter for conversationHistoryEnabled #5869

View complete release notes →

What's Next

The Spring AI team continues to focus on improving AI application development with Spring Boot. Based on the momentum from these releases, upcoming versions will build on these foundations with enhanced capabilities and developer experience improvements.

For the latest updates and to contribute to the project, visit our GitHub repository or join the discussion in our community channels.

Resources

Project Page | GitHub | Issues | Stack Overflow

Documentation: 1.0.6 Docs | 1.1.5 Docs | 2.0.0-M5 Docs