Skip to main content

Last Update: 7/13/2025

LLMProvider Release Notes

🚀 API Updates​

Version: 2025-07-13

  • New: 新增缓存功能以提高响应性能和成本优化。
  • New: 支持批量调用以高效处理多个请求。
  • New: 新增grok相关模型。
  • New: 新增Claude Code相关使用文档。
  • New: 增强系统的稳定性。

🚀 API Updates​

Version: 2025-01-15

  • New: Cache functionality for improved response performance and cost optimization
  • New: Batch calling support for processing multiple requests efficiently
  • New: Batch model endpoints for handling bulk operations
  • Added: Cache management APIs for request/response caching
  • Added: Batch processing endpoints with configurable batch sizes
  • Improved: Performance optimization through intelligent caching mechanisms
  • Enhanced: API throughput with parallel batch processing capabilities

📚 Documentation Updates​

Version: 2025-02-22

  • Fixed: Removed unnecessary conversation_id parameter from Chat API examples across all providers
  • Fixed: Corrected parameter naming inconsistencies (tools_choice → tool_choice)
  • Fixed: Updated Gemini API documentation model description
  • Fixed: Completed truncated Python code examples
  • Fixed: Spelling errors in Error codes documentation
  • Added: Documentation Style Guide for consistency
  • Added: API testing script template for validation
  • Improved: README.md with comprehensive project information

🔄 Migration Guide​

From Previous Versions​

If you're updating your integration based on previous documentation:

  1. Remove conversation_id parameter from standard chat completion requests
  2. Update parameter names: Change tools_choice to tool_choice
  3. Update model names: Ensure you're using current model identifiers
  4. Add error handling: Include proper error handling in your code

Breaking Changes​

  • None in this release. All changes are documentation improvements and don't affect API functionality.

For technical support, contact us at [email protected]