4.48.0

4.48.0

• Add -ImageGenerationAction parameter to Request-Response.

4.47.0

4.47.0

• Add gpt-5.2-codex model to Request-Response.
• Update documents.

4.45.0

4.45.0

• Add gpt-5.2 models.

4.44.0

4.44.0

• Add gpt-5.1-codex-max.
• API updates.
• Add new function for compacting responses.
  • Request-ResponseCompaction

4.43.0

4.43.0

• Add new gpt-5.1 models.
• API updates.

4.41.0

4.41.0

• Support gpt-4o-transcribe-diarize model in Request-AudioTranscription.
• Add -Description parameter to New-VectorStore.
• Rename -Format parameter to -ResponseFormat for consistency across cmdlets.
  You can still use -Format as an alias, but it will be removed in future releases.
• Remove default value for ReasoningEffort parameter in Request-Response. (For better compatibility with gpt-5-pro model.)

4.40.0

4.40.0

• Add new models that was announced at OpenAI DevDay 2025.
  • sora-2, sora-2-pro, gpt-5-pro, gpt-audio, gpt-audio-mini, gpt-image-1-mini, gpt-realtime, gpt-realtime-mini
• Add New functions for Video generation.
  Guide: How to use Video generation
  • New-Video
  • New-VideoRemix
  • Get-Video
  • Get-VideoContent
  • Remove-Video

  $VideoJob = New-Video -Model 'sora-2' -Prompt "A cat playing piano" -Size 1280x720
  $VideoJob | Get-VideoContent -OutFile "C:\output\cat_piano.mp4" -WaitForCompletion

• [Experimental] Add video generation support for Azure OpenAI Service.

4.39.1

4.39.1

• Fix bug where API requests fail when json_schema is specified as the OutputFormat in Request-Response functions. #44
• Update deprecation models list.

4.39.0

4.39.0

• Add gpt-5-codex model.

4.38.0

4.38.0

• Realtime transcript session now uses GA version of the API instead of beta.
• Fix audio format handling in Realtime API.