v1.4.0

Minor Changes

• 2e6efbd: Accept aiApiId (endpoint ID) as a valid model ID for image models and add video generation support.

  Image models now use the same fallback pattern as speech, transcription, and video models: any unrecognized model ID is used directly as https://api.runpod.ai/v2/{modelId} instead of incorrectly appending /openai/v1. This means aiApiIds like wan-2-6-t2i or black-forest-labs-flux-1-schnell work out of the box without needing explicit mappings. Console endpoint URLs are also now supported for image models.

  Video generation support includes 15 models across multiple providers (Pruna, Vidu, Kling, Wan, Seedance, Sora) with async polling, provider options, and both text-to-video and image-to-video capabilities.

• 32f06c4: Add support for the google/nano-banana-2-edit image model with resolution options (1k/2k/4k), 14 aspect ratios, output format, and safety checker.

v1.3.0

Minor Changes

• 973fae6: Add support for the Tongyi-MAI Z-Image Turbo image model with validated sizes and aspect ratios.

v1.2.0

Minor Changes

• cf0c976: Add transcription model support with pruna/whisper-v3-large
  • Add transcriptionModel() and transcription() methods to the provider
  • Support audio transcription via RunPod's Whisper endpoint
  • Accept audio as Uint8Array, base64 string, or URL via providerOptions
  • Return transcription text, segments with timing, detected language, and duration

v1.1.0

Minor Changes

• 7ec59bc: add image models and improvements
  • alibaba/wan-2.6: text-to-image model (max 1024x1024)
  • qwen/qwen-image-edit-2511: edit model (max 1536x1536), supports 1-3 input images and loras
  • google/nano-banana-edit: renamed from nano-banana-edit (backwards compatible), fixed payload format
  • added resolution and aspect ratios columns to supported models table

v1.0.1

Patch Changes

• f13758a: docs: update generateImage and generateSpeech imports to non-experimental

v1.0.0

Major Changes

• 7fa7435: Release 1.0.0 - AI SDK v6 Compatibility

  This release marks the first stable version of the Runpod AI SDK Provider, coinciding with the AI SDK v6 release.

  Breaking Changes

  • Now requires AI SDK v6 (ai@6.x) - users on AI SDK v5 must upgrade
  • Updated to V3 provider interfaces (LanguageModelV3, ImageModelV3, SpeechModelV3)

  New Features

  • Standardized files parameter support: Image models now accept the AI SDK standard files parameter for image editing, supporting both URLs and base64 data
  • Legacy providerOptions.runpod.images still works but files is now the recommended approach

  Dependencies

  • @ai-sdk/provider: ^2.0.0 → ^3.0.0
  • @ai-sdk/provider-utils: ^3.0.5 → ^4.0.0
  • @ai-sdk/openai-compatible: ^1.0.11 → ^2.0.0

  What's Unchanged

  • Public API remains identical - no code changes required for users already on AI SDK v6
  • All language models, image models, and speech models work the same way

Patch Changes

• 7fa7435: docs: expand speech docs for chatterbox turbo

v0.12.0

Minor Changes

• dcc2cc5: Add support for speech generation with resembleai/chatterbox-turbo model:
  • speechModel() and speech() methods for text-to-speech
  • Voice cloning via URL (5-10 seconds of audio)
  • 20 built-in voices

Patch Changes

• ace58c2: Add comprehensive documentation for Pruna and Nano Banana Pro models, including all supported aspect ratios, resolutions, and output formats. Update examples to use standard AI SDK options where possible.

v0.11.1

Patch Changes

• f6115ac: Fix Pruna and Nano Banana Pro model support for all aspect ratios:

  Pruna models:

  • Skip standard size/aspectRatio validation
  • Support all t2i aspect ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, custom
  • Support all edit aspect ratios: match_input_image, 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3
  • Support custom width/height for t2i (256-1440, must be multiple of 16)
  • Support 1-5 images for edit

  Nano Banana Pro model:

  • Skip standard size/aspectRatio validation
  • Support all aspect ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9, 9:21
  • Support resolution: 1k, 2k, 4k
  • Support output_format: jpeg, png, webp

v0.11.0

Minor Changes

• b8cb204: Add support for Pruna and Nano Banana Pro image models:

  • pruna/p-image-t2i - Pruna text-to-image generation
  • pruna/p-image-edit - Pruna image editing
  • google/nano-banana-pro-edit - Nano Banana Pro image editing (Gemini-powered)

  These models support flexible aspect ratios and additional provider options like aspect_ratio, resolution, enable_sync_mode, and enable_base64_output.

v0.10.0

Minor Changes

• 3ca13ef: Add support for deepcogito/cogito-671b-v2.1-fp8 model. Users can now use either deepcogito/cogito-671b-v2.1-fp8 (lowercase) or deepcogito/cogito-671b-v2.1-FP8 (uppercase) - both will work correctly. The model supports text generation, streaming, object generation, and tool calling.