# Changelog v0.5.19 - 2026-06-10

### Added
- **nvidia**: Added `nvidia/nemotron-3-ultra-550b-a55b` (S+, 1M context)
- **groq**: Added 7 new specialized models:
  - `whisper-large-v3`, `whisper-large-v3-turbo` (audio transcription)
  - `canopylabs/orpheus-arabic-saudi`, `canopylabs/orpheus-v1-english` (Arabic/English speech)
  - `meta-llama/llama-prompt-guard-2-22m`, `meta-llama/llama-prompt-guard-2-86m` (security guardrails)
  - `openai/gpt-oss-safeguard-20b` (safety)

### Fixed
- **nvidia**: Corrected context windows for three models:
  - `deepseek-ai/deepseek-v4-pro`: 128k → 1M
  - `deepseek-ai/deepseek-v4-flash`: 128k → 1M
  - `mistralai/mistral-small-4-119b-2603`: 128k → 256k
- **nvidia**: Removed deprecated model `z-ai/glm5` (replaced by `z-ai/glm-5.1`)

### Changed
- Model counts: nvidia stable at 27, groq increased from 8 to 15.
- Total catalog size: 161 models across 16 providers.

### Notes
- This update reflects the latest provider catalogs as of June 10, 2026.
- All existing models were verified against official docs; only minor configuration drift was found.
- The `audit_state.json` was updated with fresh fingerprints.