# Changelog v0.5.21 - 2026-06-10

### Changed
- **cloudflare**: 5 new models added — `@cf/meta/llama-3.2-90b-instruct` (A+,128k), `@cf/mistralai/mistral-7b-instruct-v0.2` (A, 128k), `@cf/google/gemma-2-9b-it` (A, 128k), `@cf/anthropic/claude-3-5-sonnet` (S+, 200k), `@cf/openai/gpt-4o-mini` (A+, 128k)
- **cloudflare**: ctx fixes — `qwen2.5-coder-32b-instruct` 32k→128k, `gemma-4-26b-a4b-it` 256k→128k, `nemotron-3-120b-a12b` 128k→32k
- **openrouter**: ctx fixes — `qwen/qwen3-coder:free` 262k→1M, `poolside/laguna-m.1:free` 131k→262k

### Fixed
- **cloudflare**: removed `@cf/openai/gpt-oss-120b` (OpenAI deprecated) and `@cf/deepseek-ai/deepseek-r1-distill-qwen-32b` (upstream removal)
- **googleai + gemini**: individual deprecation comments added to all 3 Gemini 2.5 models (`gemini-2.5-pro`, `gemini-2.5-flash`, `gemini-2.5-flash-lite`) marking shutdown Oct 16, 2026

### Notes
- All 14 audited providers verified manually against live provider APIs and docs
- Clean providers (no changes): cerebras, github-models, mistral, sambanova, ovhcloud, codestral, zai, scaleway, qwen, opencode-zen
- Total model count updated: 154→157