Add DeepSeek V4 flash/pro support and DeepSeek thinking compatibility (#877)

* Add DeepSeek V4 support and thinking compatibility

* Fix DeepSeek profile persistence regression

* Align multi-model handling with openai-multi-model
This commit is contained in:
JATMN
2026-04-24 11:29:46 -07:00
committed by GitHub
parent c4cb98a4f0
commit ff2a380723
15 changed files with 356 additions and 31 deletions

View File

@@ -41,11 +41,13 @@ openclaude
$env:CLAUDE_CODE_USE_OPENAI="1"
$env:OPENAI_API_KEY="sk-your-key-here"
$env:OPENAI_BASE_URL="https://api.deepseek.com/v1"
$env:OPENAI_MODEL="deepseek-chat"
$env:OPENAI_MODEL="deepseek-v4-flash"
openclaude
```
Use `deepseek-v4-pro` when you want the stronger model. `deepseek-chat` and `deepseek-reasoner` still work as DeepSeek's legacy API aliases.
### Option C: Ollama
Install Ollama first from: