DeepSeek
Use DeepSeek’s reasoning and coding models.Setup
- Get an API key at platform.deepseek.com
- In Pawz → Settings → Providers → Add Provider → DeepSeek
- Paste your API key
Configuration
| Setting | Default |
|---|---|
| Base URL | https://api.deepseek.com/v1 |
| API key | Required |
| Default model | — |
Models
| Model | Context | Best for |
|---|---|---|
deepseek-chat | 64K | General conversation, coding, analysis |
deepseek-reasoner | 64K | Complex multi-step reasoning with chain-of-thought |
Reasoning tokens
Thedeepseek-reasoner model uses extended “thinking” tokens during complex tasks. These reasoning tokens count toward your usage but produce significantly better results on math, logic, and multi-step problems. Pawz displays thinking content in a collapsible block in the chat UI.
Cost
DeepSeek is one of the most affordable providers — significantly cheaper than OpenAI or Anthropic for comparable quality. A great choice as aworker_model in multi-agent orchestration.
Tips
:::tip- Use
deepseek-chatas yourcheap_model— excellent quality at a fraction of frontier model pricing. - Pair with Ollama — test locally with Ollama, then use DeepSeek for production tasks that need a hosted model.
- DeepSeek uses an OpenAI-compatible API, so it works through the standard
OpenAiProvider. :::