Use DeepSeek Models in Big-AGI.
Bring your own DeepSeek key and use DeepSeek at its own API rates, with no markup. Keys and chats stay in your browser. Run DeepSeek in parallel with other models, then compare and merge the answers.
Running DeepSeek in Big-AGI
Add your DeepSeek API key and use DeepSeek models at DeepSeek's own API rates. Big-AGI adds no markup and keeps your keys and chats in your browser, not on its servers.
- Your key, your billing. Usage is billed by DeepSeek to your account. Big-AGI does not meter or charge for model usage.
- Direct Connection. Turn it on and the browser calls DeepSeek directly, bypassing the Big-AGI server, when your key is client-side and DeepSeek allows it.
- Reasoning, visible. Big-AGI renders DeepSeek's reasoning output so you can follow how it reached the answer.
- Beam. Run DeepSeek in parallel with other models, then compare or merge the answers. Parallel runs use more tokens than a single chat.
All supported DeepSeek models
DeepSeek V4 Pro
Premium reasoning model with 1M context. Supports extended thinking modes, JSON output, and function calling.
1M
$0.44
$0.87
Apr 2026
DeepSeek V4 Flash
Fast general-purpose model with 1M context. Supports extended thinking modes, JSON output, and function calling.
1M
$0.14
$0.28
Apr 2026
DeepSeek V4 Pro
Premium reasoning model with 1M context. Supports extended thinking modes, JSON output, and function calling.
DeepSeek V4 Flash
Fast general-purpose model with 1M context. Supports extended thinking modes, JSON output, and function calling.
Bring your DeepSeek key. Keep control.
Your key, your data, your choice of model. Big-AGI is open source and self-hostable, so you can check exactly how DeepSeek is called.
BIG-AGI
Resources
© 2026 Token Fabrics·Built with passion in San Diego