DeepSeek
DeepSeek is for running DeepSeek models in your scenario: everyday chat plus reasoning R1 and general V3. Use it when you need a strong text or reasoning model without your own API key.
Plug and Play (PnP) billing
This is a PnP (Plug and Play) node: Latenode meters usage and charges PnP tokens on top of scenario CPU seconds (1 PnP token = $1). You do not add your own API key on this node. Per-model prices are shown in the node settings where you pick the model.
Your own API key
To use your provider account and key instead, add the Custom LLM Connection node and a connection with the provider Base URL (the key is stored in the connection).
Models
| Model | Best for |
|---|---|
| DeepSeek Chat (V3.1) | General chat. Default |
| DeepSeek Chat (V3) | General chat, previous generation |
| DeepSeek Reasoner (R1) | Reasoning, math, step-by-step analysis |
Getting structured output
DeepSeek has no Structured Output toggle. Use the Response Format field instead. Set it to json_object for JSON mode, and state in the prompt that the answer must be JSON (for example: "Return the result in JSON format"). The format alone is often not enough without that prompt instruction.
Example prompt:
Extract the person's name and email from the following text and return the result as JSON:
{input_text}
Return format:
{"name": "...", "email": "..."}Fields
Anthropic Claude
Prompt Claude models in scenarios with Latenode PnP billing and no API key.
AI Image Generation Router
Generate images via ImageRouter: Gemini, Grok, GPT-Image, Flux, and more, PnP billing.
Need Help? Ask the community
If something on this page is missing or unclear, post on the Latenode community forum. Our team and other users usually reply quickly.