ActionDeepSeekUpdated May 2026

How do I call DeepSeek for chat completion?

Short answer: Drop the "DeepSeek → DeepSeek Chat Completion" action anywhere in your workflow, map the inputs from upstream nodes, and publish.

Use this action All 3 DeepSeek actions

Inputs

The fields this action accepts.

Every field can be mapped from an upstream trigger, AI step, table row, or hard-coded literal.

Field	Type	Required	Description
Model model	options	Required	Which model to use
User Message message	string	Required	User message to send to the model
System Prompt system_prompt	string	Optional	Optional system instructions that shape the model's behavior
Temperature temperature	string	Optional	Sampling temperature (0–2). Higher = more random.
Max Tokens max_tokens	string	Optional	Maximum tokens to generate in the response
Top P top_p	string	Optional	Nucleus sampling threshold (0–1)
Response Format response_format	options	Optional	Force JSON output (model must support JSON mode)

Sample request

{
  "model": "{{trigger.model}}",
  "message": "e.g. Summarize this article in 3 bullets",
  "system_prompt": "e.g. You are a helpful assistant.",
  "temperature": "0.7",
  "max_tokens": "1024"
}

Returns

{
  "id": "chatcmpl-abc123",
  "model": "deepseek-chat",
  "usage": {
    "total_tokens": 60,
    "prompt_tokens": 10,
    "completion_tokens": 50
  },
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "Sample response"
      },
      "finish_reason": "stop"
    }
  ]
}

Use these fields in downstream nodes for routing, logging, or error handling.

Triggered by

Apps that pair well as the trigger for DeepSeek Chat Completion.

Any of these apps can fire this action as part of a workflow.

Google Sheets → DeepSeek

2 Google Sheets triggers

HubSpot → DeepSeek

18 HubSpot triggers

FAQ

Questions about DeepSeek Chat Completion.

What does the DeepSeek Chat Completion action do in DeepSeek?

Runs chat completion against deepseek-chat (V3-based fast general-purpose) or deepseek-reasoner (R1-based with visible chain-of-thought). Reasoner exposes reasoning_content separately from content — useful for debugging complex multi-step reasoning.

What inputs does DeepSeek Chat Completion require?

Required: Model, User Message. Every input accepts a static value or a variable from any upstream node in your workflow.

Can I use dynamic inputs from earlier workflow nodes?

Yes. Any field on this action can pull values from upstream nodes, whether that's a form response, a trigger payload, an AI output, or a lookup result.

What happens if DeepSeek returns an error?

The workflow pauses on the failed node, the error message is captured in the run log, and you can retry the run with one click. Auto-retry policies are configurable per workflow with exponential backoff up to 5 attempts.

Does DeepSeek Chat Completion support batch operations?

Yes. Run DeepSeek Chat Completion inside a Loop node to process arrays. Tiny Command handles DeepSeek's rate limits automatically so you don't have to throttle manually.

More actions