ActionDeepSeekUpdated September 2026

How do I call DeepSeek for chat completion?

Short answer: You can deepseek chat completion in DeepSeek by hand from its own interface, but it won’t repeat itself. On TinyCommand, add the DeepSeek DeepSeek Chat Completion action to a workflow, map its 7 inputs from any upstream app, and it runs automatically every time the trigger fires. No code, and a free tier to start.

DeepSeek Chat Completion in DeepSeek — start free All 3 DeepSeek actions

DeepSeek Chat Completion in DeepSeek — start free

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 run history shows the failed step with its input and the error message DeepSeek returned, so you can fix the input and run the workflow again. Automatic retries are built into HTTP steps only, where you can also set your own retry count and delay.

Does DeepSeek Chat Completion support batch operations?

Run DeepSeek Chat Completion inside a loop to process each item in an array. TinyCommand does not throttle calls for you, so for large arrays add a Delay step if you need to stay within DeepSeek's rate limits.

More actions

Other DeepSeek actions.

Action

Get DeepSeek Credit Balance

Returns the remaining API credit balance. Useful for pre-flight budget control on high-volume LLM workflows where you want to avoid mid-run credit exhaustion.

Action

List DeepSeek Models

Returns the current DeepSeek model catalog (deepseek-chat, deepseek-reasoner, and any newer variants). Pin specific model versions for production workflow reproducibility.

DeepSeek Chat Completion in DeepSeek — start free