DeepSeek
Message DeepSeek's models with or without thinking mode, ask about images, and check the account balance.
Connect DeepSeek
- In the sidebar, open Connections and press Add connection.
- Type
deepseekand choose DeepSeek. - Fill in the fields. Each one says Required or Optional.
- Press Test and save. GoRunner checks the connection before it saves anything.
The sheet asks for:
- API Key · Required
A DeepSeek API key (sk-…).
Paste a DeepSeek API key: platform.deepseek.com → API keys → Create new API key.
Connections says how to sign in again, rename or delete it. In a product that embeds GoRunner, Add connection can be missing: then your provider makes connections for you.
Do things in DeepSeek
Add a DeepSeek step, choose a Resource, then an Operation. Choose a row to see its fields.
To start a workflow from DeepSeek, use a Schedule, Webhook or Form trigger.
Later steps read a step’s output by its name: see Use data from earlier steps.
Limits
- A reply from DeepSeek can be up to 16 MB (a file download can have its own limit). A larger one fails the step; it is never cut short.
- When DeepSeek says to slow down (429), the step waits as long as it asks, if the step’s time allows. Otherwise it fails and says when to try again.
Not in your list? See When an app isn’t here.
For developers
In the API, which calls apps pieces, DeepSeek is pieceId: "deepseek" with actionId: "deepseek", set by resource and an operation_… field, such as operation_account. Get an app returns every field.
It reads from outside without changing anything (reads_external). See How versions and side effects work.
DeepSeek › Text
Message a Model
- Model · Required
The model that answers.
Default: deepseek-flash.
- Prompt · Required
What to ask or tell the model.
- System Message · Optional
Standing instructions for the model: its role, tone and rules. Optional.
- Earlier Messages · Optional
Earlier turns of the conversation, oldest first, sent before the prompt: [{"role":"user","content":"…"},{"role":"assistant","content":"…"}].
- Thinking · Optional
Whether the model reasons before it answers. Its reasoning comes back apart from the answer, in reasoning. DeepSeek's default is on.
Options: Default, On, Off.
Default: Default.
- Reasoning Effort · Optional
How long the model thinks: Low, High (DeepSeek's default) or Max.
Options: Default, Low, High, Max.
Default: Default.
Shows when Thinking isn’t Off.
- Output Format · Optional
Text, or JSON the step parses for later steps (under json). For a JSON object, say in the prompt what the JSON should hold.
Options: Text, JSON object.
Default: Text.
- Max Tokens · Optional
The most tokens the answer may use (reasoning included on reasoning models). Empty uses the model's default.
- Temperature · Optional
0–2: lower is more focused and repeatable, higher more varied. Empty uses the model's default.
- Top P · Optional
0–1: sample only from the most likely tokens whose probabilities add up to this. Change this or Temperature, not both.
- Stop Sequences · Optional
Text that ends the answer when the model writes it, one per line (at most 4).
- Tools · Optional
Functions the model may ask to call, as a list: [{"type":"function","function":{"name":"get_weather","description":"…","parameters":{…}}}]. The calls it asks for are in tool_calls; this step does not call them.
- More Options · Optional
Other request fields DeepSeek documents for chat completions, as JSON (such as {"seed": 7}). They are added to the request as written.
DeepSeek › Image
Analyze Image
- Model · Required
A model that reads images (the list marks them).
Default: deepseek-flash.
- Question · Required
What to ask about the images.
- System Message · Optional
Standing instructions for the model: its role, tone and rules. Optional.
- Earlier Messages · Optional
Earlier turns of the conversation, oldest first, sent before the prompt: [{"role":"user","content":"…"},{"role":"assistant","content":"…"}].
- Image URLs · Optional
Links to the images, one per line (https:// or data: URLs). JPEG, PNG, GIF or WebP.
- Image File · Optional
Upload a file, or switch to an expression to use one from an earlier step (such as {{steps.download.result}}). JPEG, PNG, GIF or WebP. Use this, Image URLs, or both.
- Thinking · Optional
Whether the model reasons before it answers. Its reasoning comes back apart from the answer, in reasoning. DeepSeek's default is on.
Options: Default, On, Off.
Default: Default.
- Reasoning Effort · Optional
How long the model thinks: Low, High (DeepSeek's default) or Max.
Options: Default, Low, High, Max.
Default: Default.
Shows when Thinking isn’t Off.
- Output Format · Optional
Text, or JSON the step parses for later steps (under json). For a JSON object, say in the prompt what the JSON should hold.
Options: Text, JSON object.
Default: Text.
- Max Tokens · Optional
The most tokens the answer may use (reasoning included on reasoning models). Empty uses the model's default.
- Temperature · Optional
0–2: lower is more focused and repeatable, higher more varied. Empty uses the model's default.
- Top P · Optional
0–1: sample only from the most likely tokens whose probabilities add up to this. Change this or Temperature, not both.
- Stop Sequences · Optional
Text that ends the answer when the model writes it, one per line (at most 4).
- More Options · Optional
Other request fields DeepSeek documents for chat completions, as JSON (such as {"seed": 7}). They are added to the request as written.
DeepSeek › Model
Get Many
- Return All · Optional
Read every model, page by page (at most 1000; past that the step fails rather than stop early).
Off by default.
- Limit · Optional
How many models to return (1–1000).
Default: 100.
Shows when Return All is off.
DeepSeek › Account
Get Balance
Nothing to fill in.