✅ Link to the plugin page: https://zeroqode.com/plugin/deepseek-ai-models-plugin-for-bubble-1738940557670x217102696505632860

Demo to preview the plugin:

✅

Live Demo: https://zeroqode-demo-39.bubbleapps.io/deepseek

✅

Bubble Editor: https://bubble.io/page?version=live&name=deepseek&id=zeroqode-demo-39&tab=Design

Introduction

DeepSeek AI is an advanced plugin that leverages AI technology to optimize search and data analysis. It helps quickly find relevant information, process large datasets, provide personalized recommendations, and automate routine tasks—perfect for professionals seeking smarter solutions.

Our plugin allows you to create a full-fledged chat with the Deepseek artificial intelligence, as well as complete sentences

Prerequisites

You must have an API Key for DeepSeek. You can obtain the API key on this page - https://platform.deepseek.com/sign_in

How to setup

The plugin has 4 API calls. To work with them, you must specify the API key in the plugin settings.

Let’s go over in more detail how to obtain the API key

We need to register on this page - https://platform.deepseek.com/sign_in

Now let's create an api key - https://platform.deepseek.com/api_keys

You need to copy the created api key and paste it into the plugin settings

We need to fund our account so we can use DeepSeek.

Plugin Data Calls

Lists Models

Get User Balance

Plugin Action Calls

Create Chat Completion

Creates a model response for the given chat conversation.

Fields:

Name	Description	Type
model	ID of the model to use. Possible values: deepseek-chat, deepseek-reasoner	Text
frequency_penalty	Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.	Text
max_tokens	Integer between 1 and 8192. The maximum number of tokens that can be generated in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length. If max_tokens is not specified, the default value 4096 is used.	Number
presence_penalty	Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.	Number
temperature	What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.	Number
top_p	An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.	Number
logprobs	Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the content of message.	true/false
top_logprobs	An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. logprobs must be set to true if this parameter is used.	Number
stream	If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events (SSE) as they become available, with the stream terminated by a data: [DONE] message.	true/false
messages	List of messages in the conversation. Example: {role: "user", content: "Hi"} Role possible values: system, user, assistant Content: the contents of the message.	Text

Return values:

Name	Description	Type
id	A unique identifier for the chat completion.	Text
choices	A list of chat completion choices. Example: `[ { "index": 0, "message": { "role": "assistant", "content": "Hello! How can I assist you today? 😊" }, "logprobs": null, "finish_reason": "stop" } ]`	List of Objects
created	The Unix timestamp (in seconds) of when the chat completion was created.	Text
model	The model used for the chat completion.	Text
system_fingerprint	This fingerprint represents the backend configuration that the model runs with.	Text

Create FIM Completion (Beta)

Creates a model response for the given chat conversation.

The FIM (Fill-In-the-Middle) Completion API. User must set base_url="https://api.deepseek.com/beta" to use this feature.

Fields:

Name	Description	Type
base_url	Default: https://api.deepseek.com/beta	Text
prompt	The prompt to generate completions for. Example: Once upon a time,	Text
model	ID of the model to use. Possible values: deepseek-chat, deepseek-reasoner	Text
echo	Echo back the prompt in addition to the completion	true/false
frequency_penalty	Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.
logprobs	Include the log probabilities on the logprobs most likely output tokens, as well the chosen tokens. For example, if logprobs is 20, the API will return a list of the 20 most likely tokens. The API will always return the logprob of the sampled token, so there may be up to logprobs+1 elements in the response. The maximum value for logprobs is 20.	Number
max_tokens	The maximum number of tokens that can be generated in the completion. Default: 1024	Number
presence_penalty	Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.	Number
stream	Whether to stream back partial progress. If set, tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message.	true/false
temperature	What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.	Number
top_p	An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.	Number

Return values:

Name	Description	Type
id	A unique identifier for the completion.	Text
choices	The list of completion choices the model generated for the input prompt.	List of Objects
created	The Unix timestamp (in seconds) of when the completion was created.	Text
model	The model used for completion.	Text
system_fingerprint	This fingerprint represents the backend configuration that the model runs with.	Text

Name	Description	Type
is_available	Whether the user's balance is sufficient for API calls.	Text
balance_infos	Object Array
currency	The currency of the balance. Possible values: `[CNY, USD]`	Text
total_balance	The total available balance, including the granted balance and the topped-up balance.	Text
granted_balance	The total not expired granted balance.	Text
topped_up_balance	The total topped-up balance.	Text

DeepSeek AI Models

Demo to preview the plugin:

Introduction

Prerequisites

How to setup

Let’s go over in more detail how to obtain the API key

Plugin Data Calls

Lists Models

Get User Balance

Plugin Action Calls

Create Chat Completion

Create FIM Completion (Beta)

Changelogs

Update 09.09.25 - Version 1.8.0

Update 02.04.25 - Version 1.7.0

Update 27.03.25 - Version 1.6.0

Update 06.03.25 - Version 1.5.0

Update 06.03.25 - Version 1.4.0

Update 03.03.25 - Version 1.3.0

Update 03.03.25 - Version 1.2.0

Update 03.03.25 - Version 1.1.0

Update 12.02.25 - Version 1.0.0