DeepSeek

1. Overview

DeepSeek's current most affordable large model offers low prompt/generation costs, making it highly suitable for Chinese-English translation needs.

Available model list:

• deepseek-chat

• deepseek-coder

• deepseek-ai/DeepSeek-V2.5 (Open-source model)

• deepseek-ai/DeepSeek-V3 (Open-source model)

Note

This API is compatible with the OpenAI interface format.

2. Request Description

• Request method: POST

• Request address: https://gateway.theturbo.ai/v1/chat/completions

3. Input Parameters

3.1 Header Parameters

Parameter Name	Type	Required	Description	Example Value
Content-Type	string	Yes	Set the request header type, which must be application/json	application/json
Accept	string	Yes	Set the response type, which is recommended to be unified as application/json	application/json
Authorization	string	Yes	API_KEY required for authentication. Format: Bearer $YOUR_API_KEY	Bearer $YOUR_API_KEY

3.2 Body Parameters (application/json)

Parameter Name	Type	Required	Description	Example
model	string	Yes	The model ID to use. See available models listed in the Overview for details, such as deepseek-chat.	deepseek-chat
messages	array	Yes	Chat message list, compatible with OpenAI interface format. Each object in the array contains role and content.	[{"role": "user","content": "hello"}]
role	string	No	Message role. Optional values: system, user, assistant.	user
content	string	No	The specific content of the message.	Hello, please tell me a joke.
temperature	number	No	Sampling temperature, taking a value between 0 and 2. The larger the value, the more random the output; the smaller the value, the more concentrated and certain the output.	0.7
top_p	number	No	Another way to adjust the sampling distribution, taking a value between 0 and 1. It is usually set as an alternative to the temperature.	0.9
n	number	No	How many replies to generate for each input message.	1
stream	boolean	No	Whether to enable streaming output. When set to true, returns streaming data similar to ChatGPT.	false
stop	string	No	Up to 4 strings can be specified. Once one of these strings appears in the generated content, it stops generating more tokens.	"\n"
max_tokens	number	No	The maximum number of tokens that can be generated in a single reply, subject to the model context length limit.	1024
presence_penalty	number	No	-2.0 ~ 2.0. A positive value encourages the model to output more new topics, while a negative value reduces the probability of outputting new topics.	0
frequency_penalty	number	No	-2.0 ~ 2.0. A positive value reduces the frequency of repeated phrases in the model, while a negative value increases the probability of repeated phrases.	0

4. Request Example

HTTP

POST /v1/chat/completions
Content-Type: application/json
Accept: application/json
Authorization: Bearer $YOUR_API_KEY

{
	"model": "deepseek-chat",
	"messages": [
		{
			"role": "user",
			"content": "Hello, can you explain quantum mechanics to me?"
		}
	],
	"temperature": 0.7,
	"max_tokens": 1024
}

Shell

Go

5. Response Example

{
	"id": "chatcmpl-1234567890",
	"object": "chat.completion",
	"created": 1699999999,
	"model": "deepseek-chat",
	"choices": [
		{
			"message": {
				"role": "assistant",
				"content": "Quantum mechanics is a branch of physics that studies the microscopic world..."
			},
			"finish_reason": "stop"
		}
	],
	"usage": {
		"prompt_tokens": 10,
		"completion_tokens": 30,
		"total_tokens": 40
	}
}