Skip to main content
POST
/
v1
/
chat
/
completions
curl --request POST \
  --url https://api.evolink.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gemini-2.5-flash",
  "messages": [
    {
      "role": "user",
      "content": "Please introduce yourself"
    }
  ]
}
'
{
  "id": "chatcmpl-20251010015944503180122WJNB8Eid",
  "model": "gemini-2.5-flash",
  "object": "chat.completion",
  "created": 1760032810,
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! I'm pleased to introduce myself.\n\nI'm a Large Language Model, trained and developed by Google.\n\nSimply put, you can think of me as a \"smart brain\" that has been trained on massive amounts of text data and is able to understand and generate human language. My core capability is processing and generating text. Specifically, I can do the following:\n\n**1. Information Query & Knowledge Answering**\nI can act like a \"talking encyclopedia,\" answering various questions, whether they're about scientific knowledge, historical events, or everyday facts.\n\n**2. Creative Writing & Text Generation**\nI can create various types of text based on your requirements, such as:\n*   **Writing**: Poetry, stories, scripts, emails, speeches, advertising copy, etc.\n*   **Planning**: Travel plans, study outlines, event proposals, etc.\n*   **Brainstorming**: Working with you to generate new ideas and spark creativity.\n\n**3. Translation & Language Processing**\nI'm proficient in multiple languages and can provide fast, fluent translation services. I can also help you polish, proofread, summarize, or rewrite text to make your expression clearer and more professional.\n\n**4. Programming & Code Assistance**\nI can write code snippets, explain code logic, debug errors, or \"translate\" code from one programming language to another, making me a helpful companion for programmers.\n\n**5. Logical Analysis & Reasoning**\nI can help you analyze complex problems, organize logical chains, and make inferences and summaries based on the information you provide.\n\n---\n\n**In summary**, my goal is to be a powerful and useful tool that helps you obtain information more efficiently, complete tasks, and spark creativity through natural language communication.\n\n**Remember:** I'm an artificial intelligence, my knowledge comes from the data I've learned, and it may not be the most up-to-date. Sometimes I may also make mistakes, so for very important information, I recommend you verify it again."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 13,
    "completion_tokens": 1891,
    "total_tokens": 1904,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "text_tokens": 13,
      "audio_tokens": 0,
      "image_tokens": 0
    },
    "completion_tokens_details": {
      "text_tokens": 0,
      "audio_tokens": 0,
      "reasoning_tokens": 1480
    },
    "input_tokens": 0,
    "output_tokens": 0,
    "input_tokens_details": null
  }
}

Authorizations

​
Authorization
string
header
required

##All APIs require Bearer Token authentication##

Get API Key:

Visit API Key Management Page to get your API Key

Add to request header:

Authorization: Bearer YOUR_API_KEY

Body

application/json
​
model
enum<string>
default:gemini-2.5-flash
required

Chat model name

Available options:
gemini-2.5-flash
Example:

"gemini-2.5-flash"

​
messages
object[]
required

List of chat messages, supports multi-turn dialogue and multimodal input

Minimum array length: 1
​
stream
boolean

Whether to return response in streaming mode

  • true: Streaming return, receives content in real-time chunks
  • false: Returns complete response at once
Example:

false

​
max_tokens
integer

Maximum number of tokens for generated response

Description:

  • Too small value may cause response truncation
Required range: x >= 1
Example:

2000

​
temperature
number

Sampling temperature, controls output randomness

Description:

  • Lower values (e.g., 0.2): More deterministic, focused output
  • Higher values (e.g., 1.5): More random, creative output
Required range: 0 <= x <= 2
Example:

0.7

​
top_p
number

Nucleus Sampling parameter

Description:

  • Controls sampling from tokens with cumulative probability
  • For example, 0.9 means selecting from tokens with cumulative probability up to 90%
  • Default: 1.0 (considers all tokens)

Recommendation: Do not adjust temperature and top_p simultaneously

Required range: 0 <= x <= 1
Example:

0.9

​
top_k
integer

Top-K sampling parameter

Description:

  • For example, 10 means limiting sampling to consider only the top 10 most probable tokens
  • Smaller values make output more focused
  • Default: no limit
Required range: x >= 1
Example:

40

Response

Chat completion generated successfully

​
id
string

Unique identifier for the chat completion

Example:

"chatcmpl-20251010015944503180122WJNB8Eid"

​
model
string

Model name actually used

Example:

"gemini-2.5-flash"

​
object
enum<string>

Response type

Available options:
chat.completion
Example:

"chat.completion"

​
created
integer

Creation timestamp

Example:

1760032810

​
choices
object[]

List of chat completion choices

​
usage
object

Token usage statistics