ERNIE

1. Overview

Baidu ERNIE is a knowledge-enhanced large language model designed to deliver strong reasoning and generation capabilities.

2. Request

• Method:POST

• Endpoint:

  https://gateway.serevixai.ai/v1/chat/completions
  

---

3. Parameters

3.1 Header Parameters

Parameter	Type	Required	Description	Example
Content-Type	string	Yes	Sets the request content type. It must be application/json	application/json
Accept	string	Yes	Sets the response content type. The recommended value is application/json	application/json
Authorization	string	Yes	API key required for authentication, in the format Bearer $YOUR_API_KEY.	Bearer $YOUR_API_KEY

---

3.2 Body Parameters (application/json)

Parameter	Type	Required	Description	Example
model	string	Yes	The model ID to use. See Model List for available versions, such as ERNIE-4.0-8K.	ERNIE-4.0-8K
messages	array	Yes	A chat message list in an OpenAI-compatible format. Each object contains role and content.	[{"role": "user","content": "Hello"}]
role	string	No	Message role. Supported values: system, user, and assistant.	user
content	string	No	The message content.	Hello, tell me a joke.
temperature	number	No	Sampling temperature in the range 0-2. Higher values make the output more random, while lower values make it more focused and deterministic.	0.7
top_p	number	No	Another way to control the sampling distribution, in the range 0-1. It is usually used instead of temperature.	0.9
n	number	No	How many completions to generate for each input message.	1
stream	boolean	No	Whether to enable streaming output. When set to true, the API returns ChatGPT-style streamed data.	false
stop	string	No	You can specify up to 4 stop strings. Generation stops when one of them appears in the output.	"\n"
max_tokens	number	No	The maximum number of tokens that can be generated in a single reply, subject to the model context window.	1024
presence_penalty	number	No	-2.0 to 2.0. Positive values encourage the model to introduce new topics, while negative values reduce that tendency.	0
frequency_penalty	number	No	-2.0 to 2.0. Positive values reduce repetition, while negative values increase it.	0

---

4. Request Examples

HTTPShellGoPython

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

{
    "model": "ERNIE-4.0-8K",
    "messages": [
        {
            "role": "user",
            "content": "Hello, can you explain quantum mechanics to me?"
        }
    ]
}

curl https://gateway.serevixai.ai/v1/chat/completions \
    -H "Content-Type: application/json" \
    -H "Accept: application/json" \
    -H "Authorization: Bearer $YOUR_API_KEY" \
    -d "{
    \"model\": \"ERNIE-4.0-8K\",
    \"messages\": [{
        \"role\": \"user\",
        \"content\": \"Hello, can you explain quantum mechanics to me?\"
    }]
}"

package main

import (
    "context"
    "fmt"

    "github.com/openai/openai-go"
    "github.com/openai/openai-go/option"
)

func main() {
    apiKey := "sk-123456789012345678901234567890123456789012345678"

    client := openai.NewClient(
        option.WithAPIKey(apiKey),
        option.WithBaseURL("https://gateway.serevixai.ai/v1"),
    )

    resp, err := client.Chat.Completions.New(
        context.Background(),
        openai.ChatCompletionNewParams{
            Model: "ERNIE-4.0-8K",
            Messages: []openai.ChatCompletionMessageParamUnion{
                openai.UserMessage("Hello, can you explain quantum mechanics to me?"),
            },
        },
    )

    if err != nil {
        fmt.Println("error:", err)
        return
    }

    fmt.Println(resp.Choices[0].Message.Content)
}

#!/usr/bin/env python3

from openai import OpenAI

def main():
    api_key = "sk-123456789012345678901234567890123456789012345678"

    client = OpenAI(
        api_key=api_key,
        base_url="https://gateway.serevixai.ai/v1"
    )

    response = client.chat.completions.create(
        model="ERNIE-4.0-8K",
        messages=[
            {"role": "user", "content": "Hello, can you explain quantum mechanics to me?"}
        ]
    )

    print(response.choices[0].message.content)

if __name__ == "__main__":
    main()

5. Response Example

{
    "id": "chatcmpl-1234567890",
    "object": "chat.completion",
    "created": 1699999999,
    "model": "ERNIE-4.0-8K",
    "choices": [
        {
            "message": {
                "role": "assistant",
                "content": "Quantum mechanics is the branch of physics that studies the microscopic world..."
            },
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 10,
        "completion_tokens": 30,
        "total_tokens": 40
    }
}