Skip to main content
Build conversational AI applications using Eden AI’s OpenAI-compatible chat completions endpoint.

​
Overview

Eden AI V3 provides full OpenAI API compatibility with multi-provider support. The endpoint follows OpenAI’s exact format, making it a drop-in replacement. Endpoint: 
POST /v3/chat/completions
Note: Streaming is optional. When enabled, responses are delivered via Server-Sent Events (SSE). See Streaming for streaming examples.

​
Model Format

Use the simplified model string format for LLM: 
provider/model
Examples:
  • openai/gpt-4
  • anthropic/claude-sonnet-4-5
  • google/gemini-2.5-flash
  • cohere/command-r-plus

​
Basic Chat Completion

import requests

url = "https://api.edenai.run/v3/chat/completions"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}

payload = {
    "model": "openai/gpt-4",
    "messages": [
        {"role": "user", "content": "Hello! How are you?"}
    ]
}

response = requests.post(url, headers=headers, json=payload)
result = response.json()
print(result["choices"][0]["message"]["content"])

​
Multi-Turn Conversations

Build conversations with message history: 
import requests

url = "https://api.edenai.run/v3/chat/completions"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}

payload = {
    "model": "anthropic/claude-sonnet-4-5",
    "messages": [
        {"role": "user", "content": "What is the capital of France?"},
        {"role": "assistant", "content": "The capital of France is Paris."},
        {"role": "user", "content": "What's the population?"}
    ]
}

response = requests.post(url, headers=headers, json=payload)
result = response.json()
print(result["choices"][0]["message"]["content"])

​
System Messages

Guide the model’s behavior with system messages: 
import requests

url = "https://api.edenai.run/v3/chat/completions"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}

payload = {
    "model": "openai/gpt-4",
    "messages": [
        {
            "role": "system",
            "content": "You are a helpful assistant that speaks like a pirate."
        },
        {
            "role": "user",
            "content": "Tell me about artificial intelligence."
        }
    ]
}

response = requests.post(url, headers=headers, json=payload)
result = response.json()
print(result["choices"][0]["message"]["content"])

​
Temperature and Parameters

Control response creativity and behavior: 
import requests

url = "https://api.edenai.run/v3/chat/completions"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}

payload = {
    "model": "openai/gpt-4",
    "messages": [
        {"role": "user", "content": "Write a creative story about a robot."}
    ],
    "temperature": 0.9,  # Higher = more creative (0-2)
    "max_tokens": 500    # Limit response length
}

response = requests.post(url, headers=headers, json=payload)
result = response.json()
print(result["choices"][0]["message"]["content"])

​
Extended Thinking (Claude)

For Anthropic Claude models, the thinking parameter enables extended reasoning: the model produces internal thinking content before its final answer, which can improve quality on complex tasks. 
{
  "thinking": {
    "type": "enabled",
    "budget_tokens": 2000
  }
}
FieldTypeDescription
typestringenabled or disabled.
budget_tokensintegerMaximum tokens Claude may spend thinking. Minimum 1024, and it must be greater than max_completion_tokens. Counts toward your max_tokens limit.
import requests

url = "https://api.edenai.run/v3/chat/completions"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}

payload = {
    "model": "anthropic/claude-sonnet-4-5",
    "messages": [
        {"role": "user", "content": "How many r's are in strawberry? Think it through."}
    ],
    "thinking": {
        "type": "enabled",
        "budget_tokens": 2000
    }
}

response = requests.post(url, headers=headers, json=payload)
print(response.json())
Extended thinking is only supported on Anthropic Claude models. When thinking is enabled, top_p is ignored.

​
Available Parameters

ParameterTypeDefaultDescription
modelstringRequiredModel string (e.g., openai/gpt-4)
messagesarrayRequiredConversation messages
streambooleanfalseEnable streaming (uses SSE when true)
temperaturefloat1.0Randomness (0-2)
max_tokensinteger-Maximum response tokens
top_pfloat1.0Nucleus sampling threshold
frequency_penaltyfloat0.0Penalize repeated tokens (-2 to 2)
presence_penaltyfloat0.0Penalize topic repetition (-2 to 2)
thinkingobject-Enable Claude’s extended thinking. See Extended Thinking.
fallbacksarray-Backup models tried if model fails.
For details on the fallbacks field, see Fallback.

​
Response Format

Standard JSON response: 
{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "gpt-4",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! I'm doing well, thank you for asking."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 15,
    "total_tokens": 27
  }
}

​
Available Models

For the full list of supported models and their capabilities (PDF support, reasoning, web search, tool calling), see List LLM Models.

​
OpenAI Python SDK Integration

Use Eden AI with the OpenAI SDK: 
from openai import OpenAI

# Point to Eden AI endpoint
client = OpenAI(
    api_key="YOUR_EDEN_AI_API_KEY",
    base_url="https://api.edenai.run/v3"
)

# Use any provider through OpenAI SDK
response = client.chat.completions.create(
    model="anthropic/claude-sonnet-4-5",
    messages=[{"role": "user", "content": "Hello!"}]
)

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

​
Next Steps

First Expert Model Call

Try OCR, image, and audio features with the Expert Models endpoint

LLMs vs Expert Models

Understand when to use each endpoint