Chat Completions

Create chat completions using various AI models.

Endpoint

POST https://api.fizzlyapi.com/v1/chat/completions

Request Body

Parameter	Type	Required	Description
`model`	string	Yes	Model ID to use (e.g., `gpt-4o`, `claude-3-5-sonnet-20241022`)
`messages`	array	Yes	Array of message objects
`max_tokens`	integer	No	Maximum tokens to generate
`temperature`	number	No	Sampling temperature (0-2)
`top_p`	number	No	Nucleus sampling parameter
`stream`	boolean	No	Enable streaming responses
`stop`	string/array	No	Stop sequences

Message Object

Field	Type	Description
`role`	string	`system`, `user`, or `assistant`
`content`	string	Message content

Examples

curl https://api.fizzlyapi.com/v1/chat/completions \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What is the capital of France?"}
    ],
    "max_tokens": 100
  }'

from openai import OpenAI
 
client = OpenAI(
    api_key="your-api-key",
    base_url="https://api.fizzlyapi.com/v1"
)
 
response = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is the capital of France?"}
    ],
    max_tokens=100
)
 
print(response.choices[0].message.content)

import OpenAI from 'openai';
 
const openai = new OpenAI({
  apiKey: 'your-api-key',
  baseURL: 'https://api.fizzlyapi.com/v1',
});
 
const response = await openai.chat.completions.create({
  model: 'gpt-4o',
  messages: [
    { role: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: 'What is the capital of France?' },
  ],
  max_tokens: 100,
});
 
console.log(response.choices[0].message.content);

Response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1703123456,
  "model": "gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The capital of France is Paris."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 8,
    "total_tokens": 33
  }
}

Available Models

Fizzly API supports 200+ AI models. For the complete list and pricing, see Model Gallery.

Common models:

openai/gpt-4o - GPT-4o multimodal
openai/o3-mini - Efficient reasoning
anthropic/claude-sonnet-4 - Claude latest flagship
google/gemini-2.5-pro - Gemini latest flagship
deepseek/deepseek-chat - DeepSeek V3

Model name format: provider/model-name, e.g., openai/gpt-4o, anthropic/claude-sonnet-4.

Multi-turn Conversation

For multi-turn conversations, include the conversation history:

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "What is 2+2?"},
    {"role": "assistant", "content": "2+2 equals 4."},
    {"role": "user", "content": "And what is 4+4?"}
]
 
response = client.chat.completions.create(
    model="gpt-4o",
    messages=messages
)

Tips

Use system messages to set the AI’s behavior and context
Keep conversation history for context-aware responses
Set appropriate max_tokens to control response length and cost
Use streaming for real-time responses in chat applications

Authentication Streaming