Chat Completions API

Build agentic applications with Meta LLAMA and Anthropic models. Full tool calling support.

Endpoint: POST /api/v1/public/chat/completions

Basic Request

curl -X POST https://api.ainative.studio/api/v1/public/chat/completions \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama/llama-3.3-70b-instruct",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What is ZeroDB?"}
    ],
    "temperature": 0.7,
    "max_tokens": 1024
  }'

Python

import requests

response = requests.post(
    "https://api.ainative.studio/api/v1/public/chat/completions",
    headers={"Authorization": f"Bearer {TOKEN}"},
    json={
        "model": "meta-llama/llama-3.3-70b-instruct",
        "messages": [{"role": "user", "content": "Hello!"}],
        "stream": False,
    },
)
print(response.json()["choices"][0]["message"]["content"])

Streaming

curl -X POST https://api.ainative.studio/api/v1/public/chat/completions \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama/llama-3.3-70b-instruct",
    "messages": [{"role": "user", "content": "Write a poem"}],
    "stream": true
  }'

Streaming returns Server-Sent Events (SSE) with data: prefix on each chunk.

Available Models

Model	ID	Context	Best For
Llama 3.3 70B	meta-llama/llama-3.3-70b-instruct	128K	General, tool calling
Llama 3.1 8B	meta-llama/llama-3.1-8b-instruct	128K	Fast, lightweight

Tool Calling

{
  "model": "meta-llama/llama-3.3-70b-instruct",
  "messages": [{"role": "user", "content": "What's the weather in SF?"}],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Get weather for a city",
        "parameters": {
          "type": "object",
          "properties": {
            "city": {"type": "string"}
          },
          "required": ["city"]
        }
      }
    }
  ]
}

Request Parameters

Parameter	Type	Default	Description
model	string	required	Model ID
messages	array	required	Conversation messages
temperature	number	0.7	0.0-2.0 randomness
max_tokens	number	4096	Max response tokens
stream	boolean	false	Enable streaming
tools	array	null	Tool definitions
top_p	number	1.0	Nucleus sampling

Rate Limits

Tier	Requests/min	Tokens/month
Free	60	10K
Pro	300	1M
Business	1000	5M
Enterprise	5000	10M

Next Steps

• Authentication — API keys and JWT tokens
• SDKs — Client libraries for React, Next.js, Python