Skip to main content

Structured Outputs (JSON Mode)

Quick Start​

Basic JSON Mode​

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

response = client.chat.completions.create(
    model="openai/gpt-4o-mini",
    response_format={"type": "json_object"},
    messages=[
        {"role": "system", "content": "You are a helpful assistant designed to output JSON."},
        {"role": "user", "content": "Who won the world series in 2020?"}
    ]
)

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

cURL​

curl https://api.haimaker.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "openai/gpt-4o-mini",
    "response_format": { "type": "json_object" },
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant designed to output JSON."
      },
      {
        "role": "user",
        "content": "Who won the world series in 2020?"
      }
    ]
  }'

Using JSON Schema (Structured Outputs)​

For more precise control, specify a JSON schema to constrain the output format:

response_format: { "type": "json_schema", "json_schema": ... , "strict": true }

This works for:

  • OpenAI models
  • Azure OpenAI models
  • xAI models (Grok-2 or later)
  • Google AI Studio - Gemini models
  • Vertex AI models (Gemini + Anthropic)
  • Bedrock Models
  • Anthropic API Models
  • Groq Models
  • Ollama Models
  • Databricks Models

Python with Pydantic​

from openai import OpenAI
from pydantic import BaseModel

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

class Step(BaseModel):
    explanation: str
    output: str

class MathReasoning(BaseModel):
    steps: list[Step]
    final_answer: str

completion = client.beta.chat.completions.parse(
    model="openai/gpt-4o",
    messages=[
        {"role": "system", "content": "You are a helpful math tutor. Guide the user through the solution step by step."},
        {"role": "user", "content": "how can I solve 8x + 7 = -23"}
    ],
    response_format=MathReasoning,
)

math_reasoning = completion.choices[0].message.parsed
print(math_reasoning)

cURL with JSON Schema​

curl https://api.haimaker.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "openai/gpt-4o",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful math tutor. Guide the user through the solution step by step."
      },
      {
        "role": "user",
        "content": "how can I solve 8x + 7 = -23"
      }
    ],
    "response_format": {
      "type": "json_schema",
      "json_schema": {
        "name": "math_reasoning",
        "schema": {
          "type": "object",
          "properties": {
            "steps": {
              "type": "array",
              "items": {
                "type": "object",
                "properties": {
                  "explanation": { "type": "string" },
                  "output": { "type": "string" }
                },
                "required": ["explanation", "output"],
                "additionalProperties": false
              }
            },
            "final_answer": { "type": "string" }
          },
          "required": ["steps", "final_answer"],
          "additionalProperties": false
        },
        "strict": true
      }
    }
  }'

Using Different Models​

Anthropic Claude​

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

response = client.chat.completions.create(
    model="anthropic/claude-3-7-sonnet-latest",
    response_format={"type": "json_object"},
    messages=[
        {"role": "system", "content": "You are a helpful assistant designed to output JSON."},
        {"role": "user", "content": "List 3 famous scientists and their discoveries."}
    ]
)

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

Google Gemini​

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

response = client.chat.completions.create(
    model="gemini/gemini-1.5-pro",
    response_format={"type": "json_object"},
    messages=[
        {"role": "system", "content": "You are a helpful assistant designed to output JSON."},
        {"role": "user", "content": "List 3 programming languages and their use cases."}
    ]
)

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

Event Extraction Example​

from openai import OpenAI
from pydantic import BaseModel

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

class CalendarEvent(BaseModel):
    name: str
    date: str
    participants: list[str]

class EventsList(BaseModel):
    events: list[CalendarEvent]

completion = client.beta.chat.completions.parse(
    model="openai/gpt-4o",
    messages=[
        {"role": "system", "content": "Extract event information."},
        {"role": "user", "content": "Alice and Bob are going to a science fair on Friday. Then on Saturday, Charlie is hosting a birthday party."}
    ],
    response_format=EventsList,
)

events = completion.choices[0].message.parsed
for event in events.events:
    print(f"Event: {event.name}, Date: {event.date}, Participants: {event.participants}")