Skip to Content
ModelsGPTStructured output & PDF

GPT structured output and PDF

This page covers structured output and PDF input for the GPT family. For model IDs and endpoint setup, see the GPT family overview.

Structured output

Pass a JSON Schema in response_format; with strict: true, the output strictly conforms to the schema:

gpt_json_schema.py
import json
import os
from openai import OpenAI
 
client = OpenAI(base_url="https://api.ofox.io/v1", api_key=os.environ["OFOX_API_KEY"])
 
resp = client.chat.completions.create(
    model="openai/gpt-5.4-mini",
    response_format={
        "type": "json_schema",
        "json_schema": {
            "name": "price",
            "strict": True,
            "schema": {
                "type": "object",
                "properties": {"price": {"type": "number"}, "currency": {"type": "string"}},
                "required": ["price", "currency"],
                "additionalProperties": False,
            },
        },
    },
    messages=[{"role": "user", "content": "A bat and a ball cost $1.10 in total. The bat costs $1 more than the ball. How much does the ball cost?"}],
)
print(json.loads(resp.choices[0].message.content))

For more patterns, see Structured output.

PDF input

gpt_pdf.py
import base64
import os
from openai import OpenAI
 
client = OpenAI(base_url="https://api.ofox.io/v1", api_key=os.environ["OFOX_API_KEY"])
pdf_b64 = base64.b64encode(open("invoice.pdf", "rb").read()).decode()
 
resp = client.chat.completions.create(
    model="openai/gpt-5.4-mini",
    messages=[{"role": "user", "content": [
        {"type": "file", "file": {"filename": "invoice.pdf", "file_data": f"data:application/pdf;base64,{pdf_b64}"}},
        {"type": "text", "text": "What is the total amount on this invoice?"},
    ]}],
)
print(resp.choices[0].message.content)

For other errors, see Common errors.

Last updated on
Reasoning