High output tokens in a structured output query

[jesuspascuall]

Hello.
I've implemented a query to gpt5 API using a structured output (no more than 20 fields of less than 3 words each). When inspecting the token usage of my queries, I am using 1000 input tokens and 4000 output tokens for each query. Why am I getting that high output tokens?

create_payload = {
    "model": "gpt-5",
    "instructions": system_prompt,
    "input": [
        {
            "role": "user",
            "content": [
                {
                    "type": "input_text",
                    "text": "Extract the required fields and follow the JSON Schema.",
                },
                {"type": "input_file", "file_id": pdf_file.id},
            ],
        }
    ],
    "text": {
        "format": {
            "type": "json_schema",
            "name": "Extraction",
            "schema": schema_body,
            "strict": True,
        }
    },
}

[yashwantbezawada]

High output token usage with structured outputs can happen for a few reasons:

Since you're using GPT-5, it might be generating internal reasoning tokens that count toward
your output but aren't visible in the final response. GPT-5 models can use a lot of tokens
"thinking" before producing the structured output.

Also, you're passing a PDF file with input_file. The model might be processing/analyzing that
file content internally which adds to token count even if your final output is just 20 fields.

Try adding some debugging to see what's actually happening:

  response = client.responses.create(**create_payload)

  print(f"Input tokens: {response.usage.input_tokens}")
  print(f"Output tokens: {response.usage.output_tokens}")
  print(f"Response length: {len(str(response.text))}")

You can also try capping the output with max_tokens:

  create_payload = {
      "model": "gpt-5",
      "instructions": system_prompt,
      "max_tokens": 500,  # Add this
      # ... rest of your config
  }

If you're still seeing 4000 tokens for such a small output, that does seem excessive. Could you
check what's actually in response.text? That might show if there's hidden content being
generated