Skip to main content
JSON mode is available on paid plans only. Add a token from token.llm7.io before you start.
Use JSON mode when you need strict, machine-readable responses. Set response_format to {"type": "json_object"} to have the model return valid JSON. 
import json
import openai

client = openai.OpenAI(
    base_url="https://api.llm7.io/v1",
    api_key="your-token",  # Required for paid features
)

prompt = "Return a JSON object with fields city, country, and temperature_c."

stream = client.chat.completions.create(
    model="bidara",
    messages=[
        {"role": "system", "content": "Answer with valid JSON only."},
        {"role": "user", "content": prompt},
    ],
    response_format={"type": "json_object"},
    temperature=0.2,
    stream=True,
)

full = ""
for chunk in stream:
    delta = chunk.choices[0].delta.content or ""
    full += delta

data = json.loads(full)
print(data)
Keep prompts short and explicit about required keys. Lower temperatures reduce the chance of malformed JSON.