Documentation Index
Fetch the complete documentation index at: https://docs.requesty.ai/llms.txt
Use this file to discover all available pages before exploring further.
Requesty router supports structured JSON outputs from various model providers, making it easy to get consistent, parseable responses across different LLMs.
For all models, you can request responses in JSON format by specifying the json_object type:
Chat Completions
Responses API
from openai import OpenAI
from pydantic import BaseModel
class Entities(BaseModel):
attributes: list[str]
colors: list[str]
animals: list[str]
requesty_api_key = "YOUR_REQUESTY_API_KEY"
client = OpenAI(
api_key=requesty_api_key,
base_url="https://router.requesty.ai/v1",
)
response = client.chat.completions.create(
model="openai/gpt-4.1",
messages=[
{
"role": "system",
"content": (
"Extract entities from the input text and return them in JSON format "
'with the following structure: {"attributes": [...], "colors": [...], "animals": [...]}'
),
},
{
"role": "user",
"content": "The quick brown fox jumps over the lazy dog with piercing blue eyes",
},
],
response_format={"type": "json_object"},
)
content = response.choices[0].message.content
extracted = Entities.model_validate_json(content)
print(f"Attributes: {extracted.attributes}")
print(f"Colors: {extracted.colors}")
print(f"Animals: {extracted.animals}")
from openai import OpenAI
from pydantic import BaseModel
class Entities(BaseModel):
attributes: list[str]
colors: list[str]
animals: list[str]
requesty_api_key = "YOUR_REQUESTY_API_KEY"
client = OpenAI(
api_key=requesty_api_key,
base_url="https://router.requesty.ai/v1",
)
response = client.responses.create(
model="openai/gpt-4.1",
instructions=(
"Extract entities from the input text and return them in JSON format "
'with the following structure: {"attributes": [...], "colors": [...], "animals": [...]}'
),
input="The quick brown fox jumps over the lazy dog with piercing blue eyes",
text={"format": {"type": "json_object"}},
)
text = response.output_text
extracted = Entities.model_validate_json(text)
print(f"Attributes: {extracted.attributes}")
print(f"Colors: {extracted.colors}")
print(f"Animals: {extracted.animals}")
JSON Schema
For models that support JSON schema (currently OpenAI, Anthropic, and Google models), you can enforce a strict schema on the response:
Chat Completions
Responses API
from openai import OpenAI
from pydantic import BaseModel
class Animals(BaseModel):
animals: list[str]
requesty_api_key = "YOUR_REQUESTY_API_KEY"
client = OpenAI(
api_key=requesty_api_key,
base_url="https://router.requesty.ai/v1",
)
response = client.beta.chat.completions.parse(
model="anthropic/claude-sonnet-4-5",
messages=[
{
"role": "system",
"content": "Extract the animals from the input text",
},
{
"role": "user",
"content": "The quick brown fox jumps over the lazy dog",
},
],
response_format=Animals,
)
animals = Animals.model_validate_json(response.choices[0].message.content)
print(f"Found animals: {animals.animals}") # ['fox', 'dog']
from openai import OpenAI
from pydantic import BaseModel
class Animals(BaseModel):
animals: list[str]
requesty_api_key = "YOUR_REQUESTY_API_KEY"
client = OpenAI(
api_key=requesty_api_key,
base_url="https://router.requesty.ai/v1",
)
response = client.responses.create(
model="anthropic/claude-sonnet-4-5",
instructions="Extract the animals from the input text",
input="The quick brown fox jumps over the lazy dog",
text={
"format": {
"type": "json_schema",
"name": "Animals",
"strict": True,
"schema": Animals.model_json_schema(),
}
},
)
animals = Animals.model_validate_json(response.output_text)
print(f"Found animals: {animals.animals}") # ['fox', 'dog']
Compatibility Notes
- JSON object format works with all models supported by Requesty
- JSON schema is available for OpenAI, Anthropic, and Google models
- Both Chat Completions and Responses API support structured outputs
- Stream mode can also work with structured outputs (see streaming documentation)
Error Handling
When working with structured outputs, it’s important to handle potential parsing errors:
try:
extracted = Entities.model_validate_json(content)
# Process the data
except Exception as e:
print(f"Error parsing response: {e}")
# Handle the error appropriately
