Skip to main content
Structured Outputs ensure that models follow your supplied JSON schema. Portkey supports this for Anthropic models using a unified response_format interface. Define object schemas using Pydantic (Python) or Zod (JavaScript) to extract structured information from unstructured text. This approach provides type hinting and automatic validation. 
from portkey_ai import Portkey
from pydantic import BaseModel

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

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

portkey = Portkey(
    api_key="PORTKEY_API_KEY"
)

# Use .parse() for automatic parsing
completion = portkey.chat.completions.parse(
    model="@anthropic-testing/claude-sonnet-4-6",
    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
)

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

import { Portkey } from 'portkey-ai';
import { z } from 'zod';
import { zodResponseFormat } from "openai/helpers/zod";

const MathReasoning = z.object({
    steps: z.array(z.object({ explanation: z.string(), output: z.string() })),
    final_answer: z.string()
});

const portkey = new Portkey({
    apiKey: "PORTKEY_API_KEY",
});

async function runMathTutor() {
    try {
        const completion = await portkey.chat.completions.create({
            model: "@anthropic-testing/claude-sonnet-4-6",
            messages: [
                { role: "system", content: "You are a helpful math tutor." },
                { role: "user", content: "Solve 8x + 7 = -23" }
            ],
            response_format: zodResponseFormat(MathReasoning, "MathReasoning")
        });

        console.log(JSON.parse(completion.choices[0].message.content));
    } catch (error) {
        console.error("Error running math tutor:", error);
    }
}

runMathTutor();

import json, re
from anthropic import Anthropic
from pydantic import BaseModel


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

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

def parse(client, model, messages, response_model):
    schema = response_model.model_json_schema()

    msg = client.messages.create(
        model=model,
        max_tokens=1024,
        system=f"Return ONLY JSON matching this schema:\n{json.dumps(schema)}",
        messages=messages
    )
    text = msg.content[0].text
    json_text = re.search(r"\{.*\}", text, re.S).group(0)

    return response_model.model_validate(json.loads(json_text))

client = Anthropic(
    auth_token="PORTKEY_API_KEY",
    base_url="https://api.portkey.ai"
)

completion = parse(
    client,
    "@anthropic-testing/claude-sonnet-4-6",
    [{"role": "user", "content": "how can I solve 8x + 7 = -23"}],
    MathReasoning
)
print(completion)

import Anthropic from "@anthropic-ai/sdk";
import { z } from "zod";

const Step = z.object({
    explanation: z.string(),
    output: z.string(),
});

const MathReasoning = z.object({
    steps: z.array(Step),
    final_answer: z.string(),
});

const client = new Anthropic({
    authToken: "PORTKEY_API_KEY",
    baseURL: "https://api.portkey.ai",
});

async function main() {
    const completion = await client.messages.create({
        model: "@anthropic-testing/claude-sonnet-4-6",
        max_tokens: 1024,
        system: "Return ONLY valid JSON matching the schema: {steps:[{explanation:string,output:string}], final_answer:string}",
        messages: [
            { role: "user", content: "how can I solve 8x + 7 = -23" }
        ],
    });

    const text = completion.content[0].text;

    const jsonText = text.match(/\{[\s\S]*\}/)[0];

    const result = MathReasoning.parse(JSON.parse(jsonText));

    console.log(result);
}

main().catch(console.error);

curl https://api.portkey.ai/v1/chat/completions \
  -H "x-portkey-api-key: $PORTKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "@anthropic-provider/claude-3-5-sonnet-20241022",
    "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
        }
      }
    }
  }'

​
2. Using Raw JSON Schema

For cross-language compatibility or dynamic schemas, pass a standard JSON schema directly. 
from portkey_ai import Portkey

portkey = Portkey(
    api_key="PORTKEY_API_KEY"
)

completion = portkey.chat.completions.create(
    model="@anthropic-provider/claude-3-5-sonnet-20241022",
    messages=[
        {"role": "system", "content": "Extract the event information."},
        {"role": "user", "content": "Alice and Bob are going to a science fair on Friday."}
    ],
    response_format={
        "type": "json_schema",
        "json_schema": {
            "name": "event_extraction",
            "schema": {
                "type": "object",
                "properties": {
                    "location": { "type": "string" },
                    "date": { "type": "string" },
                    "participants": { "type": "array", "items": { "type": "string" } }
                },
                "required": ["location", "date", "participants"],
                "additionalProperties": False
            },
            "strict": True
        }
    }
)

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

import { Portkey } from "portkey-ai";

const portkey = new Portkey({
    apiKey: "PORTKEY_API_KEY",
});

async function main() {
    try {
        const completion = await portkey.chat.completions.create({
            model: "@anthropic-provider/claude-3-5-sonnet-20241022",
            messages: [
                { role: "system", content: "Extract the event information." },
                { role: "user", content: "Alice and Bob are going to a science fair on Friday." }
            ],
            response_format: {
                type: "json_schema",
                json_schema: {
                    name: "event_extraction",
                    schema: {
                        type: "object",
                        properties: {
                            location: { type: "string" },
                            date: { type: "string" },
                            participants: { type: "array", items: { type: "string" } }
                        },
                        required: ["location", "date", "participants"],
                        additionalProperties: false
                    },
                    strict: true
                }
            }
        });
        
        console.log(completion.choices[0].message.content);
    } catch (error) {
        console.error("Error extracting event:", error);
    }
}

main();

from anthropic import Anthropic
import json

client = Anthropic(
    auth_token="PORTKEY_API_KEY",
    base_url="https://api.portkey.ai" )

schema = {
    "type": "object",
    "properties": {
        "location": {"type": "string"},
        "date": {"type": "string"},
        "participants": {
            "type": "array",
            "items": {"type": "string"}
        }
    },
    "required": ["location", "date", "participants"],
    "additionalProperties": False
}

prompt = f"""
Extract the event information from the sentence.

Return ONLY valid JSON matching this schema:
{json.dumps(schema, indent=2)}

Sentence:
Alice and Bob are going to a science fair on Friday.
"""

response = client.messages.create(
    model="@anthropic-testing/claude-sonnet-4-6",
    max_tokens=200,
    system="You are an information extraction system. Only return valid JSON.",
    messages=[
        {
            "role": "user",
            "content": prompt
        }
    ]
)

print(response.content[0].text)

import Anthropic from '@anthropic-ai/sdk';


const client = new Anthropic({
    authToken: "PORTKEY_API_KEY",
    baseURL: "https://api.portkey.ai",

});

async function main() {
    const message = await client.messages.create({
        model: "@anthropic-testing/claude-sonnet-4-6",
        max_tokens: 1024,
        messages: [{ role: "user", content: "Alice and Bob are going to a science fair on Friday." }],
        response_format: {
            type: "json_schema",
            json_schema: {
                name: "event_extraction",
                schema: {
                    type: "object",
                    properties: {
                        location: { type: "string" },
                        date: { type: "string" },
                        participants: { type: "array", items: { type: "string" } }
                    },
                    required: ["location", "date", "participants"],
                    additionalProperties: false
                },
                strict: true
            }
        }
    });

    console.log(message.content);
}

main().catch(console.error);

curl https://api.portkey.ai/v1/chat/completions \
  -H "x-portkey-api-key: $PORTKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "@anthropic-provider/claude-3-5-sonnet-20241022",
    "messages": [
      { "role": "system", "content": "Extract event information." },
      { "role": "user", "content": "Alice and Bob are going to a science fair on Friday." }
    ],
    "response_format": {
      "type": "json_schema",
      "json_schema": {
        "name": "event_extraction",
        "schema": {
          "type": "object",
          "properties": {
            "location": { "type": "string" },
            "date": { "type": "string" },
            "participants": { "type": "array", "items": { "type": "string" } }
          },
          "required": ["location", "date", "participants"],
          "additionalProperties": false
        },
        "strict": true
      }
    }
  }'
For more, refer to Anthropic’s detailed documentation on Structured Outputs here.
Last modified on May 13, 2026