Structured outputs

Give the model a JSON schema and it answers with a JSON object that follows it. Your code parses the answer instead of pulling fields out of free text.

Responses
Chat Completions
Messages

import json
import os
from openai import OpenAI

client = OpenAI(base_url="https://api.naga.ac/v1", api_key=os.environ["NAGA_API_KEY"])

response = client.responses.create(
    model="deepseek-v4.1-flash",
    input="Name one European capital and its country.",
    text={
        "format": {
            "type": "json_schema",
            "name": "capital",
            "strict": True,
            "schema": {
                "type": "object",
                "properties": {"city": {"type": "string"}, "country": {"type": "string"}},
                "required": ["city", "country"],
                "additionalProperties": False,
            },
        }
    },
)

print(json.loads(response.output_text))

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.naga.ac/v1", apiKey: process.env.NAGA_API_KEY });

const response = await client.responses.create({
  model: "deepseek-v4.1-flash",
  input: "Name one European capital and its country.",
  text: {
    format: {
      type: "json_schema",
      name: "capital",
      strict: true,
      schema: {
        type: "object",
        properties: { city: { type: "string" }, country: { type: "string" } },
        required: ["city", "country"],
        additionalProperties: false,
      },
    },
  },
});

console.log(JSON.parse(response.output_text));

curl https://api.naga.ac/v1/responses \
  -H "Authorization: Bearer $NAGA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4.1-flash",
    "input": "Name one European capital and its country.",
    "text": {
      "format": {
        "type": "json_schema",
        "name": "capital",
        "strict": true,
        "schema": {
          "type": "object",
          "properties": {"city": {"type": "string"}, "country": {"type": "string"}},
          "required": ["city", "country"],
          "additionalProperties": false
        }
      }
    }
  }'

import json
import os
from openai import OpenAI

client = OpenAI(base_url="https://api.naga.ac/v1", api_key=os.environ["NAGA_API_KEY"])

completion = client.chat.completions.create(
    model="deepseek-v4.1-flash",
    messages=[{"role": "user", "content": "Name one European capital and its country."}],
    response_format={
        "type": "json_schema",
        "json_schema": {
            "name": "capital",
            "strict": True,
            "schema": {
                "type": "object",
                "properties": {"city": {"type": "string"}, "country": {"type": "string"}},
                "required": ["city", "country"],
                "additionalProperties": False,
            },
        },
    },
)

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

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.naga.ac/v1", apiKey: process.env.NAGA_API_KEY });

const completion = await client.chat.completions.create({
  model: "deepseek-v4.1-flash",
  messages: [{ role: "user", content: "Name one European capital and its country." }],
  response_format: {
    type: "json_schema",
    json_schema: {
      name: "capital",
      strict: true,
      schema: {
        type: "object",
        properties: { city: { type: "string" }, country: { type: "string" } },
        required: ["city", "country"],
        additionalProperties: false,
      },
    },
  },
});

console.log(JSON.parse(completion.choices[0].message.content));

curl https://api.naga.ac/v1/chat/completions \
  -H "Authorization: Bearer $NAGA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4.1-flash",
    "messages": [{"role": "user", "content": "Name one European capital and its country."}],
    "response_format": {
      "type": "json_schema",
      "json_schema": {
        "name": "capital",
        "strict": true,
        "schema": {
          "type": "object",
          "properties": {"city": {"type": "string"}, "country": {"type": "string"}},
          "required": ["city", "country"],
          "additionalProperties": false
        }
      }
    }
  }'

import json
import os
from anthropic import Anthropic

client = Anthropic(base_url="https://api.naga.ac", api_key=os.environ["NAGA_API_KEY"])

message = client.messages.create(
    model="claude-haiku-4.5",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Name one European capital and its country."}],
    output_config={
        "format": {
            "type": "json_schema",
            "schema": {
                "type": "object",
                "properties": {"city": {"type": "string"}, "country": {"type": "string"}},
                "required": ["city", "country"],
                "additionalProperties": False,
            },
        }
    },
)

text = "".join(block.text for block in message.content if block.type == "text")
print(json.loads(text))

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

const client = new Anthropic({ baseURL: "https://api.naga.ac", apiKey: process.env.NAGA_API_KEY });

const message = await client.messages.create({
  model: "claude-haiku-4.5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Name one European capital and its country." }],
  output_config: {
    format: {
      type: "json_schema",
      schema: {
        type: "object",
        properties: { city: { type: "string" }, country: { type: "string" } },
        required: ["city", "country"],
        additionalProperties: false,
      },
    },
  },
});

for (const block of message.content) {
  if (block.type === "text") console.log(JSON.parse(block.text));
}

The answer is a JSON string such as {"city": "Lisbon", "country": "Portugal"}, which the example parses and prints.

Schema options in each format

Each format puts the schema in its own field and returns the JSON in its own place:

	Responses	Chat Completions	Messages
JSON that follows a schema	`text: {"format": {"type": "json_schema", "name", "schema", "strict"}}`	`response_format: {"type": "json_schema", "json_schema": {"name", "schema", "strict"}}`	`output_config: {"format": {"type": "json_schema", "schema"}}`
Any JSON object	`text: {"format": {"type": "json_object"}}`	`response_format: {"type": "json_object"}`	Not available
Where the JSON is	`response.output_text`	`choices[0].message.content`	The first `text` block

JSON mode, json_object, asks for valid JSON without a schema. Say in the prompt that you want JSON when you use it, since some models need the hint. The SDK helpers client.responses.parse() and client.chat.completions.parse() build the same request from a Pydantic or Zod model, and they work against NagaAI too.

Models without schema support

Check parameters of the model’s chat operation in /v1/models for response_format. The list covers every provider that serves the model, so the provider that takes a given request can still lack schema support. In that case NagaAI asks the provider for JSON mode and adds your schema to the prompt. The answer is still JSON, but nothing guarantees it follows the schema, so validate it in your code before you use it.

Get started

How NagaAI works

Guides

API guides

Account

Product

Schema options in each format

Models without schema support

​Schema options in each format

​Models without schema support

Schema options in each format

Models without schema support