Routing and Extensions

Auriko’s gateway and extensions parameters use identical structure in Chat Completions and the Response API. Pass them at the top level of the request body.

Prerequisites

An Auriko API key
Python 3.10+ with the OpenAI SDK (pip install openai) or the Auriko SDK (pip install auriko)
- OR Node.js 18+ with the OpenAI SDK (npm install openai) or @auriko/sdk (npm install @auriko/sdk)

Route across models

Route a request across multiple models:

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AURIKO_API_KEY"],
    base_url="https://api.auriko.ai/v1"
)

response = client.responses.create(
    input="What is the capital of France?",
    extra_body={
        "gateway": {
            "models": ["gpt-4o", "claude-sonnet-4-20250514"],
            "routing": {"optimize": "cost"}
        }
    }
)

print(response.output_text)

import OpenAI from "openai";

const client = new OpenAI({
    apiKey: process.env.AURIKO_API_KEY,
    baseURL: "https://api.auriko.ai/v1",
});

const response = await client.responses.create({
    input: "What is the capital of France?",
    // @ts-expect-error Auriko extension
    gateway: {
        models: ["gpt-4o", "claude-sonnet-4-20250514"],
        routing: { optimize: "cost" },
    },
});

console.log(response.output_text);

import os
from auriko import Client

client = Client(
    api_key=os.environ["AURIKO_API_KEY"],
    base_url="https://api.auriko.ai/v1"
)

response = client.responses.create(
    input="What is the capital of France?",
    gateway={
        "models": ["gpt-4o", "claude-sonnet-4-20250514"],
        "routing": {"optimize": "cost"}
    }
)

print(response.output_text)
print(f"Provider: {response.routing_metadata.provider}")
print(f"Cost: ${response.routing_metadata.cost.usd}")

import { Client } from "@auriko/sdk";

const client = new Client({
    apiKey: process.env.AURIKO_API_KEY,
    baseUrl: "https://api.auriko.ai/v1",
});

const response = await client.responses.create({
    input: "What is the capital of France?",
    gateway: {
        models: ["gpt-4o", "claude-sonnet-4-20250514"],
        routing: { optimize: "cost" },
    },
});

console.log(response.output_text);
console.log(`Provider: ${response.routing_metadata?.provider}`);
console.log(`Cost: $${response.routing_metadata?.cost?.usd}`);

curl https://api.auriko.ai/v1/responses \
  -H "Authorization: Bearer $AURIKO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "input": "What is the capital of France?",
    "gateway": {
      "models": ["gpt-4o", "claude-sonnet-4-20250514"],
      "routing": {"optimize": "cost"}
    }
  }'

Set routing options

Control routing strategy with gateway.routing:

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AURIKO_API_KEY"],
    base_url="https://api.auriko.ai/v1"
)

response = client.responses.create(
    input="Summarize the benefits of solar energy",
    extra_body={
        "gateway": {
            "models": ["gpt-4o", "claude-sonnet-4-20250514", "gemini-2.5-flash"],
            "routing": {
                "optimize": "cost",
                "max_cost_per_1m": 5.0,
                "max_ttft_ms": 2000
            }
        }
    }
)

print(response.output_text)

import OpenAI from "openai";

const client = new OpenAI({
    apiKey: process.env.AURIKO_API_KEY,
    baseURL: "https://api.auriko.ai/v1",
});

const response = await client.responses.create({
    input: "Summarize the benefits of solar energy",
    // @ts-expect-error Auriko extension
    gateway: {
        models: ["gpt-4o", "claude-sonnet-4-20250514", "gemini-2.5-flash"],
        routing: {
            optimize: "cost",
            max_cost_per_1m: 5.0,
            max_ttft_ms: 2000,
        },
    },
});

console.log(response.output_text);

import os
from auriko import Client

client = Client(
    api_key=os.environ["AURIKO_API_KEY"],
    base_url="https://api.auriko.ai/v1"
)

response = client.responses.create(
    input="Summarize the benefits of solar energy",
    gateway={
        "models": ["gpt-4o", "claude-sonnet-4-20250514", "gemini-2.5-flash"],
        "routing": {
            "optimize": "cost",
            "max_cost_per_1m": 5.0,
            "max_ttft_ms": 2000
        }
    }
)

print(response.output_text)

import { Client } from "@auriko/sdk";

const client = new Client({
    apiKey: process.env.AURIKO_API_KEY,
    baseUrl: "https://api.auriko.ai/v1",
});

const response = await client.responses.create({
    input: "Summarize the benefits of solar energy",
    gateway: {
        models: ["gpt-4o", "claude-sonnet-4-20250514", "gemini-2.5-flash"],
        routing: {
            optimize: "cost",
            max_cost_per_1m: 5.0,
            max_ttft_ms: 2000,
        },
    },
});

console.log(response.output_text);

curl https://api.auriko.ai/v1/responses \
  -H "Authorization: Bearer $AURIKO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "input": "Summarize the benefits of solar energy",
    "gateway": {
      "models": ["gpt-4o", "claude-sonnet-4-20250514", "gemini-2.5-flash"],
      "routing": {
        "optimize": "cost",
        "max_cost_per_1m": 5.0,
        "max_ttft_ms": 2000
      }
    }
  }'

See Routing Options for all strategies and Advanced Routing for constraint combinations.

Pass provider extensions

Pass provider-specific parameters with extensions:

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AURIKO_API_KEY"],
    base_url="https://api.auriko.ai/v1"
)

response = client.responses.create(
    model="claude-sonnet-4-20250514",
    input="Write a haiku about programming",
    extra_body={
        "extensions": {
            "anthropic": {
                "metadata": {"user_id": "user-123"}
            }
        }
    }
)

print(response.output_text)

import OpenAI from "openai";

const client = new OpenAI({
    apiKey: process.env.AURIKO_API_KEY,
    baseURL: "https://api.auriko.ai/v1",
});

const response = await client.responses.create({
    model: "claude-sonnet-4-20250514",
    input: "Write a haiku about programming",
    // @ts-expect-error Auriko extension
    extensions: {
        anthropic: {
            metadata: { user_id: "user-123" },
        },
    },
});

console.log(response.output_text);

import os
from auriko import Client

client = Client(
    api_key=os.environ["AURIKO_API_KEY"],
    base_url="https://api.auriko.ai/v1"
)

response = client.responses.create(
    model="claude-sonnet-4-20250514",
    input="Write a haiku about programming",
    extensions={
        "anthropic": {
            "metadata": {"user_id": "user-123"}
        }
    }
)

print(response.output_text)

import { Client } from "@auriko/sdk";

const client = new Client({
    apiKey: process.env.AURIKO_API_KEY,
    baseUrl: "https://api.auriko.ai/v1",
});

const response = await client.responses.create({
    model: "claude-sonnet-4-20250514",
    input: "Write a haiku about programming",
    extensions: {
        anthropic: {
            metadata: { user_id: "user-123" },
        },
    },
});

console.log(response.output_text);

curl https://api.auriko.ai/v1/responses \
  -H "Authorization: Bearer $AURIKO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-20250514",
    "input": "Write a haiku about programming",
    "extensions": {
      "anthropic": {
        "metadata": {"user_id": "user-123"}
      }
    }
  }'

See Extensions and Thinking for all provider extension fields.

Access routing metadata

Every Auriko response includes routing metadata with provider, cost, and latency details. With the Auriko SDK (Python, TypeScript):

import os
from auriko import Client

client = Client(
    api_key=os.environ["AURIKO_API_KEY"],
    base_url="https://api.auriko.ai/v1"
)

response = client.responses.create(
    model="gpt-4o",
    input="Hello!"
)

meta = response.routing_metadata
print(f"Provider: {meta.provider}")
print(f"Model: {meta.provider_model_id}")
print(f"Strategy: {meta.routing_strategy}")
print(f"TTFT: {meta.ttft_ms}ms")
print(f"Throughput: {meta.throughput_tps} tps")
if meta.cost:
    print(f"Cost: ${meta.cost.usd}")

import { Client } from "@auriko/sdk";

const client = new Client({
    apiKey: process.env.AURIKO_API_KEY,
    baseUrl: "https://api.auriko.ai/v1",
});

const response = await client.responses.create({
    model: "gpt-4o",
    input: "Hello!",
});

const meta = response.routing_metadata;
console.log(`Provider: ${meta?.provider}`);
console.log(`Model: ${meta?.provider_model_id}`);
console.log(`Strategy: ${meta?.routing_strategy}`);
console.log(`TTFT: ${meta?.ttft_ms}ms`);
console.log(`Throughput: ${meta?.throughput_tps} tps`);
console.log(`Cost: $${meta?.cost?.usd}`);

For routing metadata with the OpenAI SDK, see OpenAI Compatibility. For streaming, access routing metadata from the completed response:

import os
from auriko import Client

client = Client(
    api_key=os.environ["AURIKO_API_KEY"],
    base_url="https://api.auriko.ai/v1"
)

stream = client.responses.create(
    model="gpt-4o",
    input="Hello!",
    stream=True
)

for event in stream:
    if event.type == "response.output_text.delta":
        print(event.delta, end="", flush=True)

meta = stream.completed_response.routing_metadata
print(f"\nProvider: {meta.provider}, Cost: ${meta.cost.usd}")

import { Client } from "@auriko/sdk";

const client = new Client({
    apiKey: process.env.AURIKO_API_KEY,
    baseUrl: "https://api.auriko.ai/v1",
});

const stream = await client.responses.create({
    model: "gpt-4o",
    input: "Hello!",
    stream: true,
});

for await (const event of stream) {
    if (event.type === "response.output_text.delta") {
        process.stdout.write(event.delta);
    }
}

const meta = stream.completedResponse?.routing_metadata;
console.log(`\nProvider: ${meta?.provider}, Cost: $${meta?.cost?.usd}`);

For routing metadata with the OpenAI SDK, see OpenAI Compatibility. Fields: provider, provider_model_id, model_canonical, routing_strategy, ttft_ms, throughput_tps, cost.usd. See Routing Options, Advanced Routing, Response Metadata, and Response Headers for details.

​Prerequisites

​Route across models

​Set routing options

​Pass provider extensions

​Access routing metadata

Prerequisites

Route across models

Set routing options

Pass provider extensions

Access routing metadata