Sonic API

Run cartesia/sonic through FastInfra's OpenAI-compatible API. Pay per token, no subscription, routed to the cheapest available provider.

Read the docs
Pricing

Sonic pricing

Billed per token used. Prices sync automatically from wholesale providers.

Direction Price per 1M tokens
Input$68.25
Output
Availability

Served by 1 provider

Requests route to Together AI by default (cheapest). Pin a specific provider with the :provider suffix.

Provider Upstream model ID
together cartesia/sonic
Quickstart

Call Sonic in 30 seconds

Works with any OpenAI SDK — change the base URL and API key only.

Python

from openai import OpenAI

client = OpenAI(api_key="YOUR_API_KEY", base_url="https://api.fastinfra.ai/v1")

response = client.chat.completions.create(
    model="cartesia/sonic",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

curl

curl https://api.fastinfra.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "cartesia/sonic",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
FAQ

Sonic — common questions

How much does the cartesia/sonic API cost?

On FastInfra, cartesia/sonic costs $68.25/1M input, $0/1M output tokens. Billing is per token used, with no subscription.

Is cartesia/sonic compatible with the OpenAI SDK?

Yes. FastInfra exposes cartesia/sonic through an OpenAI-compatible endpoint at https://api.fastinfra.ai/v1 — point any OpenAI SDK at that base URL with a FastInfra API key and keep your existing code.

Which providers serve cartesia/sonic?

cartesia/sonic is available from 1 provider(s): together. Requests route to Together AI by default (cheapest); append ":provider" to the model ID to pin one.