Aura-2-EN (deepgram/aura-2-en) is priced at $0.030 per 1K characters through AIgateway. AIgateway charges pass-through on the underlying Deepgram rate plus a 5% platform fee applied at credit top-up — nothing per-call, no monthly minimum. Free tier available.
AIgateway bills at the same per-token rate Deepgram publishes. There's no inflated sticker price; the model-vendor's invoice and your gateway invoice agree on the token count and unit cost. Usage is aggregated to the nearest fraction of a cent in D1 and surfaced live in your dashboard.
The only margin on top is a 5% platform fee, applied at credit top-up — not per-call. A $100 top-up funds $95 of provider calls. Cache hits (when you use prompt caching or semantic cache) bill at 10% of the uncached cost, so long-context agent workloads often run net cheaper than calling Deepgram directly.
No subscription and no monthly minimum. Free tier gives you 100 requests/day on Kimi K2.6. Paid tier starts at a $5 top-up with no auto-renew. BYOK (bring your own Deepgram key) is supported on Enterprise if you already have a direct contract you want to preserve.
# pip install aigateway-py openai
from openai import OpenAI
client = OpenAI(
base_url="https://api.aigateway.sh/v1",
api_key="sk-aig-...",
)
audio = client.audio.speech.create(
model="deepgram/aura-2-en",
voice="alloy",
input="Hello from AIgateway.",
)
audio.stream_to_file("out.mp3")import OpenAI from "openai";
import fs from "node:fs";
const client = new OpenAI({
baseURL: "https://api.aigateway.sh/v1",
apiKey: process.env.AIGATEWAY_KEY,
});
const audio = await client.audio.speech.create({
model: "deepgram/aura-2-en",
voice: "alloy",
input: "Hello from AIgateway.",
});
const buf = Buffer.from(await audio.arrayBuffer());
fs.writeFileSync("out.mp3", buf);Aura-2-EN is priced at $0.030 per 1K characters. Full breakdown is on this page's how-it-works section.
Aura-2-EN is not on the free tier; the 100 free requests/day go to Kimi K2.6. Paid tier starts at a $5 top-up.
Not natively. AIgateway's semantic cache can still hit duplicate prompts and bill cached hits at 10% of the uncached rate.
Pass-through pricing means you automatically get whatever tier discount Deepgram publishes. AIgateway doesn't mark up; the 5% platform fee applies flat regardless of volume. Enterprise customers can negotiate committed-use discounts on top.
Every call returns usage.prompt_tokens and usage.completion_tokens in the response body, same as OpenAI. We also write the exact cost into x-aigateway-cost response header. Full audit log is in the dashboard.