Google: Lyria 3 Clip Preview vs OpenAI: GPT Audio
A side-by-side comparison of Google: Lyria 3 Clip Preview (Free) and OpenAI: GPT Audio ($8.75 / 1M tokens) using current USD prices and capabilities from the api14 catalog. Both run through the same OpenAI-compatible API.
Specifications
| Google: Lyria 3 Clip Preview | OpenAI: GPT Audio | |
|---|---|---|
| Provider | OpenAI | |
| Input | - | $8.75 / 1M tokens |
| Output | - | $35.00 / 1M tokens |
| Audio input | - | $112.00 / 1M tokens |
| Audio output | - | $224.00 / 1M tokens |
| Context window | 1,048,576 | 128,000 |
| Max output | 65,536 | 16,384 |
| Input | text, image | text, audio |
| Output | text, audio | text, audio |
| Tool calling | ||
| Structured output | ||
| Reasoning control | ||
| Added | Mar 30, 2026 | Jan 19, 2026 |
Key differences
- Google: Lyria 3 Clip Preview reads 8.2× more context (1,048,576 tokens).
- Only OpenAI: GPT Audio supports tool calling.
- Only OpenAI: GPT Audio supports structured JSON output.
Switch with one string
Both models use the same endpoint and request shape. Change the model value from "google/lyria-3-clip-preview" to "openai/gpt-audio" and prompts, streaming and tools keep working.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api14.com/api/v1",
apiKey: process.env.API14_API_KEY,
});
const result = await client.chat.completions.create({
"model": "openai/gpt-audio",
"messages": [
{
"role": "user",
"content": "Explain vector databases in two sentences."
}
]
});
console.log(result.choices[0].message.content);