openai/gpt-audio-2025-08-28GPT Audio 2025 08 28 (openai/gpt-audio-2025-08-28) is an AI model from OpenAI with a 128,000-token context window and 16,384 max output tokens, priced at $2.50/1M input and $10.00/1M output tokens. Available via the haimaker.ai OpenAI-compatible API.
OpenAI's dedicated audio model for high-quality speech synthesis and audio generation tasks.
| Mode | chat |
| Context Window | 128,000 tokens |
| Max Output | 16,384 tokens |
| Function Calling | Supported |
| Vision | - |
| Reasoning | - |
| Web Search | - |
| Url Context | - |
from openai import OpenAI
client = OpenAI(
base_url="https://api.haimaker.ai/v1",
api_key="YOUR_API_KEY",
)
response = client.chat.completions.create(
model="openai/gpt-audio-2025-08-28",
messages=[
{"role": "user", "content": "Hello, how are you?"}
],
)
print(response.choices[0].message.content)GPT Audio 2025 08 28 (openai/gpt-audio-2025-08-28) has a 128,000-token context window and supports up to 16,384 output tokens per request.
GPT Audio 2025 08 28 is priced at $2.50 per 1M input tokens and $10.00 per 1M output tokens when accessed via the haimaker.ai OpenAI-compatible API.
GPT Audio 2025 08 28 supports function calling.
Send requests to https://api.haimaker.ai/v1/chat/completions with model "openai/gpt-audio-2025-08-28" using any OpenAI-compatible SDK. Authentication uses a Bearer API key from https://app.haimaker.ai.
OpenAI-compatible endpoint. Start building in minutes.