GPT Realtime
openai/gpt-realtimeGPT Realtime (openai/gpt-realtime) is an AI model from OpenAI with a 32,000-token context window and 4,096 max output tokens, priced at $4.00/1M input and $16.00/1M output tokens. Available via the haimaker.ai OpenAI-compatible API.
Overview
OpenAI's real-time model for low-latency conversational applications with streaming audio and text.
Features & Capabilities
| Mode | chat |
| Context Window | 32,000 tokens |
| Max Output | 4,096 tokens |
| Function Calling | Supported |
| Vision | - |
| Reasoning | - |
| Web Search | - |
| Url Context | - |
API Usage
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-realtime",
messages=[
{"role": "user", "content": "Hello, how are you?"}
],
)
print(response.choices[0].message.content)Frequently Asked Questions
What is the context window of GPT Realtime?
GPT Realtime (openai/gpt-realtime) has a 32,000-token context window and supports up to 4,096 output tokens per request.
How much does GPT Realtime cost?
GPT Realtime is priced at $4.00 per 1M input tokens and $16.00 per 1M output tokens when accessed via the haimaker.ai OpenAI-compatible API.
What features does GPT Realtime support?
GPT Realtime supports function calling.
How do I use GPT Realtime via API?
Send requests to https://api.haimaker.ai/v1/chat/completions with model "openai/gpt-realtime" using any OpenAI-compatible SDK. Authentication uses a Bearer API key from https://app.haimaker.ai.
Use GPT Realtime with the haimaker API
OpenAI-compatible endpoint. Start building in minutes.