Does GPT-Realtime support streaming?

Yes. GPT-Realtime supports real-time streaming audio input and output for low-latency voice conversations.

What is the context window of GPT-Realtime?

GPT-Realtime has a 32,000-token context window optimized for real-time voice interactions.

What is GPT-Realtime best used for?

GPT-Realtime is optimized for real-time voice conversations and audio interactions. It supports streaming voice input/output and function calling.

Can I use the OpenAI Realtime API to call GPT-Realtime?

Yes. Set the model parameter to “gpt-realtime” and use your MixRoute API key with the Realtime endpoint.

What is the max output length for gpt-realtime?

gpt-realtime supports up to 4096 output tokens per request. Plan your prompts to stay within this limit, and use the max_tokens or max_completion_tokens parameter to control output length.

How should you set the output budget for gpt-realtime?

For gpt-realtime, set the max_tokens or max_completion_tokens parameter to control spending per call. Start with a budget aligned to your typical response length and increase only when longer outputs are genuinely needed. Monitor token usage in the API response headers to tune your budget over time.

Can you call GPT-Realtime with the OpenAI SDK you already use?

Yes. GPT-Realtime is reachable through an OpenAI-compatible endpoint, so an existing OpenAI SDK client works after pointing the base URL at MixRoute and setting the model parameter to gpt-realtime . Keep your current request and response handling.

Model detail

GPT-Realtime

Provided by OpenAI

Pay-as-you-go

An OpenAI model for live voice and text interactions, supporting real-time communication over WebRTC, WebSocket, and SIP.

Model specs

Model ID: gpt-realtime

Context length: 32K
Max output: 4.096K
I/O modalities
Released: 2025-08

API endpoints

One MixRoute gateway, OpenAI-compatible

OpenAI-compatible /v1/chat/completions POST

Pricing

Flat rate, unit: /1M Tokens

Input

$75.0000 /1M Tokens

Completion

$150.0000 /1M Tokens

Selection summary

Quickly judge whether it fits your workload

What is this model good for?

An OpenAI model for live voice and text interactions

An OpenAI model for live voice and text interactions, supporting real-time communication over WebRTC, WebSocket, and SIP.

What should you check before using it?

Confirm audio formats, sample rates, and pricing

OpenAI model that supports tool calling, streaming, prompt caching, vision input and the OpenAI SDK. Knowledge cutoff: 2023-10-01. Released 2025-08-28.

Why use it through MixRoute?

GPT-Realtime cache reads cut repeated-prompt cost

Cached prefixes are billed at 0.40 USD per 1M tokens instead of 32.00 USD, so repeated system prompts cost less. MixRoute serves GPT-Realtime on the OpenAI-compatible endpoint /v1/chat/completions; point your existing client at https://api.mixroute.ai/v1 with the model ID gpt-realtime and re-run your integration tests.

Capabilities & compatibility

Unconfirmed capabilities stay "Unknown," no guesses

Tool calling

GPT-Realtime supports function and tool calls.

EX Send a tools definition; the response returns tool_calls to execute and feed results back.

Streaming

GPT-Realtime supports streamed responses.

EX stream: true streams tokens incrementally, so chat UIs render as they arrive.

Prompt caching

GPT-Realtime supports prompt caching under supported routing conditions.

EX Keep the system prompt and tool definitions at the start of the request; repeated prefixes are automatically billed at the cache-read rate.

Vision input

GPT-Realtime can process image inputs alongside text.

EX Pass a base64-encoded image in a image_url content part alongside text messages.

OpenAI SDK

Call GPT-Realtime through MixRoute's OpenAI-compatible endpoint.

EX Change base_url to https://api.mixroute.ai/v1; everything else follows the OpenAI style.

Token cost estimator

Live estimate from this page's pricing, not an actual bill

Input tokens Max per request 32K

Output tokens Max per request 4.096K

Requests / month

Cache hit rate –

This model has no cache-read price; caching is not counted

FAQ

Compare gpt-realtime against models of similar capability and pricing on your actual workload. Evaluate latency, output quality, instruction following, and cost per task. Run side-by-side tests with your own prompts — the best model depends on your specific use case, not just benchmark scores.

Get started

01

Create an API key

Generate a key in the Console; one key calls every model.
02

Set the base URL

Fully OpenAI SDK-compatible; just swap the URL to connect.

https://api.mixroute.ai/v1
03

Specify the model ID

In the request's model field, enter:

gpt-realtime

Create an API key

New users get $5 in free credits

Test this model and alternate routes with the same request format

Start from a real workload, then let quality, total cost, and failure conditions decide whether to send production traffic.

Create an API key View integration docs