OpenAI / API Pricing and Routing

OpenAI gpt-realtime-mini-2025-10-06 API pricing and routing

Inspect the live model ID, provider, context window, endpoint support, billing group, and Route Key pricing signals before sending production traffic.

Model ID
gpt-realtime-mini-2025-10-06

Compare gpt-realtime-mini-2025-10-06 API pricing, context length, endpoints, billing groups, and routing availability through Route Key's OpenAI-compatible AI API gateway.

Pricing signals

Input · per token / 1M tokens
$0.60
Output · per token / 1M tokens
$2.40
Cached input · per token / 1M tokens
$0.06

Billing: per token · Available groups: default

Supported endpoints

openai

Context window

-

Model technical profile

Vendor
OpenAI
Billing
per token
Pricing schema
shell-api-modelmak-v1
Model ratio
x0.3
Completion ratio
x4
Cache read ratio
x0.1
Audio input ratio
x16.666667
Audio output ratio
x8.333333
Image ratio
x1.333333

Use this model with Route Key

Keep your existing OpenAI-compatible request shape and change the gateway, key, and model values.

Base URL
https://api.routekey.ai/v1
API key
Bearer sk-route-key
Model
gpt-realtime-mini-2025-10-06
Use this model with Route Key Model

Frequently asked questions about gpt-realtime-mini-2025-10-06

What is gpt-realtime-mini-2025-10-06?

gpt-realtime-mini-2025-10-06 is a currently listed model route from OpenAI. Confirm the live catalog for its exact ID, endpoint, group availability, and pricing signal.

How is gpt-realtime-mini-2025-10-06 API pricing calculated?

Route Key exposes the current input, output, and cached-input pricing signals for gpt-realtime-mini-2025-10-06. Effective cost can vary by billing group and route ratio.

How do I use gpt-realtime-mini-2025-10-06 with Route Key?

Set the Route Key base URL, add a Route Key API key, and send the exact model ID shown below. Start with a small request before enabling streaming or tools.