Calculate the cost of using gpt-realtime-mini from OpenAI for your AI applications
Pricing data last updated:
Mode: Realtime
Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.
gpt-realtime-mini is a realtime model from OpenAI, one of 14 realtime models they offer. It is priced at $0.60 per 1M input tokens and $2.40 per 1M output tokens, ranking 7 out of 28 realtime models by cost and cheaper than 68% of models in this category. gpt-realtime-mini supports function calling, audio input, audio output. It accepts up to 128K input tokens.
Note: Use the interactive calculator above to estimate costs for your specific usage patterns.
Use the maximum token limits shown above to understand the model's capacity. This model can handle up to 128,000 input tokens. The maximum output length is 4,096 tokens.
At $0.60 per 1M input tokens and $2.40 per 1M output tokens, gpt-realtime-mini ranks 7 out of 28 realtime models by input cost. It is more affordable compared to the median of $4.00 for realtime models, and is cheaper than 68% of models in this category.
gpt-realtime-mini is one of 14 OpenAI realtime models, with support for function calling, audio input, audio output.
| Model | Provider | Input / 1M tokens | Output / 1M tokens | vs gpt-realtime-mini |
|---|---|---|---|---|
| gpt-4o-mini-realtime-preview-2024-12-17 | Azure | $0.66 | $2.64 | +10% |
| gpt-realtime-mini-2025-10-06 | Azure | $0.60 | $2.40 | 0% |
| gemini-live-2.5-flash-preview-native-audio-09-2025 | Vertex AI | $0.30 | $2.00 | -50% |
Similar realtime models from other providers
Yes. gpt-realtime-mini costs $0.60 per 1M input tokens compared to gpt-4o-mini-realtime-preview-2024-12-17's $0.66 per 1M input tokens, making it 10% more affordable. Both are realtime models and share support for function calling, audio input, audio output.
gpt-realtime-mini input pricing is $0.60 per 1M tokens, which is 85% below the median of $4.00 for realtime models. It ranks 7 out of 28 realtime models by input cost, making it cheaper than 68% of models in this category. For output, it costs $2.40 per 1M tokens compared to the median of $16.00.
Among OpenAI's 14 realtime models, gpt-realtime-mini ranks 4 by input cost.
The most comparable realtime models to gpt-realtime-mini are: gpt-4o-mini-realtime-preview-2024-12-17 from Azure ($0.66/1M input tokens); gpt-realtime-mini-2025-10-06 from Azure ($0.60/1M input tokens); gemini-live-2.5-flash-preview-native-audio-09-2025 from Vertex AI ($0.30/1M input tokens); gemini-live-2.5-flash-preview-native-audio-09-2025 from Google Gemini ($0.30/1M input tokens). These alternatives were selected based on similar capabilities, pricing, and provider diversity. You can compare any of these models in detail using the Bifrost Model Library.
You can monitor OpenAI service health in real time on the Bifrost OpenAI Status page. It tracks current component status, active incidents, and historical reliability data pulled from the official status page every 60 seconds.
gpt-realtime-mini is priced based on input and output tokens. Use the interactive calculator at the top of this page to estimate costs for your specific workload. Enter your expected input and output tokens volume and the calculator will show the total cost breakdown. For reference, processing 1M input tokens costs $0.60 and generating 1M output tokens costs $2.40.