Calculate the cost of using gpt-4o-realtime-preview-2025-06-03 from OpenAI for your AI applications
Pricing data last updated:
Mode: Realtime
Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.
gpt-4o-realtime-preview-2025-06-03 is a realtime model from OpenAI, one of 14 realtime models they offer. It is priced at $5.00 per 1M input tokens and $20.00 per 1M output tokens, ranking 24 out of 28 realtime models by cost and cheaper than 14% of models in this category. gpt-4o-realtime-preview-2025-06-03 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 $5.00 per 1M input tokens and $20.00 per 1M output tokens, gpt-4o-realtime-preview-2025-06-03 ranks 24 out of 28 realtime models by input cost. It is more expensive compared to the median of $4.00 for realtime models, and is cheaper than 14% of models in this category.
gpt-4o-realtime-preview-2025-06-03 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-4o-realtime-preview-2025-06-03 |
|---|---|---|---|---|
| gpt-4o-realtime-preview-2024-10-01 | Azure | $5.50 | $22.00 | +10% |
| gpt-4o-realtime-preview-2024-12-17 | Azure | $5.50 | $22.00 | +10% |
| gpt-realtime-2025-08-28 | Azure | $4.00 | $16.00 | -20% |
Similar realtime models from other providers
Yes. gpt-4o-realtime-preview-2025-06-03 costs $5.00 per 1M input tokens compared to gpt-4o-realtime-preview-2024-10-01's $5.50 per 1M input tokens, making it 10% more affordable. Both are realtime models and share support for function calling, audio input, audio output.
gpt-4o-realtime-preview-2025-06-03 input pricing is $5.00 per 1M tokens, which is 25% above the median of $4.00 for realtime models. It ranks 24 out of 28 realtime models by input cost, making it cheaper than 14% of models in this category. For output, it costs $20.00 per 1M tokens compared to the median of $16.00.
Among OpenAI's 14 realtime models, gpt-4o-realtime-preview-2025-06-03 ranks 14 by input cost.
The most comparable realtime models to gpt-4o-realtime-preview-2025-06-03 are: gpt-4o-realtime-preview-2024-10-01 from Azure ($5.50/1M input tokens); gpt-4o-realtime-preview-2024-12-17 from Azure ($5.50/1M input tokens); gpt-realtime-2025-08-28 from Azure ($4.00/1M input tokens); gpt-realtime-1.5-2026-02-23 from Azure ($4.00/1M 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-4o-realtime-preview-2025-06-03 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 $5.00 and generating 1M output tokens costs $20.00.