Calculate the cost of using gemini-3.8-live from Vertex AI for your AI applications
Pricing data last updated:
Mode: Realtime
Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.
gemini-3.8-live is a realtime model from Vertex AI, one of 5 realtime models they offer. It is priced at $0.75 per 1M input tokens and $4.50 per 1M output tokens, ranking 20 out of 42 realtime models by cost and cheaper than 45% of models in this category. gemini-3.8-live supports vision, function calling, audio input, audio output, web search — one of only 4 realtime models with this combination. Its 131K-token context window is in the top 29% among realtime models.
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 131,072 input tokens. The maximum output length is 65,536 tokens.
At $0.75 per 1M input tokens and $4.50 per 1M output tokens, gemini-3.8-live ranks 20 out of 42 realtime models by input cost. It is competitively priced compared to the median of $0.75 for realtime models, and is cheaper than 45% of models in this category.
gemini-3.8-live is one of 5 Vertex AI realtime models, one of only 4 realtime models combining audio input, audio output, function calling, vision, web search. its 131K-token context window places it in the top 29% of realtime models.
| Model | Provider | Input / 1M tokens | Output / 1M tokens | vs gemini-3.8-live |
|---|---|---|---|---|
| gemini-3.1-flash-live-preview | Google Gemini | $0.75 | $4.50 | 0% |
| gemini-3.8-live | Google Gemini | $0.75 | $4.50 | 0% |
| gemini-3.8-live-extended-thinking | Google Gemini | $0.75 | $4.50 | 0% |
Similar realtime models from other providers
No. gemini-3.8-live costs $0.75 per 1M input tokens while gemini-3.1-flash-live-preview costs $0.75 per 1M input tokens, making gemini-3.1-flash-live-preview 0% more affordable for input. However, gemini-3.8-live may offer different capabilities or performance characteristics that justify the price difference.
gemini-3.8-live input pricing is $0.75 per 1M tokens, which is 0% at the median of $0.75 for realtime models. It ranks 20 out of 42 realtime models by input cost, making it cheaper than 45% of models in this category. For output, it costs $4.50 per 1M tokens compared to the median of $4.50.
Among Vertex AI's 5 realtime models, gemini-3.8-live ranks 4 by input cost. Its combination of audio input, audio output, function calling, vision, web search is shared by only 3 other realtime models.
The most comparable realtime models to gemini-3.8-live are: gemini-3.1-flash-live-preview from Google Gemini ($0.75/1M input tokens); gemini-3.8-live from Google Gemini ($0.75/1M input tokens); gemini-3.8-live-extended-thinking from Google Gemini ($0.75/1M input tokens); gemini-live-2.5-flash-preview-native-audio-09-2025 from Google Gemini ($0.50/1M 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.
gemini-3.8-live supports up to 131,072 input tokens, placing it in the top 29% of realtime models by context window size (rank 5 of 38). This makes it suitable for processing long documents, extensive code repositories, or maintaining detailed conversation histories.
gemini-3.8-live 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 $0.75 and generating 1M output tokens costs $4.50.