Calculate the cost of using gemini-3.8-live-extended-thinking from Google Gemini 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-extended-thinking is a realtime model from Google Gemini, one of 8 realtime models they offer. It is priced at $0.75 per 1M input tokens and $4.50 per 1M output tokens, ranking 25 out of 45 realtime models by cost and cheaper than 44% of models in this category. gemini-3.8-live-extended-thinking supports vision, function calling, reasoning, audio input, audio output, web search — one of only 2 realtime models with this combination. Its 131K-token context window is in the top 25% 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-extended-thinking ranks 25 out of 45 realtime models by input cost. It is competitively priced compared to the median of $0.75 for realtime models, and is cheaper than 44% of models in this category.
gemini-3.8-live-extended-thinking is one of 8 Google Gemini realtime models, one of only 2 realtime models combining audio input, audio output, function calling, reasoning, vision, web search. its 131K-token context window places it in the top 25% of realtime models.
| Model | Provider | Input / 1M tokens | Output / 1M tokens | vs gemini-3.8-live-extended-thinking |
|---|---|---|---|---|
| gemini-live-2.5-flash-native-audio | Vertex AI | $0.50 | $2.00 | -33% |
| gemini-live-2.5-flash-preview-native-audio-09-2025 | Vertex AI | $0.50 | $2.00 | -33% |
| gpt-4o-mini-realtime-preview-2024-12-17 | Azure | $0.66 | $2.64 | -12% |
Similar realtime models from other providers
No. gemini-3.8-live-extended-thinking costs $0.75 per 1M input tokens while gemini-live-2.5-flash-native-audio costs $0.50 per 1M input tokens, making gemini-live-2.5-flash-native-audio 33% more affordable for input. However, gemini-3.8-live-extended-thinking may offer different capabilities or performance characteristics that justify the price difference.
gemini-3.8-live-extended-thinking input pricing is $0.75 per 1M tokens, which is 0% at the median of $0.75 for realtime models. It ranks 25 out of 45 realtime models by input cost, making it cheaper than 44% of models in this category. For output, it costs $4.50 per 1M tokens compared to the median of $4.50.
Among Google Gemini's 8 realtime models, gemini-3.8-live-extended-thinking ranks 7 by input cost. It is the most affordable Google Gemini model with reasoning support. Its combination of audio input, audio output, function calling, reasoning, vision, web search is shared by only 1 other realtime model.
The most comparable realtime models to gemini-3.8-live-extended-thinking are: gemini-live-2.5-flash-native-audio from Vertex AI ($0.50/1M input tokens); gemini-live-2.5-flash-preview-native-audio-09-2025 from Vertex AI ($0.50/1M input tokens); gpt-4o-mini-realtime-preview-2024-12-17 from Azure ($0.66/1M input tokens); gpt-realtime-2.1-mini from Azure ($0.60/1M 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.
Yes. At $0.75 per 1M input tokens, gemini-3.8-live-extended-thinking is the most affordable realtime model that supports reasoning. This makes it a strong option for reasoning-dependent workloads where cost efficiency matters.
gemini-3.8-live-extended-thinking supports up to 131,072 input tokens, placing it in the top 25% of realtime models by context window size (rank 10 of 40). This makes it suitable for processing long documents, extensive code repositories, or maintaining detailed conversation histories.
gemini-3.8-live-extended-thinking 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.