Compare models
Up to 4 models side by side: list prices, what a month of real traffic costs, limits and capabilities. The best value in each row is marked with a check.
| Model | Gemini 3.8 Live Google · Realtime | Gemini Live 2.5 Flash Native Audio Google · Realtime |
|---|---|---|
| Overview | ||
| Released | - | - |
| Status | Current | Current in 24 days Leaves Vertex AI on 13 Dec 2026 |
| Open weights | No | No |
| Hosts APIs you can call it on | 2 | 1 |
| Price · USD per million tokens, at the lab's own API where it sells the model | ||
| Priced at | Google AI Studio | Vertex AI |
| Input | $0.75 | $0.50 |
| Output | $4.50 | $2.00 |
| Cached input | - | - |
| Batch input / output | - | - |
| Cheapest anywhere input / output | $0.75 / $4.50 Google AI Studio | $0.50 / $2.00 Vertex AI |
| Monthly bill · at the price above, 30 days, with each workload's cache and batch use | ||
| Chat assistant 5,000 a day, 2K in, 500 out | $563 | $300 |
| RAG over documents 2,000 a day, 8K in, 600 out | $522 | $312 |
| Coding agent 1,000 a day, 40K in, 2K out | $1,170 | $720 |
| Overnight batch 20,000 a day, 4K in, 400 out | $2,880 | $1,680 |
| Limits | ||
| Context window | 131K tokens | 131K tokens |
| Max output | 66K tokens | 66K tokens |
| Capabilities | ||
| Takes in | Audio, Images, Text, Video | Audio, Images, Text, Video |
| Produces | Audio, Text | Audio, Text |
| Effort settings as listed by the source | - | - |
| Function calling | ||
| Tool calling | ||
| Built-in web search | ||
| Parallel tool calls | ||