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 2.5 Flash TTS Google · Speech | Gemini 3.8 Flash TTS Google · Speech |
|---|---|---|
| Overview | ||
| Released | - | - |
| Status | Older Newer: Gemini 3.8 Flash TTS | Current |
| Open weights | No | No |
| Hosts APIs you can call it on | 1 | 3 |
| Price · USD per million tokens, at the lab's own API where it sells the model | ||
| Priced at | Vertex AI | Google AI Studio |
| Input | $0.50 | $0.50 |
| Output | $10.00 | $9.00 |
| Cached input | - | - |
| Batch input / output | $0.25 / - | $0.25 / $4.50 |
| Cheapest anywhere input / output | $0.50 / $10.00 Vertex AI | $0.50 / $9.00 Google AI Studio |
| 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 | $900 | $825 |
| RAG over documents 2,000 a day, 8K in, 600 out | $600 | $564 |
| Coding agent 1,000 a day, 40K in, 2K out | $1,200 | $1,140 |
| Overnight batch 20,000 a day, 4K in, 400 out | $3,000 | $1,680 |
| Limits | ||
| Context window | - | 8K tokens |
| Max output | - | 16K tokens |
| Capabilities | ||
| Takes in | Text | Text |
| Produces | Audio | Audio |
| Effort settings as listed by the source | - | - |
| Batch API | ||