Back to models
available
Gemini 3.8 Flash TTS
google/gemini-3-8-flash-ttsPrices
- Input
$0.50 per 1M tokens
verified- Input (batch)
$0.25 per 1M tokens
verified- Input (cached read, batch)
$0.0625 per 1M tokens
verified- Input (cached read, flex)
$0.025 per 1M tokens
verified- Input (cached read, priority)
$0.225 per 1M tokens
verified- Input (cached read)
$0.125 per 1M tokens
verified- Input (flex)
$0.25 per 1M tokens
verified- Input (priority)
$0.90 per 1M tokens
verified- Output
$9.00 per 1M tokens
verified- Output (audio)
$9.00 per 1M tokens
low- Output (batch)
$4.50 per 1M tokens
verified- Output (flex)
$4.50 per 1M tokens
verified- Output (priority)
$16.20 per 1M tokens
verified
Also available on
The same model, sold by someone else. The price above is the maker's own.
| Channel | What | Price |
|---|---|---|
| Google Vertex AI | Input | $0.50 per 1M tokens |
| Output | $9.00 per 1M tokens | |
| Output (audio) | $9.00 per 1M tokens | |
| Other · vercel | Input | $0.50 per 1M tokens |
| Input (cached read) | $0.125 per 1M tokens | |
| Output | $9.00 per 1M tokens |
Specifications
- Provider
- Context window
- 8,192
- Max output tokens
- 16,384
- Open weights
- no
- Released
- 09/23/2026
- Retires
- no date announced
- First seen by this tracker
Price history
No price of this model has changed since we started tracking it.
- Input
- 0.5 per 1M tokens, unchanged since 09/24/2026
- Output
- 9 per 1M tokens, unchanged since 09/24/2026
- Input (cached read)
- 0.125 per 1M tokens, unchanged since 09/24/2026
- Input (batch)
- 0.25 per 1M tokens, unchanged since 09/24/2026
- Output (batch)
- 4.5 per 1M tokens, unchanged since 09/24/2026
- Input (cached read, batch)
- 0.0625 per 1M tokens, unchanged since 09/24/2026
- Input (flex)
- 0.25 per 1M tokens, unchanged since 09/24/2026
- Output (flex)
- 4.5 per 1M tokens, unchanged since 09/24/2026
- Input (cached read, flex)
- 0.025 per 1M tokens, unchanged since 09/24/2026
- Input (priority)
- 0.9 per 1M tokens, unchanged since 09/24/2026
- Output (priority)
- 16.2 per 1M tokens, unchanged since 09/24/2026
- Input (cached read, priority)
- 0.225 per 1M tokens, unchanged since 09/24/2026
- Output (audio)
- 9 per 1M tokens, unchanged since 09/24/2026