gemini-gemma-2-9b-it
- Input / 1M
- $0.35
- Output / 1M
- $1.05
- Cached input
- —
- Context
- 8K
A 1,000-token prompt costs $0.00035 to send. Token counts for Google models are estimated — approximated, because this family has no public tokenizer.
- Vision
- Tool calling
- Max output 8K
Priced closest to this
| Model | Provider | Input | Output | |
|---|---|---|---|---|
| gpt-oss-120b | Cerebras | $0.35 | $0.75 | |
| gemini-gemma-2-27b-it | $0.35 | $1.05 | ||
| codellama-34b-instruct | Perplexity | $0.35 | $1.40 | |
| command-light | Cohere | $0.30 | $0.60 | |
| gemini-2.5-flash-native-audio-latest | $0.30 | $2.50 | ||
| gemini-2.5-flash-native-audio-preview-09-2025 | $0.30 | $2.50 |