Open Gemma instruction model for efficient chat and self-hosted deployments
Specification
most-agreed values
Context
131K
Max output
131K
Released
2024-01-01
Knowledge cutoff
2024-12
Retires
—
Open weights
yes
Input
text, pdf
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.05
Output
$0.15
Cache read
$0.136
Available from 14 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| nvidia | free | free | — | — | 131K | 16K | — |
| deepinfra | $0.05 | $0.15 | — | — | 131K | 131K | — |
| edenai | $0.05 $0.09 | $0.15 $0.29 | — | — | 131K 128K | 131K | — |
| helicone | $0.05 | $0.10 | — | — | 131K | 8K | — |
| huggingface | $0.05 | $0.15 | — | — | 131K | 131K | — |
| kilo | $0.05 | $0.15 | — | — | 131K | 16K | — |
| novita | $0.05 | $0.10 | — | — | 131K | 8K | — |
| novita-ai | $0.05 | $0.10 | — | — | 131K | 8K | — |
| openrouter | $0.05 | $0.15 | — | — | 131K | 16K | — |
| amazon-bedrock | $0.09 | $0.29 | — | — | 131K | 8K | — |
| bedrock_converse | $0.09 | $0.29 | — | — | 128K | 8K | — |
| merge-gateway | $0.09 | $0.29 | — | — | 128K | 8K | — |
| crusoe · crusoe | $0.10 | $0.10 | — | — | 131K | 131K | — |
| nano-gpt · unsloth | $0.272 | $0.272 | $0.136 | — | 131K | 16K | — |
Price history
append-only observations · a listing writes a row only when its price moves
| Date | Host | Field | $/M |
|---|---|---|---|
| 2026-09-02 | amazon-bedrock | Input | $0.05 |
| 2026-09-12 | amazon-bedrock | Input | $0.09 |
| 2026-09-02 | deepinfra | Input | $0.05 |
| 2026-09-12 | deepinfra | Input | $0.05 |
| 2026-09-02 | openrouter | Input | $0.05 |
| 2026-09-06 | openrouter | Input | $0.05 |
| 2026-09-02 | amazon-bedrock | Output | $0.10 |
| 2026-09-12 | amazon-bedrock | Output | $0.29 |
| 2026-09-02 | deepinfra | Output | $0.15 |
| 2026-09-12 | deepinfra | Output | $0.15 |
| 2026-09-02 | openrouter | Output | $0.15 |
| 2026-09-06 | openrouter | Output | $0.15 |
More from Google
most-hosted first