Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...
| Field | Per token (USD) | Per million |
|---|---|---|
| prompt | 0.00000008 | $0.080 |
| completion | 0.00000035 | $0.350 |
| input_cache_read | 0.00000004 | $0.040 |
{
"temperature": null,
"top_p": null,
"frequency_penalty": null
}