Probed: missed a spoken codeword inside the clip. Any comment it makes on sound is invented.
SHAPE: yellow square AUDIO: NONE
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
| Field | Per token (USD) | Per million |
|---|---|---|
| prompt | 0.0000002 | $0.200 |
| completion | 0.0000004 | $0.400 |
{
"temperature": 1,
"top_p": 0.95,
"top_k": 64,
"frequency_penalty": null,
"presence_penalty": null,
"repetition_penalty": null
}