Probed: partially recovered the spoken codeword. Treat sound commentary as unverified.
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 | — |
| completion | 0 | — |
{
"temperature": 1,
"top_p": 0.95,
"top_k": 64,
"frequency_penalty": null,
"presence_penalty": null,
"repetition_penalty": null
}