Not probed. OpenRouter lists no audio input for this model, so it most likely cannot hear a clip — but that field describes accepted content parts, not clip handling. Run `pnpm probe-audio` to settle it.
MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...
| Field | Per token (USD) | Per million |
|---|---|---|
| prompt | 0.000000224 | $0.224 |
| completion | 0.00000088 | $0.880 |
| input_cache_read | 0.0000000448 | $0.045 |
{
"temperature": 1,
"top_p": 0.95,
"top_k": null,
"frequency_penalty": null,
"presence_penalty": null,
"repetition_penalty": null
}