Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon...
| Field | Per token (USD) | Per million |
|---|---|---|
| prompt | 0.00000025 | $0.250 |
| completion | 0.00000075 | $0.750 |
| input_cache_read | 0.00000012 | $0.120 |
{
"temperature": 0.7,
"top_p": 0.8,
"frequency_penalty": null
}