Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...
| Field | Per token (USD) | Per million |
|---|---|---|
| prompt | 0.00000021 | $0.210 |
| completion | 0.0000019 | $1.90 |
| input_cache_read | 0.0000001 | $0.100 |
{
"temperature": 0.7,
"top_p": 0.8,
"frequency_penalty": null
}