TheRouter.aiTheRouter.ai
Back to Models

Qwen3 VL 235B

qwenqwen/qwen3-vl-235b

Qwen3 vision-language model (235B MoE, 22B active). Full multimodal: images, video, 2D/3D spatial grounding, OCR in 32 languages, GUI understanding.

Context Length
256K
Max Output
33K
Input Price
$0.360/ 1M tokens
Output Price
$1.38/ 1M tokens

Modalities

textimage→text

Pricing Breakdown

TypeRate
Input$0.360 / 1M tokens
Output$1.38 / 1M tokens

Supported Parameters

temperaturemax_tokenstop_ptoolstool_choiceresponse_formatstop

API Usage Examples

cURL
curl https://api.therouter.ai/v1/chat/completions   -H "Content-Type: application/json"   -H "Authorization: Bearer $THE_ROUTER_API_KEY"   -d '{
    "model": "qwen/qwen3-vl-235b",
    "messages": [
      {"role": "user", "content": "Summarize the key points from this input."}
    ]
  }'