Qwen / qwen/qwen3-vl-30b-a3b-thinking

Qwen3-Vl-30B-A3b-Thinking - access through LLMTR

Qwen3-Vl-30B-A3b-Thinking is a vision-language model for understanding text, images, and video. It is well suited to OCR, screenshot analysis, document understanding, and multimodal assistant workflows. The thinking variant is better suited to harder visual problems and more deliberate step-by-step analysis.

Technical specifications

Canonical IDqwen/qwen3-vl-30b-a3b-thinking
ProviderQwen
Context window256,000 tokens
OperationsRESPONSES
Modalitiestext

Pricing

A 6% platform margin applies to credit top-ups; model usage prices are not separately marked up.

OperationMetricUnitPrice
RESPONSESINPUT_TEXTPER_1M_TOKENS$0.200000
RESPONSESOUTPUT_TEXTPER_1M_TOKENS$2.40

Example usage

With existing OpenAI SDK flows, change only the base URL and model identifier.

curl https://llmtr.com/v1/chat/completions \
  -H "Authorization: Bearer llmtr-your_key" \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen/qwen3-vl-30b-a3b-thinking","messages":[{"role":"user","content":"Hello"}]}'

Related models