All AI models · LLM benchmarks · Methodology

Alibaba

Qwen: Qwen3 VL 8B Thinking

Qwen vision-language model for visual reasoning, documents, and agent tasks

Model facts

Context window
131K tokens
Maximum output
33K tokens
Cheapest paid input
$0.18 per 1M tokens
Cheapest paid output
$2.1 per 1M tokens
Open weights
no
Providers
1

Capabilities and modalities

reasoning, tool calling, structured output, attachments, temperature control, text, image.

Observed price history

  • 2026-08-24: $0.18 input / $2.1 output per 1M tokens

API providers

  • Kilo Gateway — model id qwen/qwen3-vl-8b-thinking; $0.18 input / $2.1 output per 1M tokens; provider documentation