All AI models · LLM benchmarks · Methodology

Qwen2.5-VL 7B Instruct

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

Model facts

Context window
131K tokens
Maximum output
8K tokens
Cheapest paid input
$0.287 per 1M tokens
Cheapest paid output
$0.717 per 1M tokens
Open weights
yes
Providers
3

Capabilities and modalities

tool calling, attachments, temperature control, open weights, text, image, audio, video.

Local hardware estimate

At 4K context: Q4_K_M 6.1 GiB, Q8_0 9.9 GiB, F16 17.2 GiB working memory.

Parameters
8.3 billion
Architecture
qwen2_5_vl
Model license
apache-2.0

Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.

Observed price history

  • 2026-08-24: $0.287 input / $0.717 output per 1M tokens

API providers

  • Alibaba (China) — model id qwen2-5-vl-7b-instruct; $0.287 input / $0.717 output per 1M tokens; provider documentation
  • Alibaba — model id qwen2-5-vl-7b-instruct; $0.35 input / $1.05 output per 1M tokens; provider documentation
  • Qiniu — model id qwen2.5-vl-7b-instruct; not published input / not published output per 1M tokens; provider documentation