All AI models · LLM benchmarks · Methodology

Alibaba

Qwen/Qwen3.5-27B

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

Model facts

Context window
262K tokens
Maximum output
66K tokens
Cheapest paid input
$0.26 per 1M tokens
Cheapest paid output
$2.09 per 1M tokens
Open weights
yes
Providers
1

Capabilities and modalities

reasoning, tool calling, temperature control, open weights, text, image, video.

Local hardware estimate

At 4K context: Q4_K_M 18.0 GiB, Q8_0 30.9 GiB, F16 55.2 GiB working memory.

Parameters
27.8 billion
Architecture
qwen3_5
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: $0.26 input / $2.09 output per 1M tokens

API providers

  • SiliconFlow (China) — model id Qwen/Qwen3.5-27B; $0.26 input / $2.09 output per 1M tokens; provider documentation