{"schema":"postcutoff/model@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/m/qwen3-8-27b/","md":"https://postcutoff.com/m/qwen3-8-27b/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"qwen3-8-27b","name":"Qwen3.8-27B","org":"Alibaba (Qwen)","family":"Qwen3.8","released":"2026-08-05","status":"current","type":"multimodal","modality_in":["text","image","video"],"modality_out":["text"],"open_weights":true,"model_license":"apache-2.0","context_window":262144,"max_output":null,"knowledge_cutoff":null,"pricing":{"input":0.2,"output":2.5,"unit":"per 1M tokens, OpenRouter's listed price for qwen/qwen3.8-27b (read from its models API 2026-10-25); its providers range from $0.02-$0.99 in and $0.50-$3.20 out, Alibaba's own endpoint there $0.425 / $2.55; a :free variant also exists","source":"https://openrouter.ai/qwen/qwen3.8-27b"},"price_line":"$0.20 in, $2.50 out per 1M tokens","access":[{"provider":"Hugging Face","url":"https://huggingface.co/Qwen/Qwen3.8-27B"},{"provider":"Hugging Face (FP8)","url":"https://huggingface.co/Qwen/Qwen3.8-27B-FP8"},{"provider":"OpenRouter","model_id":"qwen/qwen3.8-27b","url":"https://openrouter.ai/qwen/qwen3.8-27b"},{"provider":"OpenRouter (free tier)","model_id":"qwen/qwen3.8-27b:free","url":"https://openrouter.ai/qwen/qwen3.8-27b"},{"provider":"Web app","url":"https://chat.qwen.ai"}],"capabilities":[{"name":"Dense open VLM with agentic focus","detail":"27B dense native vision-language model (images and hour-scale video) tuned for coding and long-horizon agent tasks, Apache-2.0.","first":false,"discovered":"launch","source":"https://huggingface.co/Qwen/Qwen3.8-27B"},{"name":"Thinking control","detail":"Thinking on by default, can be disabled per request; reasoning_effort and preserve_thinking supported.","first":false,"discovered":"launch","source":"https://huggingface.co/Qwen/Qwen3.8-27B"},{"name":"Extensible to 1M context","detail":"262,144 tokens native, extensible up to 1,000,000.","first":false,"discovered":"launch","source":"https://huggingface.co/Qwen/Qwen3.8-27B"}],"entry":null,"notes":"Best Apache-2.0 Qwen for self-hosting; also the go-to open Qwen VL model (Qwen3-VL successor). First-party hosted API 'coming soon' on Qwen Cloud at time of check. No first-party price page found; OpenRouter price used (2026-10-25). ARC Prize verified (Oct 1 2026): ARC-AGI-2 42.4% at $0.45/task, ARC-AGI-1 87.5% at $0.22/task (x.com/arcprize/status/2105751611570069908).","verified":"2026-10-25","body_md":"Open-weight (Apache-2.0) dense multimodal model for local/self-hosted coding agents and vision tasks; runs on vLLM, SGLang, Transformers.\n\n```bash\nvllm serve Qwen/Qwen3.8-27B --max-model-len 262144\n```\n\nSources: https://huggingface.co/Qwen/Qwen3.8-27B · https://openrouter.ai/qwen/qwen3.8-27b","page_url":"https://postcutoff.com/m/qwen3-8-27b/","events_after":null,"major_after":null,"historic_after":null,"missing_at_launch":null,"events_since_release":1686,"you_url":"https://postcutoff.com/you/qwen3-8-27b/","briefings":null}