{"schema":"postcutoff/model@1","as_of":"2026-11-19T22:11:00+01:00","url":"https://postcutoff.com/m/ling-3-1-flash/","md":"https://postcutoff.com/m/ling-3-1-flash/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":"ling-3-1-flash","name":"Ling 3.1 Flash","org":"inclusionAI (Ant Group)","family":"Ling 3","released":"2026-09-29","status":"current","type":"reasoning-llm","modality_in":["text"],"modality_out":["text"],"open_weights":true,"model_license":"mit","context_window":1000000,"max_output":32768,"knowledge_cutoff":null,"pricing":{"input":0,"output":0,"unit":"per 1M tokens (USD); free trial on gateways (Vercel lists free through 2026-10-13)","source":"https://openrouter.ai/inclusionai/ling-3.1-flash"},"price_line":"Free","access":[{"provider":"OpenRouter","model_id":"inclusionai/ling-3.1-flash","url":"https://openrouter.ai/inclusionai/ling-3.1-flash"},{"provider":"Vercel AI Gateway","model_id":"inclusionai/ling-3.1-flash","url":"https://vercel.com/ai-gateway/models/ling-3.1-flash"},{"provider":"Hugging Face","model_id":"inclusionAI/Ling-3.1-flash","url":"https://huggingface.co/inclusionAI/Ling-3.1-flash"},{"provider":"Hugging Face (Oct 27 update)","model_id":"inclusionAI/Ling-3.1-flash-1019","url":"https://huggingface.co/inclusionAI/Ling-3.1-flash-1019"},{"provider":"Hugging Face (base model)","model_id":"inclusionAI/Ling-3.1-flash-base","url":"https://huggingface.co/inclusionAI/Ling-3.1-flash-base"}],"capabilities":[{"name":"560B-total / 25B-active hybrid-reasoning MoE","detail":"Sparse MoE for coding, agents and tool use; reasoning enabled by default (can be turned off via the reasoning parameter on OpenRouter); tools and tool_choice supported.","first":false,"discovered":"launch","source":"https://openrouter.ai/inclusionai/ling-3.1-flash"}],"entry":"2026-10-14-ling-3-1-flash-open-weights","notes":"Open weights released Oct 13–14, 2026 on Hugging Face (MIT, 1M context, hybrid-linear MoE: 63 KDA + 9 gated MLA layers; SGLang day-0 support on 8x H200 or 4x GB300). The Sept 29 trial was capped at 256K context; gateway trial pricing was free (Vercel through Oct 13); no official paid pricing yet. Served on Vercel by Novita. Oct 27: Ling-3.1-flash-1019 checkpoint (post-training update; model card reports AA Intelligence Index 44, up from 41) and Ling-3.1-flash-base.","verified":"2026-10-28","body_md":"Free trial model as of Oct 2, 2026. Example (OpenRouter, OpenAI-compatible):\n\n```bash\ncurl https://openrouter.ai/api/v1/chat/completions -H \"Authorization: Bearer $OPENROUTER_API_KEY\" \\\n -H \"Content-Type: application/json\" -d '{\"model\":\"inclusionai/ling-3.1-flash\",\"messages\":[{\"role\":\"user\",\"content\":\"Hello\"}]}'\n```\n\nSelf-hosting (model card, Oct 14, 2026): `docker pull lmsysorg/sglang:dev-ling-3.1-flash`, then `python3 -m sglang.launch_server --model-path inclusionAI/Ling-3.1-flash --tp 8 --ep 8 --speculative-algorithm NEXTN`. Recommended sampling: temperature 1.0, top_p 0.95, top_k 20, `enable_thinking: true`.\n\n## Changelog\n- 2026-10-14: open weights (MIT, 1M context) released; status, license, access and notes updated\n- 2026-10-28: added Ling-3.1-flash-1019 and base checkpoints","page_url":"https://postcutoff.com/m/ling-3-1-flash/","events_after":null,"major_after":null,"historic_after":null,"missing_at_launch":null,"events_since_release":1385,"you_url":"https://postcutoff.com/you/ling-3-1-flash/","briefings":null}