As of: 2026-11-19 22:11 CET. Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/ Canonical page: https://postcutoff.com/m/kolibri-1/ # Kolibri-1 Aleph Alpha, Kolibri family. Status: current. Type: reasoning model. Released: 2026-10-03. Training cutoff: 2026-06. ## How to call it | Provider | Model id | Endpoint | Docs | |---|---|---|---| | Hugging Face | | | https://huggingface.co/Aleph-Alpha/Kolibri-1 | | Self-hosted (vLLM + aleph-alpha-inference, OpenAI-compatible API) | | | https://huggingface.co/Aleph-Alpha/Kolibri-1 | ## Pricing - Price not published. - Last checked: 2026-10-03 ## Specs - Input: text - Output: text - Context window: 1,048,576 tokens - Max output: not published - Open weights: yes - Licence: apache-2.0 ## What it has not seen - Published training cutoff: 2026-06 (June 2026). - AI events after it on Post-Cutoff: 1,923 (451 major, 84 historic), as of 2026-11-19. - Already missing at launch: 664. - Briefings of the news since June 2026: https://postcutoff.com/briefings/cutoff-2026-06-s.md (short), https://postcutoff.com/briefings/cutoff-2026-06-m.md (medium), https://postcutoff.com/briefings/cutoff-2026-06.md (full). - Its card, with five things it has never heard of: https://postcutoff.com/you/kolibri-1/ ## What stands out - German-optimised tokenizer: Bilingual EN–DE 128k tokenizer; Aleph Alpha reports 11.2% fewer German tokens than GPT-5's tokenizer (an independent test on the German Basic Law found ~15%). Source: https://aleph-alpha.com/en/blog/kolibri-has-landed-a-sovereign-open-weight-model/ - Sparse 1M-token context: 78B-total / ~3.46B-active MoE (384 experts, 6 routed) with 512-token sliding-window attention and a global layer every 5th layer; up to 1,048,576 tokens of context (262,144 recommended). Source: https://huggingface.co/Aleph-Alpha/Kolibri-1 - Abstention / grounding training: Trained with a Merlin–Arthur protocol to abstain rather than hallucinate; Aleph Alpha reports an M/A grounding score of 0.23 (scale 0–0.5). Source: https://aleph-alpha.com/en/blog/kolibri-has-landed-a-sovereign-open-weight-model/ ## Notes Reasoning mode with configurable effort and tool calling. Recommended sampling temperature 1.0, top_p 0.97, top_k 128. Needs ~2×80GB GPUs (min 2× A100 80GB). Benchmarks are Aleph Alpha's own (AIME 2025 96.9 EN, GPQA Diamond 84.3 EN). Weaker than Qwen models on closed-book recall and agentic coding per reviewers. No hosted API price found. Aleph Alpha's open-weight English–German MoE. Serve with vLLM plus the `aleph-alpha-inference` package (reasoning and tool-calling parsers enabled) for an OpenAI-compatible endpoint. Model page: https://postcutoff.com/m/kolibri-1/