# aya-101 [Canonical model page](https://headlessthrones.com/models/cohere-aya-101) · [Model library](https://headlessthrones.com/models) Public catalog reference from Headless Thrones. Exact catalog ID: `cohere-aya-101`. Catalog source-check date: 2026-10-23. This brief contains the public catalog answers and any catalog guide, not private drafts, historical editorial revisions or independently measured rankings. The canonical HTML page may also display separately published editorial. Current catalog answers ## What to know about aya-101 AI-compiled from linked model documentation. This is a catalog reference, not an independent performance review. Catalog checked October 23, 2026. [Exact model](https://headlessthrones.com/models/cohere-aya-101#model-answer-identity) · [Access](https://headlessthrones.com/models/cohere-aya-101#model-answer-access) · [Inputs & outputs](https://headlessthrones.com/models/cohere-aya-101#model-answer-modalities) · [License](https://headlessthrones.com/models/cohere-aya-101#model-answer-license) · [Model details](https://headlessthrones.com/models/cohere-aya-101#model-answer-research) · [Weight details](https://headlessthrones.com/models/cohere-aya-101#model-answer-repository) ### Which aya-101 does this page describe? aya-101 is a model record from **Cohere** in the Aya family. [Source](https://huggingface.co/CohereLabs/aya-101) A separate version identifier is not documented in this record; the model name alone does not establish which snapshot a service runs. ### How can you access aya-101? The catalog documents **Open weights** access for aya-101. [Source](https://huggingface.co/CohereLabs/aya-101) As of the catalog check, this version was listed without confirmed general availability. [Source](https://huggingface.co/CohereLabs/aya-101) Open weights means the model weights are distributed for use under their stated terms. It does not establish a hosted API, an open-source license, or a hardware requirement. ### What can aya-101 receive and generate? Documented inputs: **Text**. [Source](https://huggingface.co/CohereLabs/aya-101/resolve/e7dad472b9de8a30a00cf08a05c19003bf59028d/README.md) Documented outputs: **Text**. [Source](https://huggingface.co/CohereLabs/aya-101/resolve/e7dad472b9de8a30a00cf08a05c19003bf59028d/README.md) Input support and output generation are separate capabilities. Reading an image does not establish image generation; a text output listing does not establish speech output. File sizes, formats and media limits depend on the documented implementation. ### What license is recorded for aya-101? The recorded license label is **apache-2.0**. [Source](https://huggingface.co/CohereLabs/aya-101) Read the linked license and associated use terms for this exact version before redistribution, commercial deployment or fine-tuning. A label alone does not establish every permission, restriction or obligation, and it does not determine the terms of a separate hosted service. ### What distinguishes aya-101? These details come from the linked publisher material for this model. Reported capabilities and training descriptions are publisher statements, not independent test results. **Multilingual instruction model**: Instruction-following model for 101 languages, trained using multilingual Aya, xP3x, DataProvenance and ShareGPT-Command data. [Source](https://huggingface.co/CohereLabs/aya-101/resolve/e7dad472b9de8a30a00cf08a05c19003bf59028d/README.md) **Nominal parameters**: Publisher reports 13 billion nominal parameters. [Source](https://huggingface.co/CohereLabs/aya-101/resolve/e7dad472b9de8a30a00cf08a05c19003bf59028d/README.md) **Architecture**: Uses the mT5-XXL architecture. [Source](https://huggingface.co/CohereLabs/aya-101/resolve/e7dad472b9de8a30a00cf08a05c19003bf59028d/README.md) **Instruction training size**: Fine-tuning saw 25 million examples. [Source](https://huggingface.co/CohereLabs/aya-101/resolve/e7dad472b9de8a30a00cf08a05c19003bf59028d/README.md) **Language scope**: Training datasets cover the 101 languages supported by mT5. [Source](https://huggingface.co/CohereLabs/aya-101/resolve/e7dad472b9de8a30a00cf08a05c19003bf59028d/README.md) ### What is documented about the aya-101 checkpoint? This evidence refers to `CohereLabs/aya-101` at recorded revision `e7dad472b9de8a30a00cf08a05c19003bf59028d`, checked October 23, 2026. [Repository metadata](https://huggingface.co/api/models/CohereLabs/aya-101) Safetensors metadata records **12,921,057,280 stored parameters**. This is a stored-weight count, not necessarily the number activated per token, a download size or a GPU-memory requirement. [Repository metadata](https://huggingface.co/api/models/CohereLabs/aya-101) Recorded architecture class: `T5ForConditionalGeneration`. [Repository metadata](https://huggingface.co/api/models/CohereLabs/aya-101) Listed library: `transformers`. Check that library's version and model support before loading the weights. [Repository metadata](https://huggingface.co/api/models/CohereLabs/aya-101) Repository language labels: afr, amh, ara, aze, bel, ben, bul, cat, ceb, ces, cym, dan, deu, ell, eng, epo, est, eus, fin, fil, fra, fry, gla, gle, glg, guj, hat, hau, heb, hin, hun, hye, ibo, ind, isl, ita, jav, jpn, kan, kat, kaz, khm, kir, kor, kur, lao, lav, lat, lit, ltz, mal, mar, mkd, mlg, mlt, mon, mri, msa, mya, nep, nld, nor, nso, nya, ory, pan, pes, pol, por, pus, ron, rus, sin, slk, slv, smo, sna, snd, som, sot, spa, sqi, srp, sun, swa, swe, tam, tel, tgk, tha, tur, twi, ukr, urd, uzb, vie, xho, yid, yor, and zho. These labels are not independent evaluations of language quality. [Repository metadata](https://huggingface.co/api/models/CohereLabs/aya-101) Repository access gate: `false`. This records the repository's gate setting when checked; licensing and use terms still apply. [Repository metadata](https://huggingface.co/api/models/CohereLabs/aya-101) #### What the configuration file says The pinned `config.json` contains these values. [Pinned configuration](https://huggingface.co/CohereLabs/aya-101/resolve/e7dad472b9de8a30a00cf08a05c19003bf59028d/config.json) `torch_dtype`: float32 Configuration values describe the checkpoint and its implementation. In particular, max\_position\_embeddings, sliding\_window and rope\_scaling do not independently establish an API context limit, tested usable length or hardware requirement. Runtime, quantization, cache, batch size and input length affect deployment behavior. Read the retrieved model card for setup and qualifications. [Model card](https://huggingface.co/CohereLabs/aya-101/resolve/e7dad472b9de8a30a00cf08a05c19003bf59028d/README.md) **Catalog qualifications:** Official publisher model repository; listed status confirms a catalog entry, not a verified hosted API service. [Source 1](https://huggingface.co/api/models/CohereLabs/aya-101) · [Source 2](https://huggingface.co/CohereLabs/aya-101/resolve/e7dad472b9de8a30a00cf08a05c19003bf59028d/README.md) · [Source 3](https://huggingface.co/CohereLabs/aya-101/resolve/e7dad472b9de8a30a00cf08a05c19003bf59028d/config.json) **Evidence still missing here:** context or input capacity, knowledge and training-data cutoffs, and tested hardware requirements. Missing documentation is not evidence that a feature is unavailable. Headless Thrones has not independently benchmarked this model for this reference. Evaluate it on representative work before choosing it; these facts do not rank its accuracy, reliability, speed or suitability against another model. Keep the exact version in view ## Other Aya models from Cohere. These are separate records in the same publisher family. A shared family name does not establish equal capabilities or interchangeable licenses. ### [aya-expanse-32b](https://headlessthrones.com/models/cohere-aya-expanse-32b) API · Open weights · 128,000 context tokens ### [aya-vision-32b](https://headlessthrones.com/models/cohere-aya-vision-32b) API · Open weights · 16,000 context tokens ### [tiny-aya-earth](https://headlessthrones.com/models/cohere-tiny-aya-earth) API · Open weights · 8,000 context tokens ### [tiny-aya-fire](https://headlessthrones.com/models/cohere-tiny-aya-fire) API · Open weights · 8,000 context tokens ### [tiny-aya-global](https://headlessthrones.com/models/cohere-tiny-aya-global) API · Open weights · 8,000 context tokens ### [tiny-aya-water](https://headlessthrones.com/models/cohere-tiny-aya-water) API · Open weights · 8,000 context tokens