Aya 23 8B

Name: Aya 23 8B
Author: Cohere

Catalogue only Open weights

Sovereignty and hosting

Catalogue only

This model is catalogued for reference. It is not hosted on LLM EU yet, and no first-party endpoint serves it here. Requests to it go to the provider directly, under that provider's own terms.

Summary

Aya 23 8B is the 8B member of Cohere Labs’ Aya 23 release, covering 23 languages under CC-BY-NC-4.0 with a context length of 8192 tokens. It is the multilingual baseline that appears in the OpenGPT-X European evaluation, where it scores 0.485 on EU21, below Llama 3.1 8B Instruct and Mistral 7B Instruct v0.3. It is superseded by Aya Expanse for most multilingual work.

Specifications

Provider: Cohere (CA)
Context window: 8.2k
Parameters: 8.03B
Modalities: text
License: cc-by-nc-4.0 · licence
Open weights: yes
Release date: 19 May 2024
Tasks: multilingual-support, translation, summarization

Languages

Strong: en, fr, de, es, it, pt

Adequate: nl, pl, cs, el, ro, ru, uk, tr, ar, he, fa, hi, id, vi, zh, ja, ko

Languages

Strong

Adequate

Not verified: the provider has not documented this claim. — a language is listed as strong only where a source claims it; the card links the evidence where one exists.

When to use it

Strengths

23 declared languages with a European emphasis
appears as a baseline in an independent European-language evaluation
small footprint for fine-tuning

Limits

CC-BY-NC-4.0 forbids commercial serving
8192-token context window and dated May 2024
superseded by Aya Expanse

Pricing

This model is catalogued for reference. It is not hosted on LLM EU yet, and no first-party endpoint serves it here. Requests to it go to the provider directly, under that provider's own terms.

Verification status

Where a field has no source, the card shows it as unverified instead of filling it in. An empty field is information.

LLM EU Verified means documented, not legally certified. It is not an AI Act conformity assessment and LLM EU is not an EU body.

Versions and variants

catalogue · Catalogue only · weights

Example request

curl https://api.llmeu.com/v1/chat/completions \
  -H "Authorization: Bearer $LLMEU_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"aya-23-8b","messages":[{"role":"user","content":"Hello"}]}'

No playground is deployed for this model: no endpoint serves it, so a request would have nowhere to go.

Benchmarks

EU21 average (translated ARC, HellaSwag, TruthfulQA, MMLU): 0.485 (OpenGPT-X evaluation) source

Sources

Card changelog

19 May 2024 — Release date
19 Sept 2026 — Last reviewed

Last reviewed: 19 Sept 2026