Aya Expanse 8B
Smaller Aya Expanse for single-GPU deployment. Same 23-language coverage at lower cost.
Aya Expanse 8B is a efficient AI model from Cohere. It costs $0.5000 per million input tokens and $1.50 per million output tokens (blended $0.8000/M), with a 8,000-token context window.
RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.
Hand-maintained from Cohere's published pricing; no check date on record.
- Multilingual on a single GPU
- Open weights
- 128K context
- On-prem multilingual chat
- Multilingual fine-tune base
Benchmarks
Also reported by the provider
Results on benchmarks outside the set we compare across models. They are listed for completeness and are deliberately excluded from the bars above and from every ranking on this site, because a score is only comparable against the same benchmark variant. Why benchmark scores do not compare →
- Global MMLU (23 languages, 5-shot)53.7%self-reported by Cohere · 2024-12-05 · Aya Expanse technical report: 5-shot accuracy averaged over the 23 supported languages, culturally agnostic and culturally sensitive subsets. Not the English MMLU. Not comparable with the MMLU column, so shown here and never ranked.
More from Cohere
See all 12 →Frequently asked questions
How much does Aya Expanse 8B cost?
Aya Expanse 8B costs $0.5000 per million input tokens and $1.50 per million output tokens, for a blended reference rate of $0.8000 per million tokens.
What is Aya Expanse 8B's context window?
Aya Expanse 8B supports up to 8,000 tokens of context in a single request.
What is Aya Expanse 8B best for?
Aya Expanse 8B is well suited to Multilingual on a single GPU, Open weights and 128K context.
Who makes Aya Expanse 8B?
Aya Expanse 8B is developed and served by Cohere. It was released in Oct 2024.
