Aya Expanse 32B

cohere

A highly performant 32B multilingual model designed to rival monolingual performance through innovations in instruction tuning with data arbitrage, preference training, and model merging. Serves 23 languages including Arabic, Chinese, Japanese, Korean, and major European languages. With 128K context window, it handles substantial multilingual workloads effectively.

Try Now

Example Use Cases

Multilingual task across 23 languages

Cross-lingual reasoning and generation

Non-english content generation on a budget

Technical Specifications

Context Window

128,000 tokens

Max Output

4,000 tokens

Cache Miss Cost

$0.50 per 1M tokens

Non-Reasoning Cost

$1.50 per 1M tokens

Web Search Cost

$15 per 1K calls

Code Execution Cost

$0.19 per 1K calls

⚠️ Legacy

Made legacy on

Reason

Untested

Recommended Replacement

Claude Haiku 4.5