Skip to main content
← Back to Models
⚖️

Aya 23 35BvsAya Expanse

Cohere vs Cohere — Side-by-side model comparison

Aya Expanse leads 3/5 categories

Head-to-Head Comparison

MetricAya 23 35BAya Expanse
Provider
Arena Rank
Context Window
8K
128K
Input Pricing
Free (open)/1M tokens
Free/1M tokens
Output Pricing
Free (open)/1M tokens
Free/1M tokens
Parameters
35B
32B
Open Source
Yes
Yes
Best For
Multilingual tasks, low-resource languages
Multilingual (23 languages), research
Release Date
May 23, 2024
Oct 24, 2024

Aya 23 35B

Aya 23 35B, developed by Cohere through the Cohere For AI research initiative, is an open-source multilingual model with 35 billion parameters and an 8K token context window supporting 23 languages. The model was developed with contributions from researchers worldwide, focusing on extending quality AI capabilities to lower-resource languages that mainstream models underserve. Aya 23 35B performs well on multilingual benchmarks, particularly for languages in Africa, South Asia, and Southeast Asia where few commercial alternatives exist. Free and open-source, it can be fine-tuned and deployed for language-specific applications without cost. The model represents Cohere's commitment to democratizing AI access globally, providing a foundation for researchers and developers working in languages outside the English-Chinese-European focus of most commercial models.

View Cohere profile →

Aya Expanse

Aya Expanse, developed by Cohere through the Cohere For AI research initiative, is a multilingual open-source model with 32 billion parameters and a 128K token context window supporting 23 languages. Building on Aya 23, it substantially extends context length and improves quality across diverse languages. The model demonstrates strong cross-lingual transfer, enabling tasks like translation, summarization, and question answering across language pairs with limited parallel training data. Its 128K context window makes it suitable for processing long documents in languages where few other models offer extended context. Free and open-source, Aya Expanse aims to democratize access to capable multilingual AI. The model is particularly valuable for researchers and organizations working in lower-resource languages that receive minimal attention from major commercial AI providers.

View Cohere profile →

Key Differences: Aya 23 35B vs Aya Expanse

1

Aya Expanse supports a larger context window (128K), allowing it to process longer documents in a single request.

2

Aya 23 35B has 35B parameters vs Aya Expanse's 32B, which affects inference speed and capability.

A

When to use Aya 23 35B

  • +Your use case involves multilingual tasks, low-resource languages
View full Aya 23 35B specs →
A

When to use Aya Expanse

  • +You need to process long documents (128K context)
  • +Your use case involves multilingual (23 languages), research
View full Aya Expanse specs →

The Verdict

Aya Expanse wins our head-to-head comparison with 3 out of 5 category wins. It's the stronger choice for multilingual (23 languages), research, though Aya 23 35B holds an edge in multilingual tasks, low-resource languages.

Last compared: April 2026 · Data sourced from public benchmarks and official pricing pages

Frequently Asked Questions

Which is better, Aya 23 35B or Aya Expanse?
In our head-to-head comparison, Aya Expanse leads in 3 out of 5 categories (arena rank, context window, input pricing, output pricing, and parameters). Aya Expanse excels at multilingual (23 languages), research, while Aya 23 35B is better suited for multilingual tasks, low-resource languages. The best choice depends on your specific requirements, budget, and use case.
How does Aya 23 35B pricing compare to Aya Expanse?
Aya 23 35B charges Free (open) per 1M input tokens and Free (open) per 1M output tokens. Aya Expanse charges Free per 1M input tokens and Free per 1M output tokens. For high-volume production workloads, the pricing difference can significantly impact total cost of ownership.
What is the context window difference between Aya 23 35B and Aya Expanse?
Aya 23 35B supports a 8K token context window, while Aya Expanse supports 128K tokens. Aya Expanse can process longer documents, codebases, and conversations in a single request. Context window size matters most for tasks involving long documents, large codebases, or extended conversations.
Can I use Aya 23 35B or Aya Expanse for free?
Aya 23 35B is a paid API model starting at Free (open) per 1M input tokens. Aya Expanse is available for free (open-source). Open-source models can be self-hosted for free but require your own GPU infrastructure.
Which model has better benchmarks, Aya 23 35B or Aya Expanse?
Aya 23 35B's arena rank is not yet available, while Aya Expanse's rank is not yet available. Note that benchmarks don't capture every use case — we recommend testing both models on your specific tasks.
Is Aya 23 35B or Aya Expanse better for coding?
Aya 23 35B's primary strength is multilingual tasks, low-resource languages. Aya Expanse's primary strength is multilingual (23 languages), research. For coding specifically, arena rank and code-specific benchmarks are the best indicators of performance.