Cohere Aya 23 35B
Open-weights multilingual research model from Cohere covering 23 languages. 35B parameters.
Cohere Aya 23 35B is text & chat AI model from Custom, priced at €0.000 per 1M input tokens with a 8.2K tokens context window.
0.7
Pricing
API Integration
Use our OpenAI-compatible API to integrate Cohere Aya 23 35B into your application.
npm install railwailimport railwail from "railwail";
const rw = railwail("YOUR_API_KEY");
// Simple — just pass a string
const reply = await rw.run("aya-23-35b", "Hello! What can you do?");
console.log(reply);
// With message history
const reply2 = await rw.run("aya-23-35b", [
{ role: "system", content: "You are a helpful assistant." },
{ role: "user", content: "Explain quantum computing simply." },
]);
console.log(reply2);
// Full response with usage info
const res = await rw.chat("aya-23-35b", [
{ role: "user", content: "Hello!" },
], { temperature: 0.7, max_tokens: 500 });
console.log(res.choices[0].message.content);
console.log(res.usage);Deep dive — Cohere For AI's Cohere Aya 23 35B
Cohere For AI (C4AI) is the non-profit research lab of Cohere, founded in 2022 and led by Sara Hooker. Its remit is open science and global multilingual NLP. C4AI's flagship Aya initiative — launched in 2023 — coordinated 3,000+ collaborators across 119 countries to build the largest open-access multilingual instruction-tuning dataset (the Aya Collection: 513M instances across 114 languages). Aya 23, released May 2024, is the second generation of the Aya model family. It builds on Cohere's Command R base architecture and trades broad coverage (101 languages in Aya-101) for stronger per-language quality across 23 widely-used languages. Cohere itself was founded in 2019 by Aidan Gomez (co-author of 'Attention Is All You Need'), Ivan Zhang and Nick Frosst.
Visit Cohere For AI →Aya 23 35B is a dense decoder-only transformer fine-tuned from Cohere's Command R 35B base. The architecture uses grouped-query attention (8 KV heads), RoPE positional embeddings, SwiGLU activations, RMSNorm, no biases, and a 256,000-token multilingual BPE tokeniser that is particularly efficient on non-Latin scripts (Arabic, Hebrew, Korean, Japanese, Chinese). The model was instruction-tuned on the Aya Collection — 513M templated and translated instruction instances — narrowed to coverage for 23 target languages, supplemented by the Aya Dataset (204K human-curated prompt-completion pairs from 65 languages collected via the Aya Annotation Platform) and ShareGPT, Dolly and Flan corpora. There is no public RLHF or DPO stage for Aya 23. Released May 2024 under CC-BY-NC 4.0 alongside an 8B sibling.
- Parameters
- 35B (dense)
- Context
- 8.2K tokens
- State-of-the-art open multilingual performance across 23 languages
- Particularly strong on Arabic, Hebrew, Persian, Korean, Hindi, Vietnamese
- Outperforms Aya-101 13B, Mistral 7B Instruct v0.2, Gemma 1.1 7B on multilingual benchmarks
- 256K multilingual BPE tokeniser efficient for non-Latin scripts
- Open weights on Hugging Face under CC-BY-NC 4.0
- 8K context window
- Strong instruction following in covered languages
- Best for: research and academic multilingual NLP, non-commercial multilingual prototypes.
Instruction-tuned on the Aya Collection (513M instances across 114 languages, filtered to 23 target languages for the 23 variants) plus the Aya Dataset (204K human-curated multilingual prompt-completion pairs from 65 languages collected through the Aya Annotation Platform), ShareGPT, Dolly and Flan. No public RLHF stage. Base model knowledge cutoff March 2024.
License: Open weights under CC-BY-NC 4.0 — non-commercial research use only. Commercial use requires the hosted Cohere API under separate commercial terms.
Known limitations
- CC-BY-NC license blocks commercial use of the open weights
- Narrower language coverage than Aya-101 (23 vs 101 languages)
- Short 8K context by 2024 standards
- No tool-use or function-calling fine-tune
- No vision input
Frequently asked questions
Related Models
View all Text & ChatBio_ClinicalBERT
The original Bio_ClinicalBERT from Alsentzer et al., a BERT model initialized from BioBERT and further pretrained on all MIMIC-III clinical notes. Served as a fill-mask endpoint it predicts masked tokens in clinical text and produces clinical embeddings. It is the standard encoder backbone behind many downstream clinical NLP fine-tunes.
Biomedical NER (all entities)
Token-classification model from d4data that tags 84 biomedical entity types in clinical and medical text, including disease, sign, symptom, medication, dosage, lab value, body part and procedure. Trained on the Maccrobat clinical case corpus on a DistilBERT base, so it runs cheaply for high-volume tagging.
Claude Opus 4
Anthropic's most powerful model. Exceptional at complex analysis, agentic tasks, and extended reasoning.
Claude Opus 4.8
Anthropic's most capable Opus-tier model. State of the art on long-horizon agentic work, coding and knowledge tasks, with a 1M-token context window at standard pricing.
Start using Cohere Aya 23 35B today
Get started with free credits. No credit card required. Access Cohere Aya 23 35B and 100+ other models through a single API.