Simon Willison's Weblog: cohere

More model releases on 31st July

2025-07-31T21:54:47+00:00

Here are a few more model releases from today, to round out a very busy July:

Cohere released Command A Vision, their first multi-modal (image input) LLM. Like their others it's open weights under Creative Commons Attribution Non-Commercial, so you need to license it (or use their paid API) if you want to use it commercially.
San Francisco AI startup Deep Cogito released four open weights hybrid reasoning models, cogito-v2-preview-deepseek-671B-MoE, cogito-v2-preview-llama-405B, cogito-v2-preview-llama-109B-MoE and cogito-v2-preview-llama-70B. These follow their v1 preview models in April at smaller 3B, 8B, 14B, 32B and 70B sizes. It looks like their unique contribution here is "distilling inference-time reasoning back into the model’s parameters" - demonstrating a form of self-improvement. I haven't tried any of their models myself yet.
Mistral released Codestral 25.08, an update to their Codestral model which is specialized for fill-in‑the‑middle autocomplete as seen in text editors like VS Code, Zed and Cursor.
And an anonymous stealth preview model called Horizon Alpha running on OpenRouter was released yesterday and is attracting a lot of attention.

Tags: ai, generative-ai, llms, mistral, cohere, llm-release, openrouter

Introducing Command A: Max performance, minimal compute

2025-03-13T20:37:32+00:00

Introducing Command A: Max performance, minimal compute

New LLM release from Cohere. It's interesting to see which aspects of the model they're highlighting, as an indicator of what their commercial customers value the most (highlights mine):

Command A delivers maximum performance with minimal hardware costs when compared to leading proprietary and open-weights models, such as GPT-4o and DeepSeek-V3. For private deployments, Command A excels on business-critical agentic and multilingual tasks, while being deployable on just two GPUs, compared to other models that typically require as many as 32. [...]

With a serving footprint of just two A100s or H100s, it requires far less compute than other comparable models on the market. This is especially important for private deployments. [...]

Its 256k context length (2x most leading models) can handle much longer enterprise documents. Other key features include Cohere’s advanced retrieval-augmented generation (RAG) with verifiable citations, agentic tool use, enterprise-grade security, and strong multilingual performance.

It's open weights but very much not open source - the license is Creative Commons Attribution Non-Commercial and also requires adhering to their Acceptable Use Policy.

Cohere offer it for commercial use via "contact us" pricing or through their API. I released llm-command-r 0.3 adding support for this new model, plus their smaller and faster Command R7B (released in December) and support for structured outputs via LLM schemas.

(I found a weird bug with their schema support where schemas that end in an integer output a seemingly limitless integer - in my experiments it affected Command R and the new Command A but not Command R7B.)

Via @Prince_Canuma

Tags: ai, generative-ai, llms, llm, cohere, structured-extraction, llm-release

Command R+ now ranked 6th on the LMSYS Chatbot Arena

2024-04-09T16:19:09+00:00

Command R+ now ranked 6th on the LMSYS Chatbot Arena

The LMSYS Chatbot Arena Leaderboard is one of the most interesting approaches to evaluating LLMs because it captures their ever-elusive “vibes”—it works by users voting on the best responses to prompts from two initially hidden models

Big news today is that Command R+—the brand new open weights model (Creative Commons non-commercial) by Cohere—is now the highest ranked non-proprietary model, in at position six and beating one of the GPT-4s.

(Linking to my screenshot on Mastodon.)

Tags: ai, generative-ai, llms, cohere, command-r, chatbot-arena

llm-command-r

2024-04-04T17:38:42+00:00

llm-command-r

Cohere released Command R Plus today—an open weights (non commercial/research only) 104 billion parameter LLM, a big step up from their previous 35 billion Command R model.

Both models are fine-tuned for both tool use and RAG. The commercial API has features to expose this functionality, including a web-search connector which lets the model run web searches as part of answering the prompt and return documents and citations as part of the JSON response.

I released a new plugin for my LLM command line tool this morning adding support for the Command R models.

In addition to the two models it also adds a custom command for running prompts with web search enabled and listing the referenced documents.

Tags: plugins, projects, ai, generative-ai, llms, llm, cohere, command-r, rag, llm-tool-use, llm-release

Cohere int8 & binary Embeddings - Scale Your Vector Database to Large Datasets

2024-03-26T06:19:30+00:00

Cohere int8 & binary Embeddings - Scale Your Vector Database to Large Datasets

Jo Kristian Bergum told me “The accuracy retention [of binary embedding vectors] is sensitive to whether the model has been using this binarization as part of the loss function.”

Cohere provide an API for embeddings, and last week added support for returning binary vectors specifically tuned in this way.

250M embeddings (Cohere provide a downloadable dataset of 250M embedded documents from Wikipedia) at float32 (4 bytes) is 954GB.

Cohere claim that reducing to 1 bit per dimension knocks that down to 30 GB (954/32) while keeping “90-98% of the original search quality”.

Via @jobergum

Tags: embeddings, cohere, jo-kristian-bergum

Aya

2024-02-13T17:14:35+00:00

Aya

“A global initiative led by Cohere For AI involving over 3,000 independent researchers across 119 countries. Aya is a state-of-art model and dataset, pushing the boundaries of multilingual AI for 101 languages through open science.”

Both the model and the training data are released under Apache 2. The training data looks particularly interesting: “513 million instances through templating and translating existing datasets across 114 languages”—suggesting the data is mostly automatically generated.

Via Hacker News

Tags: open-source, ai, generative-ai, llms, cohere, training-data, llm-release