Release Notes

January 31, 2025

Deprecation of the Classify endpoint via default Embed models

Effective January 31st, 2025, we are deprecating the use of default Embed models with the Classify endpoint.

This deprecation does not affect usage of the Classify endpoint with fine-tuned Embed models. Fine-tuned models continue to be fully supported and are recommended for achieving optimal classification performance.

For guidance on implementing Classify with fine-tuned models, please refer to our Classify fine-tuning documentation.

January 16, 2025

Aya Expanse is Available on WhatsApp!

Aya Expanse is a multilingual large language model that is designed to expand the number of languages covered by generative AI. It is optimized to perform well in 23 languages, including Arabic, Chinese (simplified & traditional), Czech, Dutch, English, French, German, Greek, Hebrew, Russian, Spanish, and more.

Now, you can talk to Aya Expanse directly in the popular messaging service WhatsApp! All of Aya’s functionality is avaible through the app, and you can find more details here.

December 13, 2024

Announcing Command R7b

We’re thrilled to announce the release of Command R7B, the smallest, fastest, and final model in our R family of enterprise-focused large language models (LLMs). With a context window of 128K, Command R7B offers state-of-the-art performance across a variety of real-world tasks, and is designed for use cases in which speed, cost, and compute are important. Specifically, Command R7B is excellent for retrieval-augmented generation, tool use, and agentic applications where complex reasoning, multiple actions, and information-seeking are important for success.

Command R7B is available today on the Cohere Platform as well as accessible on HuggingFace, or you can access it in the SDK with command-r7b-12-2024. For more information, check out our dedicated blog post.

December 2, 2024

Announcing Rerank-v3.5

We’re pleased to announce the release of Rerank 3.5 our newest and most performant foundational model for ranking. Rerank 3.5 has a context length of 4096, SOTA performance on Multilingual Retrieval tasks and Reasoning Capabilities. In addition, Rerank 3.5 has SOTA performance on BEIR and domains such as Finance, E-commerce, Hospitality, Project Management, and Email/Messaging Retrieval tasks.

In the rest of these release notes, we’ll provide more details about changes to the api.

Technical Details

API Changes:

Along with the model, we are releasing V2 of the Rerank API. It includes the following major changes:

  • model is now a required parameter
  • max_chunks_per_doc has been replaced by max_tokens_per_doc; max_tokens_per_doc will determine the maximum amount of tokens a document can have before truncation. The default value for max_tokens_per_doc is 4096.
  • support for passing a list of objects for the documents parameter has been removed - if your documents contain structured data, for best performance we recommend formatting them as YAML strings.

Example request

cURL
1POST https://api.cohere.ai/v2/rerank
2{
3    "model": "rerank-v3.5",
4    "query": "What is the capital of the United States?",
5    "top_n": 3,
6    "documents": ["Carson City is the capital city of the American state of Nevada.",
7                  "The Commonwealth of the Northern Mariana Islands is a group of islands in the Pacific Ocean. Its capital is Saipan.",
8                  "Washington, D.C. (also known as simply Washington or D.C., and officially as the District of Columbia) is the capital of the United States. It is a federal district.",
9                  "Capitalization or capitalisation in English grammar is the use of a capital letter at the start of a word. English usage varies from capitalization in other languages.",
10                  "Capital punishment has existed in the United States since beforethe United States was a country. As of 2017, capital punishment is legal in 30 of the 50 states."]
11}
November 27, 2024

Structured Outputs support for tool use

Today, we’re pleased to announce that we have added Structured Outputs support for tool use in the Chat API.

In addition to supporting Structured Outputs with JSON generation via the response_format parameter, Structured Outputs will be available with Tools as well via the strict_tools parameter.

Setting strict_tools to true ensures that tool calls will follow the provided tool schema exactly. This means the tool calls are guaranteed to adhere to the tool names, parameter names, parameter data types, and required parameters, without the risk of hallucinations.

See the Structured Outputs documentation to learn more.

October 22, 2024

Embed v3.0 Models are now Multimodal

Today we’re announcing updates to our embed-v3.0 family of models. These models now have the ability to process images into embeddings. There is no change to existing text capabilities which means there is no need to re-embed texts you have already processed with our embed-v3.0 models.

In the rest of these release notes, we’ll provide more details about technical enhancements, new features, and new pricing.

Technical Details

API Changes:

The Embed API has two major changes:

  • Introduced a new input_type called image
  • Introduced a new parameter called images

Example request on how to process

cURL
1POST https://api.cohere.ai/v1/embed
2{
3    "model": "embed-multilingual-v3.0",
4    "input_type": "image",
5    "embedding_types": ["float"],
6    "images": [enc_img]
7}

Restrictions:

  • The API only accepts images in the base format of the following: png, jpeg,Webp, and gif
  • Image embeddings currently does not support batching so the max images sent per request is 1
  • The maximum image sizez is 5mb
  • The images parameter only accepts a base64 encoded image formatted as a Data Url
September 26, 2024

New Embed, Rerank, Chat, and Classify APIs

We’re excited to introduce improvements to our Chat, Classify, Embed, and Rerank APIs in a major version upgrade, making it easier and faster to build with Cohere. We are also releasing new versions of our Python, TypeScript, Java, and Go SDKs which feature cohere.ClientV2 for access to the new API.

New at a glance

Other updates

We are simplifying the Chat API by removing support for the following parameters available in V1:

  • search_queries_only, which generates only a search query given a user’s message input. search_queries_only is not supported in the V2 Chat API today, but will be supported at a later date.
  • connectors, which enables users to register a data source with Cohere for RAG queries. To use the Chat V2 API with web search, see our migration guide for instructios to implement a web search tool.
  • conversation_id, used to manage chat history on behalf of the developer. This will not be supported in the V2 Chat API.
  • prompt_truncation, used to automatically rerank and remove documents if the query did not fit in the model’s context limit. This will not be supported in the V2 Chat API.
  • force_single_step, which forced the model to finish tool calling in one set of turns. This will not be supported in the V2 Chat API.
  • preamble, used for giving the model task, context, and style instructions. Use a system turn at the beginning of your messages array in V2.
  • citation_quality, for users to select between fast citations, accurate citations (slightly higher latency than fast), or citations off. In V2 Chat, we are introducing a top level citation_options parameter for all citation settings. citation_quality will be replaced by a mode parameter within citation_options.

See our Chat API migration guide for detailed instructions to update your implementation.

These APIs are in Beta and are subject to updates. We welcome feedback in our Discord channel.

Older posts
Built with