Anthropic’s Claude 3 Sonnet model is now available as an option to power Tabnine Chat

We’re thrilled to announce that Tabnine is partnering with Anthropic, the leading AI research and safety company to make the Claude 3 Sonnet model available as one of the underlying LLMs that powers Tabnine Chat. You get the full capability of Tabnine Chat with the Claude 3 Sonnet model including code generation, code explanations, documentation generation, AI-created tests, and more. Additionally, when using the Claude 3 Sonnet model, Tabnine Chat delivers highly personalized recommendations by utilizing the context from locally available data in your IDE as well as your organization’s global codebases.

Claude 3: The next generation of Claude models from Anthropic

Released in March 2024, Claude 3 offers significant updates over its predecessor (Claude 2) and delivers the best combination of speed and performance for enterprise use cases. The Claude 3 family consists of three models: Claude 3 Haiku, Claude 3 Sonnet, and Claude 3 Opus. The benchmarks conducted by Anthropic demonstrate that the entire Claude 3 family of models delivers increased capability in data analysis, nuanced content creation, and code generation. The Claude 3 Sonnet model performed excellently in our internal benchmarks, so we’re starting our support for the Claude 3 family with Sonnet.  

Partnership with Anthropic

Tabnine is partnering with Anthropic to provide the Claude 3 Sonnet model as one of the underlying LLMs to support Tabnine Chat. With this strategic partnership, Tabnine Chat accesses the Claude 3 Sonnet model using the API from Amazon Bedrock instead of accessing the model via third-party APIs. Since the Claude 3 Sonnet model is hosted on Amazon Bedrock, Tabnine sends data to Amazon Bedrock for the purposes of computing responses to the user prompts. Amazon Bedrock ensures that the data transferred between your IDE and the Amazon API endpoint is encrypted in transit to prevent eavesdropping or person-in-the-middle attacks. Additionally, the data at rest is also encrypted.

Extending the switchable models functionality with cutting-edge models

A few weeks ago, we launched the switchable models capability for Tabnine Chat which allows users to switch the model that powers Tabnine Chat in real time. With today’s announcement, we’re extending that capability to include support for the Claude 3 Sonnet model. Today’s announcement comes on the heels of support for the recently introduced OpenAI GPT-4o model and Codestral, Mistral’s first-ever code model, and demonstrates our commitment to bringing new, state-of-the-art models to Tabnine Chat as they become available.

You can choose from the following models with Tabnine’s AI software development chat tools:

• Tabnine Protected: Tabnine’s original model, designed to deliver high performance without the risks of intellectual property violations or exposing your code and data to others. 
• Tabnine + Mistral: Tabnine’s newest offering, built to deliver the highest class of performance while still maintaining complete privacy over your data.
• Claude 3 Sonnet: The latest generation of the Claude model from Anthropic that delivers the highest levels of performance for teams that are willing to share their data externally. 
• GPT-4o, GPT-4.0 Turbo, and GPT-3.5 Turbo: The industry’s most popular LLMs, proven to deliver the highest levels of performance for teams willing to share their data externally.
• Codestral: Trained on more than 80 programming languages, Codestral — Mistral’s first-ever code model, demonstrates proficiency in both widely used and less-common languages. This model is recommended for users looking for the best possible performance who are comfortable sharing their data externally and using models trained on any publicly available code.

You’re not locked into any one of these models. Switch instantly between them for specific projects, use cases, or to meet the requirements of specific teams. We plan to make more models available for Tabnine Chat in the near future. This eliminates any worry about missing out on LLM innovations and makes it simple to use new models as they emerge. It future-proofs your investment in AI and enables your team to focus on accelerating the software development life cycle using Tabnine.

During model selection, Tabnine provides transparency into the behaviors and characteristics of each of the available models to help you decide which one is right for your situation. For example, for projects where data privacy and legal risks are less important, you can use a model optimized for performance over compliance such as Claude 3 Sonnet. As you switch to working on projects that have stricter requirements for privacy and protection, you can change to a model like Tabnine Protected that is built for that purpose. The underlying LLM can be changed with just a few clicks — and Tabnine Chat adapts instantly.

Check out this short video that shows the Claude 3 Sonnet model in action: 

As Tabnine users, there’s no additional cost for you to use the Claude 3 Sonnet model. 

We provide complete control when selecting models that power Tabnine Chat. All the models are available to Tabnine Pro users who can pick the model that fits their use case. 

For enterprise SaaS users, only the Tabnine Protected model is available by default. Any Tabnine administrators who need access to the Claude 3 Sonnet model or any additional models can contact our Support team, and we’ll enable the specific models on your account. 

Check out our Docs to learn more about this functionality. If you’re not yet a customer, you can sign up for Tabnine Pro today — it’s free for 90 days.