LogoLogo
Tabnine websiteContact Sales
  • πŸ‘‹Welcome
    • Overview
      • Architecture
        • Deployment options
      • Security
      • Privacy
      • Protection
        • Provenance and Attribution
      • Personalization
        • Tabnine’s Personalization in Depth
        • Connection: Global Codebase Awareness
      • AI Models
        • Tabnine's private and protected Universal models
        • Tabnine's fine-tuned AI models
      • Integrations
        • Atlassian Jira
      • System Requirements
      • Supported Languages
      • Supported IDEs
      • Tabnine Subscription Plans
        • Dev Preview
        • Dev
        • Enterprise (SaaS)
        • Enterprise (private installation)
    • Support & Feedback
  • πŸš€Getting started
    • Install
      • Client setup (SaaS)
        • VS Code
          • Install Tabnine in VS Code
          • Activate Tabnine in VS Code
        • JetBrains IDEs
          • Install Tabnine in a JetBrains IDE
          • Activate Tabnine in a JetBrains IDE
        • Visual Studio
          • Install Tabnine in Visual Studio 2022
          • Activate Tabnine in Visual Studio 2022
        • Eclipse
          • Install Tabnine in Eclipse
          • Activate Tabnine in Eclipse
        • Sign in
          • Using an email
          • Using an authentication token
      • Client setup (private installation)
        • Join your team (private installation)
        • VS Code (private installation)
        • JetBrains IDEs (private installation)
        • Visual Studio (private installation)
        • Eclipse (private installation)
    • Quickstart Guide
      • Menus and Icons
    • Getting the Most from Tabnine Code Completions
      • Pause (snooze)
    • Getting the Most from Inline Actions
    • Getting the Most from Tabnine Chat
      • Launching Tabnine Chat
      • Interacting with Tabnine Chat
      • Reviewing suggestions
      • Writing prompts
      • Chat Context
        • Understanding Context
        • Jira Connection
        • Context Scoping
      • Conversing with Tabnine Chat
      • Switching between chat AI models
      • Image Prompts
      • Tabnine's Prompting Guide
        • Getting Started
        • Basic Prompting
          • Be specific and clear
          • Define the context
          • Start a fresh conversation as appropriate
          • Include necessary details
          • Ask for examples
          • Be concise but complete
  • πŸ’ͺSoftware Development with Tabnine
    • Overview
    • Plan
    • Create
    • Test
      • Intro to the Test Agent
      • Test Agent Workflow
      • Custom Commands
      • Generate Test Files with @Mentions
    • Review
    • Fix
    • Document
    • Explain
    • Maintain
  • 🏭Administering Tabnine
    • Start a team
    • Manage a team
    • SaaS
      • Enterprise (SaaS) team admin
        • Set up a Tabnine Enterprise (SaaS) account
        • Invite team members
        • Manage your team
        • AI models for Chat (Enterprise SaaS)
      • Enterprise (SaaS) team member
        • Join your Tabnine team by invitation email (team member)
        • Join Tabnine team by link (member)
    • Private installation
      • Server setup guide
        • Kubernetes (MicroK8s) Installation guide
        • Deployment guide
          • Tabnine update guide
        • Air-gapped deployment guide
      • Admin guide
        • Monitoring Tabnine
        • Prometheus Operator install
        • Audit logs
      • Managing your team
        • Tabnine teams
        • Roles in an enterprise
        • Inviting users to your team
        • Deactivating and reactivating users
        • Deleting PII data of a deactivated user
        • Reset user's password
        • Usage reports
          • Reports Glossary
          • CSV-based reports (V2)
            • Configuring scheduled CSV reports
            • CSV-based reports V1 (Depracted since version 5.7.0
          • Usage API
        • Settings
          • General
          • Single Sign-On (SSO)
          • Personalization (f.k.a. Workspace)
            • Connecting to External Code Repositories
          • Email
          • License
          • Models
          • Access Tokens
        • IdP Sync
      • Release Notes
  • πŸ“£Product Updates
    • What's new?
      • What's new? (August 2024)
      • What's new? (July 2024)
      • What's new? (June 2024)
      • What's new? (May 2024)
      • What's new? (April 2024)
      • What's new? (March 2024)
      • What's new? (February 2024)
      • What's new? (January 2024)
Powered by GitBook
On this page
  • Tabnine’s AI Models
  • Optional AI Models for Chat
  • Tabnine gives you the insight you need to choose
  • Tabnine users can choose which Tabnine Chat model to use
  • Fine-tuned code completion models for Enterprise customers

Was this helpful?

  1. Welcome
  2. Overview

AI Models

Tabnine AI code assistant: AI models

Last updated 1 month ago

Was this helpful?

Tabnine's AI coding assistance is backed by Tabnine’s proprietary AI models for code completions and chat, which are trained and hosted by Tabnine and are private and protected.

In addition, Tabnine Chat includes the option of using third-party models. The privacy policies and the protection offered by these third-party models may be different from the Tabnine models.

Tabnine’s AI Models

These are the proprietary models hosted by Tabnine:

  • Tabnine Universal code completions model: Tabnine’s proprietary model is designed to deliver exceptional performance without the risk of intellectual property violations. It's trained and hosted by Tabnine and is available in all tiers.

  • Tabnine Protected chat model: Tabnine’s core model is designed to deliver high performance without the risk of intellectual property violations.

Optional AI Models for Chat

Tabnine Chat users can choose from these chat models (in addition to the Tabnine Protected chat model):

  • Claude 3.7 Sonnet: Claude 3.7 Sonnet raises the industry bar for coding tasks.

    Privacy: Tabnine sends data to either Amazon Bedrock or GCP servers, for computing responses to user prompts. Both Amazon and GCP commit not to retain our customers’ data, or to use it for any kind of training. Protection: The source of the Anthropic model’s training data is not fully disclosed.

  • Claude 3.5 Sonnet: Claude 3.5 Sonnet raises the industry bar for coding tasks.

    Privacy: Tabnine sends data to either Amazon Bedrock or GCP servers, for computing responses to user prompts. Both Amazon and GCP commit not to retain our customers’ data, or to use it for any kind of training. Protection: The source of the Anthropic model’s training data is not fully disclosed.

We support Claude 3.5v1 and v2 via our customers' own endpoints. However, we’ve stopped offering Claude 3.5v2 via the Tabnine endpoint.

  • GPT-o3 Mini: Best class of performance.

    Privacy: Tabnine sends data to OpenAI servers for computing responses to user prompts. OpenAI commits not to retain our customers’ data, or use it for any kind of training. Protection: The source of OpenAI GPT training data is not fully disclosed.

  • GPT-4o: Best class of performance.

    Privacy: Tabnine sends data to OpenAI servers for computing responses to user prompts. OpenAI commits not to retain our customers’ data, or use it for any kind of training. Protection: The source of OpenAI GPT training data is not fully disclosed.

  • Gemini 2.0 Flash: Best class of performance.

    Privacy: Tabnine sends data to GCP servers for computing responses to user prompts.

    GCP commits not to retaining our customers’ data or using it for any kind of training. Protection: The source of the Gemini model’s training data is not fully disclosed.

Tabnine gives you the insight you need to choose

Tabnine users can choose which chat model to use. This decision depends on the specific use case and constraints of each user around these three main aspects:

  • Performance: Does the model provide accurate, relevant results for the programming languages and frameworks I’m working in right now?

  • Privacy: Does the model store my code or user data? Could my code or data be shared with third parties? Is my code used to train their model?

  • Protection: What code was the model trained on? Is it all licensed permissively by the author? Will I create risks for my business by accepting generated code from a model trained on unlicensed repositories?

Performance Levels

The performance levels are Tabnine’s estimation of how each model behaves in real-world software development use cases, as Tabnine has deployed them with context awareness.

Privacy

  • Private: No code data is retained or shared with Tabnine or any other entities.

  • Not private: Code or data may be shared with third parties, as per their public terms of service. Tabnine still adheres to our zero data retention policy.

Protection

Models might recite code they were trained on. The unwary developer might commit code recited from an open source repository with a non-permissive license. This will expose their employer to a legal risk due to the code license infringement.

  • ContactProtected model (training time protection): The model was exclusively trained on code with permissive open-source licenses, or on code that was otherwise licensed by the model provider. Any code used for training is explicitly allowed for use by developers without encumbrances. The model cannot recite restricted code.

  • Attribution and Provenance (inference time protection): For any model (independent of what it was trained on), trace the provenance of all code generated by the model, then report/censor code with an open source provenance trace according to its license. This lets the developer use any model with a layer of protection, shielding the legal risk caused by being blind to non-permissive code recitation.

    Enterprise-only Private Preview: Reach out to your Customer Success Manager if you wish to participate.

  • Not protected: Model training data may include code with licenses that do not explicitly allow their reuse or allow their use for training AI models.

Tabnine users can choose which Tabnine Chat model to use

Tabnine users specify their preferred model the first time they use Chat and can change it anytime. For projects where data privacy and legal risks are less important, you can use a model optimized for performance over compliance. 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's built for that purpose. The underlying LLM can be changed with just a few clicks β€” and Tabnine Chat adapts instantly.\

Fine-tuned code completion models for Enterprise customers

Enterprise customers have the option to deploy private fine-tuned models. Fine-tuned models are private models that result from refining the Universal completion model with the customer codebase and replacing the Universal model.

Tabnine Enterprise customers with private installation can use some of these models and more using private endpoints.

Tabnine Enterprise administrators control and specify the models that are available to their organization. Administrators for their organization. Enterprises often make strategic bets on using specific models across their organization. This update helps Tabnine to be compatible with your chosen LLM and be a part of its ecosystem and makes it easier for you to get the most out of Tabnine without evolving your LLM strategy.

πŸ‘‹
control the available models
Learn more
Learn more
Learn more
⚠ Example image may show models that are no longer available