AI Models
Tabnine AI code assistant: AI models
Last updated
Was this helpful?
Tabnine AI code assistant: AI models
Last updated
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.
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.
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 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?
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.
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.
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 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 — and Tabnine Chat adapts instantly.\
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.
