Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Tabnine / Deep TabNine

Deep TabNine

Historical GPT-2-based code completion model documented in Tabnine’s official repository.

Language models (LLMs)
historicalClosed weightsCoding
Official documentation (opens in a new tab)Reviewed 15 Oct 2026
4 of 17 specification fields collected
Context windowNot collectedAwaiting source review
Maximum outputNot collectedAwaiting source review
Input billingNot collectedTabnine · historical Deep Cloud
Output billingNot collectedNo inferred price

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected

No exact model-specific value or customer API contract established in the reviewed sources.

Maximum input tokens
Not collected

No exact model-specific value or customer API contract established in the reviewed sources.

Maximum output
Not collected

No exact model-specific value or customer API contract established in the reviewed sources.

Parameters
Not collected

No exact model-specific value or customer API contract established in the reviewed sources.

Release date
Not collected

No exact model-specific value or customer API contract established in the reviewed sources.

Knowledge cutoff
Not collected

No exact model-specific value or customer API contract established in the reviewed sources.

Reasoning
Not collected

No exact model-specific value or customer API contract established in the reviewed sources.

Tool calling
Not collected

No exact model-specific value or customer API contract established in the reviewed sources.

Structured output
Not collected

No exact model-specific value or customer API contract established in the reviewed sources.

Streaming
Not collected

No exact model-specific value or customer API contract established in the reviewed sources.

Batch processing
Not collected

No exact model-specific value or customer API contract established in the reviewed sources.

Fine-tuning
Not collected

No exact model-specific value or customer API contract established in the reviewed sources.

Context caching
Not collected

No exact model-specific value or customer API contract established in the reviewed sources.

Input modalities
TextSource for Input modalities (opens in a new tab)
Output modalities
TextSource for Output modalities (opens in a new tab)
Base model
GPT-2-based transformer; exact inherited checkpoint and parameter count unverified.Source for Base model (opens in a new tab)
Published training data
Approximately two million GitHub files.Source for Published training data (opens in a new tab)

Historical corpus statement. Do not apply current Protected licensing/corpus claims retroactively.

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Tabnine · historical Deep Cloud

Provider source (opens in a new tab)
API model ID
Not collected

No public model-version selector established.

Access
Historical opt-in GPU-accelerated cloud completion service. No current access or numeric tariff established.
Regions
No historical serving regions established.

Endpoint pricing has not been collected. Check the provider for applicable rates.

Data & enterprise terms

Historical Deep Cloud documentation says sent code fragments are used only to answer the request and not retained. This is not a verified current contract.

Read the service policy (opens in a new tab)

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

Tabnine · historical Deep Cloud

Not verified

No model-specific prompt-cache contract or billed cache tariff established.

How it works
Not collected

No model-specific prompt-cache contract or billed cache tariff established.

Minimum reusable input
Not collected

No model-specific prompt-cache contract or billed cache tariff established.

Lifetime & refresh
Not collected

No model-specific prompt-cache contract or billed cache tariff established.

How to enable it
Not collected

No model-specific prompt-cache contract or billed cache tariff established.

Usage fields
Not collected

No model-specific prompt-cache contract or billed cache tariff established.

Billing rules
Not collected

No model-specific prompt-cache contract or billed cache tariff established.

Limits & data boundaries
Not collected

No model-specific prompt-cache contract or billed cache tariff established.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Caching reviewed 15 Oct 2026

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Official repository distinguishes MIT-licensed integration source from EULA-covered TabNine binaries. Private model classification is inferred from the proprietary packaged/cloud distribution; public client source does not establish public weights.

Classification evidence (opens in a new tab)

Sources reviewed