Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Google / PaLM 2 for Text

PaLM 2 Text Unicorn

Historical PaLM 2 hosted text-generation release, with original version identifiers and dated evidence.

Language models (LLMs)
historicalClosed weightsText generation
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
5 of 18 specification fields collected
Input token limitNot collectedAwaiting source review
Maximum outputNot collectedAwaiting source review
Input billingNot collectedGoogle Vertex AI (historical)
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.

Input token limit
Not collected

Exact historical model-version evidence has not been collected; no current replacement value is inferred.

Maximum output
Not collected

Exact historical model-version evidence has not been collected; no current replacement value is inferred.

Input modalities
TextSource for Input modalities (opens in a new tab)
Output modalities
TextSource for Output modalities (opens in a new tab)
Context caching
Not collected

Exact historical model-version evidence has not been collected; no current replacement value is inferred.

Reasoning
Not collected

Exact historical model-version evidence has not been collected; no current replacement value is inferred.

Tool calling
Not collected

Exact historical model-version evidence has not been collected; no current replacement value is inferred.

Structured output
Not collected

Exact historical model-version evidence has not been collected; no current replacement value is inferred.

Streaming
Not collected

Exact historical model-version evidence has not been collected; no current replacement value is inferred.

Batch processing
Not collected

Exact historical model-version evidence has not been collected; no current replacement value is inferred.

Fine-tuning
Not collected

Exact historical model-version evidence has not been collected; no current replacement value is inferred.

Parameters
Not collected

Exact historical model-version evidence has not been collected; no current replacement value is inferred.

Architecture
Not collected

Exact historical model-version evidence has not been collected; no current replacement value is inferred.

Knowledge cutoff
Not collected

Exact historical model-version evidence has not been collected; no current replacement value is inferred.

Languages
Not collected

Exact historical model-version evidence has not been collected; no current replacement value is inferred.

Release date
2023-11-30Source for Release date (opens in a new tab)
Provider model name
text-unicornSource for Provider model name (opens in a new tab)
Base model
PaLM 2 hosted model familySource for Base model (opens in a new tab)

No exact parameter count or underlying checkpoint equivalence is established.

Access & pricing

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

Google Vertex AI (historical)

Provider source (opens in a new tab)
API model ID
text-unicorn
Access
Historical release documented; current access and an exact shutdown date have not been established. Do not assume it is still callable.
Regions
Exact historical region coverage not established

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

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

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.

Google Vertex AI (historical)

text-unicorn
Not verified

No verified historical caching policy; contemporary Gemini caching does not apply automatically.

How it works
Not collected

No verified historical caching policy; contemporary Gemini caching does not apply automatically.

Minimum reusable input
Not collected

No verified historical caching policy; contemporary Gemini caching does not apply automatically.

Lifetime & refresh
Not collected

No verified historical caching policy; contemporary Gemini caching does not apply automatically.

How to enable it
Not collected

No verified historical caching policy; contemporary Gemini caching does not apply automatically.

Usage fields
Not collected

No verified historical caching policy; contemporary Gemini caching does not apply automatically.

Billing rules
Not collected

No verified historical caching policy; contemporary Gemini caching does not apply automatically.

Limits & data boundaries
Not collected

No verified historical caching policy; contemporary Gemini caching does not apply automatically.

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

Caching reviewed 14 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

Google documents this proprietary hosted model or version through original release notes and SDK identifiers. No public weights are supplied in the reviewed evidence. Exact architecture, model size and equivalence across versions are not inferred from the client SDK license.

Classification evidence (opens in a new tab)

Lifecycle dates

Named release announcement30 Nov 2023Source (opens in a new tab)

Sources reviewed