Real explicit cache limit

Gemini API
,
1

Documentation states that

Minimum cache token count for implicit and explicit caching

  • Gemini 3 and Gemini 3.1 models: 4,096 tokens

  • Gemini 2.0 and 2.5 models: 2,048 tokens

https://docs.cloud.google.com/vertex-ai/generative-ai/docs/context-cache/context-cache-overview#limits

But in reality i was able to create for 3.1 model with 1024 tokens:

cache = await client.aio.caches.create(
    model="gemini-3.1-pro-preview",
    config=types.CreateCachedContentConfig(
        contents=[
            types.Content(
                role="user",
                parts=[types.Part(text=text)],
            )
        ],
        display_name="vertex-cached-prompt",
        ttl="120s",
    ),
)

Error i got while on attempt to create cache for 100 tokens:

google.genai.errors.ClientError: 400 INVALID_ARGUMENT. {‘error’: {‘code’: 400, ‘message’: ‘The cached content is of 151 tokens. The minimum token count to start caching is 1024.’, ‘status’: ‘INVALID_ARGUMENT’}}

Can you clarify this please?