Should I run Chinese or English prompts?

Chinese, if the question is about the Chinese market. We will run both if you want the contrast documented.

Does egress country matter?

Less than language, but we control it anyway for consistency.

DeepSeek locale variance tracking

deepseeklocale_varianceAccount required

DeepSeek locale work is mostly a language question rather than a country one: the same prompt in Chinese and English returns materially different source sets and often different conclusions.

How it renders

Controlled by prompt language and egress, with language the stronger variable.

Sampling

Each locale is its own sample set. A cross-market comparison at n=30 per market costs what it says on the tin, which is why we surface the arithmetic before you commit.

Gotcha

Running your China prompts in English tells you almost nothing about how the market sees your brand. The English-language answer leans on Western sources DeepSeek's Chinese answer never touches.

What the API returns

A single collection call against DeepSeek for the locale variance field, sampled n times and returned as one object per prompt.

{
  "engine": "deepseek",
  "field": "locale_variance",
  "prompt": "best ai visibility tracking tool",
  "country": "GB",
  "language": "en",
  "n": 30,
  "locales": [
    {
      "country": "GB",
      "language": "en",
      "share": 0.34,
      "divergence": 0.02,
      "unique_domains": 4
    },
    {
      "country": "DE",
      "language": "de",
      "share": 0.19,
      "divergence": 0.15,
      "unique_domains": 11
    }
  ]
}

GET /v1/collect?engine=deepseek&field=locale_variance

Response fields

Key	Type	Notes
country	string	ISO 3166-1 alpha-2 country of the egress used.
language	string	ISO 639-1 language the prompt was issued in.
share	float	Brand share within that locale.
divergence	float	Distance from the global mean for this prompt.
unique_domains	integer	Domains cited in this locale and nowhere else.

What it costs

Each locale multiplies the collection count. Two markets at n=30 is 60 credits per prompt.

See credit pricing →

DeepSeek locale variance FAQ

Should I run Chinese or English prompts?: Chinese, if the question is about the Chinese market. We will run both if you want the contrast documented.
Does egress country matter?: Less than language, but we control it anyway for consistency.

Run your China prompts in the language of the market

We will build the Chinese prompt set with you and show the English contrast where it is useful.

Other DeepSeek data

Citations Brand mentions Sources Answer text Share of voice Sentiment Prompt volatility Position

Across every engine

Compare how locale variance behaves on every engine we track.

Locale variance across all engines →