Nostimates

DeepSeek share of voice tracking

deepseekshare_of_voiceAccount required

DeepSeek share of voice is computed over the samples where the engine actually answered, with account-blocked runs excluded rather than silently counted as an absent brand.

How it renders

Derived across successful samples, with a collection success rate reported alongside.

Sampling

This is the field where n matters most. At n=1 the metric is noise; at n=30 the interval is typically tight enough to defend in a client report.

Gotcha

Failed collections are not zeroes. An engine that refused to answer is a different thing from an engine that answered without your brand, and conflating them is the most common error in Chinese-surface reporting.

What the API returns

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

{
  "engine": "deepseek",
  "field": "share_of_voice",
  "prompt": "best ai visibility tracking tool",
  "country": "GB",
  "language": "en",
  "n": 30,
  "share_of_voice": [
    {
      "brand": "Nostimates",
      "share": 0.34,
      "ci95": {
        "low": 0.2,
        "high": 0.52
      },
      "n": 30
    },
    {
      "brand": "Competitor",
      "share": 0.21,
      "ci95": {
        "low": 0.1,
        "high": 0.38
      },
      "n": 30
    }
  ]
}
GET /v1/collect?engine=deepseek&field=share_of_voice

Response fields

KeyTypeNotes
brandstringBrand from the configured competitor set.
sharefloatPoint estimate across the sample set.
ci95object95% Wilson interval as { low, high }.
nintegerSamples behind the estimate.
delta_priorfloat | nullChange against the previous run of the same prompt set.

What it costs

Derived at no extra credit cost, but it scales with n — the interval is bought with samples.

See credit pricing →

DeepSeek share of voice FAQ

How do you handle blocked runs?
They are excluded from the share denominator and reported as a separate success rate.
What sample size does DeepSeek need?
n=30 is usually enough, but the effective n is lower after exclusions, so we oversample.

Report Chinese share of voice defensibly

We will show you the success rate alongside the share so the number survives scrutiny.

No newsletter. One reply from a human.

Across every engine

Compare how share of voice behaves on every engine we track.

Share of voice across all engines →