OLLAMA CLOUD, UNLEASHED

Change radar

Dated changes we have seen in Ollama Cloud’s plans, models and usage API. Each entry names its source.

Verified 12 Oct 2026

Sources: ollama.com/pricing, ollama.com/api/usage (live probe), ollama.com/api/tags (live probe)

Follow it

The same entries feed an RSS file, built from this list each time the site is built. Use it in any feed reader.

RSS feedradar/feed.xml

The entries

Newest first. “About” means we could not pin the exact day.

  1. Plans

    Dollar-credit plans with off-peak pricing, observed on the pricing page

    Observed by us on the pricing page on 12 Oct 2026. Plans include dollar usage credits. Models with an off-peak row are cheaper outside 12:00 to 18:00 UTC on weekdays, and all day at weekends.

    Source: ollama.com/pricing

  2. Usage API

    The usage API stopped returning quota percentages

    The session and weekly fractions are gone from the usage API. Old-plan windows are now estimates built from request counts, labelled EST. New-plan accounts still get exact dollars per bucket.

    Source: ollama.com/api/usage

  3. Models

    mistral-large-4 appears in the cloud model list

    The model record was modified on 6 Oct 2026. It is in the live list with a 1,048,576-token context window, but it has no price row on the pricing page yet.

    Source: ollama.com/api/tags

  4. Models

    deepseek-v4.1-flash: model record dated 10 Sep 2026

    The pricing page lists standard and off-peak prices for it: 0.30 fresh input, 0.006 cached and 1.20 output per million tokens standard. See Our tests for its per-call results.

    Source: ollama.com/pricing

  5. Models

    glm-5.3: model record dated 28 Aug 2026

    Priced at 1.40 fresh input, 0.26 cached input and 4.40 output per million tokens, on the pricing page.

    Source: ollama.com/pricing

  6. Models

    glm-5.3-flash: model record dated 26 Aug 2026

    Priced at 0.15 fresh input, 0.03 cached input and 0.50 output per million tokens. Our first per-call test ran the next day, on 27 Aug 2026.

    Source: ollama.com/pricing

How we date entries

  • A plan or price entry is dated the day we checked the pricing page.
  • A model entry carries the date on the model record in the live list.
  • An API change is dated from when we first saw it. Where that is only approximate, the entry says About.

For what the figures mean in practice, read Plans and quota and Cheaper models.

Check the real numbers

Paste an Ollama Cloud key on the home page. Exact monthly dollars on new plans, estimates on old ones, and nothing is stored.

Check your own usage