Vultr Serverless Inference model pricing.

Prices checked

Vultr Serverless Inference sells 14 prices on 14 models, from $0.08 per million tokens, checked .

Every model Vultr Serverless Inference sells

  1. 1

    Nemotron 3.5 Content Safety

    Runs it themselves

    $0.05 in · $0.15 out

    $0.08/M tokens
    View
  2. 2

    Laguna S 2.1

    Same as maker

    $0.09 in · $0.18 out

    $0.11/M tokens
    View
  3. 3

    DeepSeek V4 Flash 0731

    Runs it themselves

    $0.10 in · $0.25 out

    $0.14/M tokens
    View
  4. 4

    MiMo-V2.6-Flash

    Runs it themselves

    $0.10 in · $0.25 out

    $0.14/M tokens
    View
  5. 5

    $0.10 in · $0.25 out

    $0.14/M tokens
    View
  6. 6

    GLM-5.3-Flash

    Runs it themselves

    $0.10 in · $0.35 out

    $0.16/M tokens
    View
  7. 7

    $0.15 in · $0.60 out

    $0.26/M tokens
    View
  8. 8

    Qwen3.8 27B

    Runs it themselves

    $0.15 in · $1 out

    $0.36/M tokens
    View
  9. 9

    MiniMax-M3

    Runs it themselves

    $0.20 in · $0.90 out

    $0.38/M tokens
    View
  10. 10

    Muse Glimmer 30B

    Runs it themselves

    $0.25 in · $1 out

    $0.44/M tokens
    View
  11. 11

    $0.40 in · $0.80 out

    $0.50/M tokens
    View
  12. 12

    GLM-5.2

    Runs it themselves

    $0.75 in · $3 out

    $1.31/M tokens
    View
  13. 13

    GLM-5.3

    Runs it themselves

    $0.75 in · $3 out

    $1.31/M tokens
    View

Not ranked

Below the maker's own price with nothing published to account for it, or from a catalog we could not read reliably. Why

  1. Qwen3.8 Flash

    Not ranked

    $0.10 in · $0.20 out

    $0.13/M tokens
    View

Where to start

Kind

Cloud platform

based in US

Free tier

No

every price is paid

Frequently asked

What is Vultr Serverless Inference?
Serves open-weight models on its own GPUs. It sells 14 of the models we track, and trades as The Constant Company, LLC, based in US.
Is Vultr Serverless Inference cheaper than buying from the maker?
11 of its 14 prices are below the maker's own price, and 10 of those come with a published reason, so they can lead a ranking. 1 are listed and not ranked, because nothing accounts for the gap.
Does Vultr Serverless Inference train on what you send it?
Vultr Serverless Inference does not say whether it trains on what you send it. It does not say how long it keeps requests.
How current are these Vultr Serverless Inference prices?
They come from the public catalogs we read, read every 3 days; the reading on this page is from 31 Oct 2026. Prices exclude tax.

Models it sells

Other cloud platforms

Where to go next