Vultr Serverless Inference model pricing.

prices as of · 8 models · 8 prices

Serves open-weight models on its own GPUs.

Vultr Serverless Inference is a cloud platform selling 8 models, from $1.90 per million tokens for DeepSeek V4 Flash 0731, read on 16 Sept 2026.

Vultr Serverless Inference website

Kind of provider

Cloud platform

based in US

Where it runs

not stated

no regions published

How you pay

not stated

no payment terms published

Free tier

none published

nothing given away

Where Vultr Serverless Inference's prices land, and why

Vultr Serverless Inference publishes 8 prices we can compare, and 4 of them are below the list price for that model. 4 of those have a published reason behind them, so they rank like any other price. Nobody here has read its terms yet, so treat what it says about itself as its own claim.

Vultr Serverless Inference does not say whether it trains on what you send it. It does not say how long it keeps requests.

not yet checked: terms

Models to start with

all 8 prices ↓

Everything Vultr Serverless Inference sells, against the list price

Cheapest first inside each group. The share is this row against the price the lab that trained the model charges.

Cheaper, and we know why

4 prices

Below list, with a published reason: hosting the open weights, a regional price list, credits, a stated discount.

  • Kimi K2.6

    Moonshot AI · 262k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.30 / $1.20in / out per M

    0.31×of list price

  • Qwen3.5 397B-A17B

    Alibaba Cloud · 262k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.30 / $2in / out per M

    0.54×of list price

  • Qwen3.6 27B

    Alibaba Cloud · 262k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.30 / $2in / out per M

    0.54×of list price

  • GLM-5.2

    Z.ai · 1M context

    Serves the open weights at fp8, a lower precision than the maker's, so not quite the same product.

    $0.85 / $3.10in / out per M

    0.66×of list price

Same price as the maker

4 prices

The same price the maker charges, sold by someone else.

Frequently asked

What is Vultr Serverless Inference?
Serves open-weight models on its own GPUs. It sells 8 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?
4 of its 8 prices sit below the list price for the model, and 4 of those have a published reason behind them, so they can lead a ranking.
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, last read 16 Sept 2026. Prices exclude tax.