Inference.net model pricing.

prices as of · 53 models · 55 prices

Serves open-weight models on a distributed GPU network.

Inference.net is a open network selling 53 models, from $0.25 per million tokens for Gemma 3 4B, read on 16 Sept 2026.

Inference.net prices

Kind of provider

Open network

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 Inference.net's prices land, and why

Inference.net publishes 55 prices we can compare, and 9 of them are below the list price for that model. 6 of those have a published reason behind them, so they rank like any other price. The other 2 sit below list on models whose weights are closed, with nothing published to account for the gap, so they are listed here in full and ranked nowhere on the site. Nobody here has read its entity, terms yet, so treat what it says about itself as its own claim.

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

not yet checked: entity, terms · privacy policy ↗ · status page ↗

Models to start with

all 55 prices ↓

Everything Inference.net 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

6 prices

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

  • Qwen3 8B

    Alibaba Cloud · 131k context

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

    $0.12 / $0.46in / out per M

    0.65×of list price

  • Qwen3 30B A3B Instruct 2507

    Alibaba Cloud · 262k context

    8% under the list price, an ordinary reseller margin.

    $0.12 / $0.50in / out per M

    0.95×of list price

  • Qwen3 14B

    Alibaba Cloud · 131k context

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

    $0.23 / $0.91in / out per M

    0.65×of list price

  • GLM-5

    Z.ai · 205k context

    5% under the list price, an ordinary reseller margin.

    $0.95 / $2.55in / out per M

    0.87×of list price

  • GLM-5.2

    Z.ai · 1M context

    7% under the list price, an ordinary reseller margin.

    $1.30 / $4.40in / out per M

    0.97×of list price

  • Kimi K3

    Moonshot AI · 1M context

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

    $2.10 / $10.95in / out per M

    0.72×of list price

Same price as the maker

47 prices

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

showing the 30 cheapest of 47 · every row in the open dataset

Cheaper, and nobody says why

2 prices · never ranked

Below list on a closed model with nothing to account for it. Shown, never ranked, never a pick.

  • Qwen3.7 Plus

    Alibaba Cloud · 1M context

    0.80× Alibaba Cloud's list price on a closed model, and nobody says why. Listed, never ranked.

    $0.40 / $1.60in / out per M

    0.62×of list price

  • GPT-4o

    OpenAI · 128k context

    0.50× OpenAI's list price on a closed model, and nobody says why. Listed, never ranked.

    $2.50 / $10in / out per M

    0.58×of list price

Frequently asked

What is Inference.net?
Serves open-weight models on a distributed GPU network. It sells 53 of the models we track, and trades as Inference.net, based in US.
Is Inference.net cheaper than buying from the maker?
9 of its 55 prices sit below the list price for the model, and 6 of those have a published reason behind them, so they can lead a ranking. 2 are listed and never ranked.
Does Inference.net train on what you send it?
Inference.net does not say whether it trains on what you send it. It does not say how long it keeps requests.
How current are these Inference.net prices?
They come from its own public catalog, last read 16 Sept 2026. Prices exclude tax.