io.net Intelligence model pricing.
prices as of · 36 models · 41 prices
Serves open-weight models on a decentralised GPU network.
io.net Intelligence is a open network selling 36 models, from $0.29 per million tokens for Mistral Nemo, read on 16 Sept 2026.
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 io.net Intelligence's prices land, and why
io.net Intelligence publishes 41 prices we can compare, and 21 of them are below the list price for that model. 18 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.
io.net Intelligence does not say whether it trains on what you send it. It does not say how long it keeps requests.
not yet checked: terms · privacy policy ↗ · status page ↗
Models to start with
all 41 prices ↓- DeepSeek V4 Flash 0731DeepSeek · 1M context · 97 providers sell it$0.21 / $0.5917% above listbuy at io.net Intelligence ↗
- GLM-5.2Z.ai · 1M context · 94 providers sell it$1.58 / $4.9713% above listbuy at io.net Intelligence ↗
- DeepSeek V4 ProDeepSeek · 1M context · 84 providers sell it$1.70 / $3.40291% above listbuy at io.net Intelligence ↗
- Kimi K2.6Moonshot AI · 262k context · 82 providers sell it$0.85 / $3.788% under listbuy at io.net Intelligence ↗
- Kimi K3Moonshot AI · 1M context · 81 providers sell it$3.15 / $15.765% above listbuy at io.net Intelligence ↗
Everything io.net Intelligence 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
18 pricesBelow list, with a published reason: hosting the open weights, a regional price list, credits, a stated discount.
- Mistral Nemo
Mistral AI · 128k context
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.06 / $0.10in / out per M
0.48×of list price
- Mistral Nemo
Mistral AI · 128k context
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision fp16.
$0.04 / $0.16in / out per M
0.49×of list price
- Devstral Small
Mistral AI · 128k context
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.05 / $0.22in / out per M
0.62×of list price
- Gemma 4 26B A4B IT
Google · 262k context
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.10 / $0.33in / out per M
0.60×of list price
- Qwen3 235B A22B Thinking 2507
Alibaba Cloud · 131k context
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.11 / $0.60in / out per M
0.31×of list price
- GLM-4.5-Air
Z.ai · 131k context
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.16 / $0.94in / out per M
0.83×of list price
- Qwen3-Next 80B-A3B Instruct
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 / $1.14in / out per M
0.43×of list price
- Qwen3.6 35B-A3B
Alibaba Cloud · 262k context
Serves the open weights at fp8, a lower precision than the maker's, so not quite the same product.
$0.19 / $0.99in / out per M
0.70×of list price
- Qwen3.6 35B-A3B
Alibaba Cloud · 262k context
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.18 / $1.25in / out per M
0.80×of list price
- GLM-4.6
Z.ai · 205k context
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.52 / $2.04in / out per M
0.90×of list price
- Qwen3.8 27B
Alibaba Cloud · 1M context
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.31 / $2.73in / out per M
0.96×of list price
- Qwen3.8 27B
Alibaba Cloud · 1M context
Serves the open weights at fp8, a lower precision than the maker's, so not quite the same product.
$0.30 / $2.80in / out per M
0.97×of list price
$0.57 / $2.30in / out per M
0.93×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.
$0.34 / $3.01in / out per M
0.75×of list price
$0.56 / $2.94in / out per M
0.96×of list price
$0.93 / $2.88in / out per M
0.91×of list price
- GLM-5.3
Z.ai · 1M context
Serves the open weights at fp8, a lower precision than the maker's, so not quite the same product.
$0.91 / $3.08in / out per M
0.68×of list price
- 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.
$0.85 / $3.78in / out per M
0.92×of list price
Same price as the maker
23 pricesThe same price the maker charges, sold by someone else.
$0.06 / $0.20in / out per M
1.67×of list price
$0.06 / $0.40in / out per M
1.02×of list price
$0.15 / $0.50in / out per M
2.00×of list price
$0.18 / $0.68in / out per M
4.32×of list price
$0.21 / $0.59in / out per M
1.17×of list price
$0.20 / $0.64in / out per M
1.78×of list price
$0.21 / $0.69in / out per M
2.77×of list price
$0.29 / $1.18in / out per M
0.98×of list price
$0.30 / $1.19in / out per M
1.98×of list price
$0.61 / $1.04in / out per M
4.61×of list price
$0.50 / $1.50in / out per M
1.00×of list price
$0.48 / $1.85in / out per M
1.57×of list price
$0.57 / $2.28in / out per M
1.04×of list price
$0.60 / $2.50in / out per M
1.00×of list price
$0.88 / $2.37in / out per M
1.25×of list price
$1.43 / $2.41in / out per M
5.40×of list price
$1.07 / $4.65in / out per M
1.15×of list price
$1.36 / $4.27in / out per M
0.97×of list price
$1.36 / $4.31in / out per M
0.98×of list price
$1.70 / $3.40in / out per M
3.91×of list price
$1.58 / $4.97in / out per M
1.13×of list price
$2 / $6in / out per M
4.00×of list price
$3.15 / $15.76in / out per M
1.05×of list price
Frequently asked
- What is io.net Intelligence?
- Serves open-weight models on a decentralised GPU network. It sells 36 of the models we track, and trades as io.net, based in US.
- Is io.net Intelligence cheaper than buying from the maker?
- 21 of its 41 prices sit below the list price for the model, and 18 of those have a published reason behind them, so they can lead a ranking.
- Does io.net Intelligence train on what you send it?
- io.net Intelligence does not say whether it trains on what you send it. It does not say how long it keeps requests.
- How current are these io.net Intelligence prices?
- They come from its own public catalog, last read 16 Sept 2026. Prices exclude tax.