Hugging Face Inference Providers model pricing.
prices as of · 65 models · 64 prices
Routes to partner hosts at their price; each model's page lists the hosts with latency and throughput.
Hugging Face Inference Providers is a router selling 65 models, from $0.24 per million tokens for Llama 3.1 8B Instruct, read on 16 Sept 2026.
Kind of provider
Router
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 Hugging Face Inference Providers's prices land, and why
Hugging Face Inference Providers publishes 64 prices we can compare, and 19 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.
Hugging Face Inference Providers 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 64 prices ↓- DeepSeek V4 Flash 0731DeepSeek · 1M context · 97 providers sell it$0.14 / $0.2833% under listbuy at Hugging Face Inference Providers ↗
- GLM-5.2Z.ai · 1M context · 94 providers sell it$1.40 / $4.40same as listbuy at Hugging Face Inference Providers ↗
- DeepSeek V4 ProDeepSeek · 1M context · 84 providers sell it$1.32 / $3.96264% above listbuy at Hugging Face Inference Providers ↗
- Kimi K2.6Moonshot AI · 262k context · 82 providers sell it$0.95 / $4same as listbuy at Hugging Face Inference Providers ↗
- Kimi K3Moonshot AI · 1M context · 81 providers sell it$3 / $15same as listbuy at Hugging Face Inference Providers ↗
Everything Hugging Face Inference Providers 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.
- Qwen3-Coder 30B-A3B Instruct
Alibaba Cloud · 262k context
Routes to a host serving the open weights; precision not disclosed.
$0.07 / $0.26in / out per M
0.13×of list price
- MiMo-V2-Flash
Xiaomi · 262k context
Routes to a host serving the open weights; precision not disclosed.
$0.10 / $0.30in / out per M
0.86×of list price
$0.14 / $0.28in / out per M
0.67×of list price
- Gemma 4 26B A4B IT
Google · 262k context
Routes to a host serving the open weights; precision not disclosed.
$0.13 / $0.40in / out per M
0.75×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
$0.13 / $0.85in / out per M
0.73×of list price
- Qwen3.6 35B-A3B
Alibaba Cloud · 262k context
Routes to a host serving the open weights; precision not disclosed.
$0.15 / $0.95in / out per M
0.63×of list price
- Qwen3 235B-A22B
Alibaba Cloud · 131k context
Routes to a host serving the open weights; precision not disclosed.
$0.20 / $0.80in / out per M
0.29×of list price
- Qwen3 32B
Alibaba Cloud · 131k context
Routes to a host serving the open weights; precision not disclosed.
$0.29 / $0.59in / out per M
0.30×of list price
- Qwen3-Next 80B-A3B Instruct
Alibaba Cloud · 131k context
Routes to a host serving the open weights; precision not disclosed.
$0.25 / $1in / out per M
0.50×of list price
- Qwen3 Coder Next
Alibaba Cloud · 262k context
Routes to a host serving the open weights; precision not disclosed.
$0.20 / $1.50in / out per M
0.88×of list price
- Qwen3-VL 235B-A22B
Alibaba Cloud · 131k context
Routes to a host serving the open weights; precision not disclosed.
$0.30 / $1.50in / out per M
0.49×of list price
- Qwen3-Next 80B-A3B (Thinking)
Alibaba Cloud · 131k context
Routes to a host serving the open weights; precision not disclosed.
$0.30 / $2in / out per M
0.39×of list price
$0.55 / $2.20in / out per M
0.96×of list price
$0.40 / $3in / out per M
1.10×of list price
- Qwen3.6 27B
Alibaba Cloud · 262k context
Routes to a host serving the open weights; precision not disclosed.
$0.47 / $3.19in / out per M
0.85×of list price
$1 / $3.20in / out per M
0.72×of list price
- Inkling
Thinking Machines · 1M context
Routes to a host serving the open weights; precision not disclosed.
$1 / $4.05in / out per M
0.69×of list price
Same price as the maker
46 pricesThe same price the maker charges, sold by someone else.
$0.06 / $0.06in / out per M
1.04×of list price
$0.05 / $0.10in / out per M
1.00×of list price
$0.05 / $0.15in / out per M
1.00×of list price
$0.08 / $0.16in / out per M
0.58×of list price
$0.10 / $0.30in / out per M
1.00×of list price
$0.17 / $0.25in / out per M
1.69×of list price
$0.10 / $0.50in / out per M
3.64×of list price
$0.14 / $0.40in / out per M
1.34×of list price
$0.15 / $0.50in / out per M
2.00×of list price
$0.14 / $0.58in / out per M
1.08×of list price
$0.28 / $0.40in / out per M
1.00×of list price
$0.25 / $0.69in / out per M
5.12×of list price
$0.20 / $1.15in / out per M
1.05×of list price
$0.30 / $1.20in / out per M
2.00×of list price
$0.30 / $1.20in / out per M
1.00×of list price
$0.30 / $1.20in / out per M
1.00×of list price
$0.30 / $1.20in / out per M
1.00×of list price
$0.30 / $1.20in / out per M
1.00×of list price
$0.30 / $1.20in / out per M
1.00×of list price
$0.59 / $0.79in / out per M
4.13×of list price
$0.44 / $1.32in / out per M
2.51×of list price
$0.50 / $1.20in / out per M
1.06×of list price
$0.25 / $2in / out per M
1.00×of list price
$0.40 / $2in / out per M
4.57×of list price
$0.30 / $2.40in / out per M
1.00×of list price
$0.60 / $1.80in / out per M
1.00×of list price
$0.30 / $3in / out per M
1.30×of list price
$0.60 / $2.20in / out per M
1.00×of list price
$0.60 / $2.20in / out per M
1.00×of list price
$0.60 / $2.50in / out per M
1.00×of list price
showing the 30 cheapest of 46 · every row in the open dataset
Frequently asked
- What is Hugging Face Inference Providers?
- Routes to partner hosts at their price; each model's page lists the hosts with latency and throughput. It sells 65 of the models we track, and trades as Hugging Face, Inc., based in US.
- Is Hugging Face Inference Providers cheaper than buying from the maker?
- 19 of its 64 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 Hugging Face Inference Providers train on what you send it?
- Hugging Face Inference Providers does not say whether it trains on what you send it. It does not say how long it keeps requests.
- How current are these Hugging Face Inference Providers prices?
- They come from the public catalogs we read, last read 16 Sept 2026. Prices exclude tax.