Featherless model pricing.
prices as of · 88 models · 89 prices
Serves more than 20,000 open-weight models on flat monthly plans with concurrency limits; its per-model prices are size steps, not a market price.
Featherless is a host selling 88 models, from $0.20 per million tokens for Qwen Turbo, read on 16 Sept 2026.
Kind of provider
Host
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 Featherless's prices land, and why
Featherless publishes 89 prices we can compare, and 38 of them are below the list price for that model. None of them has a published reason we can point at. The other 89 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 terms yet, so treat what it says about itself as its own claim.
Featherless does not say whether it trains on what you send it. It does not say how long it keeps requests.
Flat-rate plan, so the per-model price is not comparable with pay-as-you-go rows.
not yet checked: terms · privacy policy ↗ · status page ↗
Models to start with
all 89 prices ↓Everything Featherless 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 nobody says why
89 prices · never rankedBelow list on a closed model with nothing to account for it. Shown, never ranked, never a pick.
- Qwen Turbo
Alibaba Cloud · 1M context
We could not read this provider's prices reliably, so the row is listed but never ranked.
$0.04 / $0.08in / out per M
0.57×of list price
- Gemma 3 4B
Google · 131k context
We could not read this provider's prices reliably, so the row is listed but never ranked.
$0.05 / $0.10in / out per M
1.00×of list price
- Nemotron 3.5 Content Safety
NVIDIA · 131k context
We could not read this provider's prices reliably, so the row is listed but never ranked.
$0.05 / $0.10in / out per M
0.31×of list price
- gpt-oss-20b
OpenAI · 131k context
We could not read this provider's prices reliably, so the row is listed but never ranked.
$0.04 / $0.15in / out per M
1.23×of list price
- Llama 3.2 1B Instruct
Meta · 60k context
We could not read this provider's prices reliably, so the row is listed but never ranked.
$0.03 / $0.20in / out per M
1.00×of list price
- Gemma 3 12B
Google · 131k context
We could not read this provider's prices reliably, so the row is listed but never ranked.
$0.05 / $0.15in / out per M
1.00×of list price
- Phi 4
Microsoft · 16k context
We could not read this provider's prices reliably, so the row is listed but never ranked.
$0.07 / $0.14in / out per M
1.00×of list price
- Llama 3.2 3B Instruct
Meta · 131k context
We could not read this provider's prices reliably, so the row is listed but never ranked.
$0.05 / $0.34in / out per M
1.02×of list price
- UI-TARS 7B
ByteDance · 128k context
We could not read this provider's prices reliably, so the row is listed but never ranked.
$0.10 / $0.20in / out per M
1.00×of list price
- gpt-oss-safeguard-20b
OpenAI · 131k context
We could not read this provider's prices reliably, so the row is listed but never ranked.
$0.07 / $0.30in / out per M
1.00×of list price
- Gemma 4 26B A4B IT
Google · 262k context
We could not read this provider's prices reliably, so the row is listed but never ranked.
$0.07 / $0.34in / out per M
0.52×of list price
- GLM-4.7-Flash
Z.ai · 200k context
We could not read this provider's prices reliably, so the row is listed but never ranked.
$0.07 / $0.40in / out per M
1.02×of list price
- Qwen3 14B
Alibaba Cloud · 131k context
We could not read this provider's prices reliably, so the row is listed but never ranked.
$0.12 / $0.24in / out per M
0.24×of list price
- Gemma 3 27B
Google · 131k context
We could not read this provider's prices reliably, so the row is listed but never ranked.
$0.10 / $0.30in / out per M
0.87×of list price
- Step 3.5 Flash 2603
StepFun · 256k context
We could not read this provider's prices reliably, so the row is listed but never ranked.
$0.10 / $0.30in / out per M
1.00×of list price
- MiMo-V2-Flash
Xiaomi · 262k context
We could not read this provider's prices reliably, so the row is listed but never ranked.
$0.11 / $0.28in / out per M
0.86×of list price
- Qwen2.5 14B Instruct
Alibaba Cloud · 131k context
We could not read this provider's prices reliably, so the row is listed but never ranked.
$0.11 / $0.28in / out per M
0.25×of list price
- DeepSeek V4 Flash 0731
DeepSeek · 1M context
We could not read this provider's prices reliably, so the row is listed but never ranked.
$0.14 / $0.28in / out per M
0.67×of list price
- Gemma 4 31B IT
Google · 262k context
We could not read this provider's prices reliably, so the row is listed but never ranked.
$0.12 / $0.36in / out per M
1.18×of list price
- Qwen3 VL 32B Instruct
Alibaba Cloud · 131k context
We could not read this provider's prices reliably, so the row is listed but never ranked.
$0.10 / $0.42in / out per M
0.65×of list price
- Qwen3.5-9B
Alibaba Cloud · 262k context
We could not read this provider's prices reliably, so the row is listed but never ranked.
$0.17 / $0.25in / out per M
1.69×of list price
- Qwen3 32B
Alibaba Cloud · 131k context
We could not read this provider's prices reliably, so the row is listed but never ranked.
$0.10 / $0.49in / out per M
0.16×of list price
- Qwen3 8B
Alibaba Cloud · 131k context
We could not read this provider's prices reliably, so the row is listed but never ranked.
$0.12 / $0.46in / out per M
0.65×of list price
- Mistral Small 3
Mistral AI · 33k context
We could not read this provider's prices reliably, so the row is listed but never ranked.
$0.17 / $0.29in / out per M
3.54×of list price
- Qwen3 30B A3B Instruct 2507
Alibaba Cloud · 262k context
We could not read this provider's prices reliably, so the row is listed but never ranked.
$0.13 / $0.45in / out per M
0.91×of list price
- Qwen3-Coder 30B-A3B Instruct
Alibaba Cloud · 262k context
We could not read this provider's prices reliably, so the row is listed but never ranked.
$0.13 / $0.45in / out per M
0.23×of list price
- Llama 3.1 8B Instruct
Meta · 131k context
We could not read this provider's prices reliably, so the row is listed but never ranked.
$0.20 / $0.32in / out per M
4.00×of list price
- MiMo-V2.5
Xiaomi · 1M context
We could not read this provider's prices reliably, so the row is listed but never ranked.
$0.15 / $0.49in / out per M
1.34×of list price
- GLM-5.3-Flash
Z.ai · 1M context
We could not read this provider's prices reliably, so the row is listed but never ranked.
$0.15 / $0.50in / out per M
2.00×of list price
- Qwen3-VL 30B-A3B
Alibaba Cloud · 131k context
We could not read this provider's prices reliably, so the row is listed but never ranked.
$0.15 / $0.50in / out per M
0.68×of list price
showing the 30 cheapest of 89 · every row in the open dataset
Frequently asked
- What is Featherless?
- Serves more than 20,000 open-weight models on flat monthly plans with concurrency limits; its per-model prices are size steps, not a market price. It sells 88 of the models we track, and trades as Featherless AI, based in US.
- Is Featherless cheaper than buying from the maker?
- 38 of its 89 prices sit below the list price for the model. None of them has a published reason we can point at, so none of them leads a ranking. 89 are listed and never ranked.
- Does Featherless train on what you send it?
- Featherless does not say whether it trains on what you send it. It does not say how long it keeps requests.
- How current are these Featherless prices?
- They come from its own public catalog, last read 16 Sept 2026. Prices exclude tax.