Qwen3.5 397B-A17B pricing.
prices as of · 44 providers · 49 prices
Alibaba Cloud's Qwen3.5 397B-A17B holds 262k tokens of context, reads images as well as text and has a reasoning mode. Open weights, so anyone may host it, which is why the prices below differ so much.
Qwen3.5 397B-A17B costs $0.60 in and $3.60 out per million tokens from Alibaba Cloud; the cheapest price we can explain is $1.55 at OrcaRouter, checked 16 Sept 2026.
Alibaba Cloud list price
$5.40/M tokens
$0.60 in · $3.60 out
read · 52% above the market median
Cheapest price we can explain
$1.55/M tokens
$0.17 in · $1.03 out · 71% under list
OrcaRouterread
What it costs for your work
Alibaba Cloud list price
$0.576a month
cheapest we can explain · OrcaRouter
$0.165a month
difference
$0.411saved
A page is about 600 tokens in and 60 out, a support reply 200 in and 300 out, an email 150 in and 250 out. Nothing else is counted: no cache discount, no batch rate, no free tier.
Every provider selling Qwen3.5 397B-A17B
Four groups, decided by the price and by what the provider publishes about it. Prices are per million tokens, and the share is that row against Alibaba Cloud's price.
The maker's list price
1 priceWhat the lab that trained the model charges on its own API.
Alibaba CloudThe price Alibaba Cloud charges for the model it trained. Every row below is measured against it.
$0.60 / $3.60in / out per M
1.00×of list price
Cheaper, and we know why
25 pricesBelow list, with a published reason: hosting the open weights, a regional price list, credits, a stated discount.
- OrcaRouter
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.17 / $1.03in / out per M
0.29×of list price
Alibaba Cloud (China)Alibaba's China-region Model Studio, which prices the Qwen models below the international list. A region, not a deal.
$0.17 / $1.03in / out per M
0.29×of list price
Empirio LabsRoutes to a host serving the open weights; precision not disclosed.
256k context hereEmpirio Labs ↗$0.17 / $1.03in / out per M
0.29×of list price
Merge GatewayHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
131k context here$0.17 / $1.03in / out per M
0.29×of list price
SiliconFlow (China)SiliconFlow's China-region catalog, priced in the domestic market.
$0.29 / $1.74in / out per M
0.48×of list price
CrofHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.35 / $1.75in / out per M
0.52×of list price
Vultr Serverless InferenceHosts 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
$0.39 / $2.34in / out per M
0.65×of list price
SiliconFlowHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.39 / $2.34in / out per M
0.65×of list price
Nous PortalResells OpenRouter's catalog at 0.80× the listed price, funded by a subscription whose credits carry a 10% bonus.
$0.39 / $2.34in / out per M
0.65×of list price
TokenGoHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.40 / $2.65in / out per M
0.71×of list price
ChutesHosts the open weights on its own servers, so the price is its own, not a resale. Precision tee.
$0.45 / $3in / out per M
0.81×of list price
DeepInfraHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.45 / $3in / out per M
0.81×of list price
- DeepInfra
Serves the open weights at fp8, a lower precision than the maker's, so not quite the same product.
fp8 precisionDeepInfra ↗$0.45 / $3in / out per M
0.81×of list price
- Chutes
Serves the open weights at fp8, a lower precision than the maker's, so not quite the same product.
fp8 precisionChutes ↗$0.45 / $3in / out per M
0.81×of list price
$0.47 / $3.17in / out per M
0.85×of list price
NEAR AI CloudHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
128k context hereNEAR AI Cloud ↗$0.50 / $3.30in / out per M
0.89×of list price
$0.49 / $3.60in / out per M
0.94×of list price
ParasailServes the open weights at fp8, a lower precision than the maker's, so not quite the same product.
fp8 precisionParasail ↗$0.50 / $3.60in / out per M
0.94×of list price
$0.55 / $3.50in / out per M
0.95×of list price
DigitalOcean Gradient8% under the list price, an ordinary reseller margin.
131k context hereDigitalOcean Gradient ↗$0.55 / $3.50in / out per M
0.95×of list price
$0.55 / $3.50in / out per M
0.95×of list price
$0.55 / $3.50in / out per M
0.95×of list price
$0.55 / $3.50in / out per M
0.95×of list price
$0.55 / $3.50in / out per M
0.95×of list price
Same price as the maker
21 pricesThe same price the maker charges, sold by someone else.
$0.60 / $3.60in / out per M
1.00×of list price
$0.60 / $3.60in / out per M
1.00×of list price
$0.60 / $3.60in / out per M
1.00×of list price
$0.60 / $3.60in / out per M
1.00×of list price
$0.60 / $3.60in / out per M
1.00×of list price
$0.60 / $3.60in / out per M
1.00×of list price
Hugging Face Inference ProvidersThe same price Alibaba Cloud charges.
$0.60 / $3.60in / out per M
1.00×of list price
Cloudflare AI GatewayThe same price Alibaba Cloud charges.
$0.60 / $3.60in / out per M
1.00×of list price
Jalapeno CloudThe same price Alibaba Cloud charges.
$0.60 / $3.60in / out per M
1.00×of list price
MixlayerThe same price Alibaba Cloud charges.
$0.60 / $3.60in / out per M
1.00×of list price
$0.60 / $3.60in / out per M
1.00×of list price
StreamLakeThe same price Alibaba Cloud charges.
256k context here$0.60 / $3.60in / out per M
1.00×of list price
$0.60 / $3.60in / out per M
1.00×of list price
$0.60 / $3.60in / out per M
1.00×of list price
$0.61 / $3.64in / out per M
1.01×of list price
Cortecs15% above Alibaba Cloud's price.Routes only to EU-hosted providers, prices in euros, and adds a flat 5% fee.
262k context hereCortecs ↗$0.69 / $4.15in / out per M
1.15×of list price
$0.69 / $4.15in / out per M
1.15×of list price
$0.71 / $4.25in / out per M
1.18×of list price
$0.75 / $4.50in / out per M
1.25×of list price
GreenPT33% above Alibaba Cloud's price.
$0.80 / $4.96in / out per M
1.36×of list price
Infomaniak65% above Alibaba Cloud's price.
200k context herefp8 precision$0.99 / $4.46in / out per M
1.38×of list price
Cheaper, and nobody says why
1 price · never rankedBelow list on a closed model with nothing to account for it. Shown, never ranked, never a pick.
FeatherlessWe could not read this provider's prices reliably, so the row is listed but never ranked.
$0.55 / $3.50in / out per M
0.95×of list price
Given away with limits
1 free tiers · never rankedThese providers give Qwen3.5 397B-A17B away inside a quota of their own. A limit is not a price, so none of them counts as cheapest here or anywhere else on the site.
NVIDIA build
Frequently asked
- Who sells Qwen3.5 397B-A17B cheapest?
- OrcaRouter, at $0.17 in and $1.03 out per million tokens, read on 16 Sept 2026. Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
- Is Qwen3.5 397B-A17B open weights?
- Yes. Alibaba Cloud publishes the weights, so anyone may host Qwen3.5 397B-A17B, which is why 44 providers sell it and why their prices differ so much.
- How much context does Qwen3.5 397B-A17B hold?
- 262,144 tokens in one call, which is about 262k, and it can call your own functions.
- How does Qwen3.5 397B-A17B compare with the rest of the market?
- At $5.40 per million tokens, Alibaba Cloud's price is 52% above the $3.55 median across the 337 text models we track.