Qwen3.6 35B-A3B pricing.
prices as of · 38 providers · 47 prices
Alibaba Cloud's Qwen3.6 35B-A3B 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.
Qwen3.6 35B-A3B costs $0.25 in and $1.49 out per million tokens from Alibaba Cloud; the cheapest price we can explain is $0.46 at TrustedRouter, checked 16 Sept 2026.
Alibaba Cloud list price
$2.23/M tokens
$0.25 in · $1.49 out
read · 37% below the market median
Cheapest price we can explain
$0.46/M tokens
$0.05 in · $0.32 out · 79% under list
TrustedRouterread
What it costs for your work
Alibaba Cloud list price
$0.238a month
cheapest we can explain · TrustedRouter
$0.0475a month
difference
$0.19saved
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 Qwen3.6 35B-A3B
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.
$0.25 / $1.49in / out per M
1.00×of list price
Cheaper, and we know why
28 pricesBelow list, with a published reason: hosting the open weights, a regional price list, credits, a stated discount.
$0.05 / $0.32in / out per M
0.21×of list price
Empirio LabsRoutes to a host serving the open weights; precision not disclosed.
131k context hereEmpirio Labs ↗$0.07 / $0.42in / out per M
0.28×of list price
- Darkbloom
Serves the open weights at fp4, a lower precision than the maker's, so not quite the same product.
fp4 precision$0.05 / $0.70in / out per M
0.38×of list price
Nous PortalResells OpenRouter's catalog at 0.80× the listed price, funded by a subscription whose credits carry a 10% bonus.
$0.05 / $0.70in / out per M
0.38×of list price
SaladCloud AI GatewayHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.09 / $0.60in / out per M
0.39×of list price
$0.07 / $0.70in / out per M
0.41×of list price
CortecsRoutes to a host serving the open weights; precision not disclosed.
262k context hereCortecs ↗$0.17 / $0.58in / out per M
0.49×of list price
$0.11 / $0.80in / out per M
0.51×of list price
$0.11 / $0.80in / out per M
0.51×of list price
$0.10 / $0.90in / out per M
0.54×of list price
$0.10 / $0.90in / out per M
0.54×of list price
AkashMLServes the open weights at fp8, a lower precision than the maker's, so not quite the same product.
fp8 precision$0.10 / $0.90in / out per M
0.54×of list price
DeepInfraHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.10 / $0.95in / out per M
0.56×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 ↗$0.10 / $0.95in / out per M
0.56×of list price
VeniceHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
256k context hereVenice ↗$0.10 / $1in / out per M
0.58×of list price
DekaLLMHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.10 / $1in / out per M
0.58×of list price
- Venice
Serves the open weights at fp8, a lower precision than the maker's, so not quite the same product.
$0.10 / $1in / out per M
0.58×of list price
Hugging Face Inference ProvidersRoutes to a host serving the open weights; precision not disclosed.
$0.15 / $0.95in / out per M
0.63×of list price
ParasailServes the open weights at fp8, a lower precision than the maker's, so not quite the same product.
fp8 precisionParasail ↗$0.15 / $1in / out per M
0.65×of list price
io.net IntelligenceServes the open weights at fp8, a lower precision than the maker's, so not quite the same product.
fp8 precisionio.net Intelligence ↗$0.19 / $0.99in / out per M
0.70×of list price
NEAR AI CloudServes the open weights at fp8, a lower precision than the maker's, so not quite the same product.
fp8 precisionNEAR AI Cloud ↗$0.17 / $1.10in / out per M
0.72×of list price
Atlas CloudServes the open weights at fp8, a lower precision than the maker's, so not quite the same product.
fp8 precisionAtlas Cloud ↗$0.19 / $1.11in / out per M
0.75×of list price
$0.19 / $1.11in / out per M
0.75×of list price
- io.net Intelligence
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
Phala (RedPill)Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.20 / $1.27in / out per M
0.84×of list price
showing the 25 cheapest of 28 · every row in the open dataset
Same price as the maker
11 pricesThe same price the maker charges, sold by someone else.
Weights & BiasesThe same price Alibaba Cloud charges.
$0.25 / $1.25in / out per M
0.90×of list price
CoreWeaveThe same price Alibaba Cloud charges.
fp8 precision$0.25 / $1.25in / out per M
0.90×of list price
$0.24 / $1.46in / out per M
0.98×of list price
$0.25 / $1.49in / out per M
1.00×of list price
OrcaRouterThe same price Alibaba Cloud charges.
$0.25 / $1.49in / out per M
1.00×of list price
Merge GatewayThe same price Alibaba Cloud charges.
$0.25 / $1.49in / out per M
1.00×of list price
$0.25 / $1.49in / out per M
1.00×of list price
$0.25 / $1.50in / out per M
1.01×of list price
Models Think Evroc39% above Alibaba Cloud's price.
$0.34 / $1.38in / out per M
1.08×of list price
302.AI14% above Alibaba Cloud's price.
$0.28 / $1.71in / out per M
1.15×of list price
GreenPT38% above Alibaba Cloud's price.
$0.34 / $2.05in / out per M
1.38×of list price
Cheaper, and nobody says why
4 prices · never rankedBelow list on a closed model with nothing to account for it. Shown, never ranked, never a pick.
ZenifraA router whose catalog prices are several times list, most likely a unit we have not identified.
$0.19 / $0.48in / out per M
0.47×of list price
$0.12 / $0.76in / out per M
0.50×of list price
$0.14 / $1in / out per M
0.64×of list price
FeatherlessWe could not read this provider's prices reliably, so the row is listed but never ranked.
33k context hereFeatherless ↗$0.19 / $1.11in / out per M
0.75×of list price
Given away with limits
3 free tiers · never rankedThese providers give Qwen3.6 35B-A3B 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.
- QVAC
InferX
Hetzner
Frequently asked
- Who sells Qwen3.6 35B-A3B cheapest?
- TrustedRouter, at $0.05 in and $0.32 out per million tokens, read on 16 Sept 2026. Routes to a host serving the open weights; precision not disclosed.
- Is Qwen3.6 35B-A3B open weights?
- Yes. Alibaba Cloud publishes the weights, so anyone may host Qwen3.6 35B-A3B, which is why 38 providers sell it and why their prices differ so much.
- How much context does Qwen3.6 35B-A3B hold?
- 262,144 tokens in one call, which is about 262k, and it can call your own functions.
- How does Qwen3.6 35B-A3B compare with the rest of the market?
- At $2.23 per million tokens, Alibaba Cloud's price is 37% below the $3.55 median across the 337 text models we track.