Qwen3-Coder 30B-A3B Instruct pricing.
prices as of · 24 providers · 27 prices
Alibaba Cloud's Qwen3-Coder 30B-A3B Instruct holds 262k tokens of context. Open weights, so anyone may host it, which is why the prices below differ so much.
Qwen3-Coder 30B-A3B Instruct costs $0.45 in and $2.25 out per million tokens from Alibaba Cloud; the cheapest price we can explain is $0.46 at Cortecs, checked 16 Sept 2026.
Alibaba Cloud list price
$3.60/M tokens
$0.45 in · $2.25 out
read · 1% above the market median
Cheapest price we can explain
$0.46/M tokens
$0.07 in · $0.25 out · 87% under list
Cortecsread
What it costs for your work
Alibaba Cloud list price
$0.405a month
cheapest we can explain · Cortecs
$0.0568a month
difference
$0.348saved
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-Coder 30B-A3B Instruct
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.
$0.45 / $2.25in / out per M
1.00×of list price
Cheaper, and we know why
23 pricesBelow list, with a published reason: hosting the open weights, a regional price list, credits, a stated discount.
$0.07 / $0.25in / out per M
0.13×of list price
Hugging Face Inference ProvidersRoutes to a host serving the open weights; precision not disclosed.
$0.07 / $0.26in / out per M
0.13×of list price
OVHcloud AI EndpointsHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.07 / $0.26in / out per M
0.13×of list price
Eden AIAlibaba's China-region price list, which is lower than the international one. A region, not a deal.
$0.07 / $0.26in / out per M
0.13×of list price
LLM GatewayRoutes to a host serving the open weights; precision not disclosed.
160k context hereLLM Gateway ↗$0.07 / $0.27in / out per M
0.13×of list price
NovitaHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
160k context hereNovita ↗$0.07 / $0.27in / out per M
0.13×of list price
- Novita
Serves the open weights at fp8, a lower precision than the maker's, so not quite the same product.
$0.07 / $0.27in / out per M
0.13×of list price
Nous PortalResells OpenRouter's catalog at 0.80× the listed price, funded by a subscription whose credits carry a 10% bonus.
$0.07 / $0.27in / out per M
0.13×of list price
$0.07 / $0.28in / out per M
0.14×of list price
SiliconFlow (China)SiliconFlow's China-region catalog, priced in the domestic market.
262k context hereSiliconFlow (China) ↗$0.07 / $0.28in / out per M
0.14×of list price
SiliconFlowHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
262k context hereSiliconFlow ↗$0.07 / $0.28in / out per M
0.14×of list price
- SiliconFlow
Serves the open weights at fp8, a lower precision than the maker's, so not quite the same product.
fp8 precisionSiliconFlow ↗$0.07 / $0.28in / out per M
0.14×of list price
TrustedRouterRoutes to a host serving the open weights; precision not disclosed.
160k context hereTrustedRouter ↗$0.07 / $0.28in / out per M
0.14×of list price
HeliconeHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.10 / $0.30in / out per M
0.17×of list price
NanoGPTRoutes to a host serving the open weights; precision not disclosed.
128k context hereNanoGPT ↗$0.10 / $0.40in / out per M
0.19×of list price
Vercel AI GatewayRoutes to a host serving the open weights; precision not disclosed.
$0.15 / $0.60in / out per M
0.29×of list price
Fireworks AIHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.15 / $0.60in / out per M
0.29×of list price
Amazon BedrockHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
context hereAmazon Bedrock ↗$0.15 / $0.60in / out per M
0.29×of list price
- Clarifai
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.11 / $0.75in / out per M
0.30×of list price
ScalewayHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
128k context hereScaleway ↗$0.20 / $0.80in / out per M
0.39×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.
$0.22 / $0.86in / out per M
0.42×of list price
GreenPTHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
128k context here$0.28 / $1.08in / out per M
0.54×of list price
$0.29 / $1.46in / out per M
0.65×of list price
Cheaper, and nobody says why
2 prices · never rankedBelow list on a closed model with nothing to account for it. Shown, never ranked, never a pick.
- TensorX
0.13× the list price, from one source and far below what hosting the weights costs. Listed until a second source agrees.
262k context here$0.06 / $0.25in / out per M
0.12×of list price
FeatherlessWe could not read this provider's prices reliably, so the row is listed but never ranked.
33k context hereFeatherless ↗$0.13 / $0.45in / out per M
0.23×of list price
Given away with limits
1 free tiers · never rankedThese providers give Qwen3-Coder 30B-A3B Instruct 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.
ModelScope
Frequently asked
- Who sells Qwen3-Coder 30B-A3B Instruct cheapest?
- Cortecs, at $0.07 in and $0.25 out per million tokens, read on 16 Sept 2026. Routes to a host serving the open weights; precision not disclosed.
- Is Qwen3-Coder 30B-A3B Instruct open weights?
- Yes. Alibaba Cloud publishes the weights, so anyone may host Qwen3-Coder 30B-A3B Instruct, which is why 24 providers sell it and why their prices differ so much.
- How much context does Qwen3-Coder 30B-A3B Instruct hold?
- 262,144 tokens in one call, which is about 262k, and it can call your own functions.
- How does Qwen3-Coder 30B-A3B Instruct compare with the rest of the market?
- At $3.60 per million tokens, Alibaba Cloud's price is 1% above the $3.55 median across the 337 text models we track.