EN / 中文
Model prices / Alibaba / Qwen3 30B A3B

Qwen3 30B A3BOpen weights

Alibaba · released 2025-04-28

No price from the maker itself is on record for Qwen3 30B A3B. The lowest of 14 providers is Helicone: $0.08 per 1M input tokens and $0.29 per 1M output tokens (as of 2026-11-12). Context window: 41K tokens, up to 16.4K output tokens per request.

Price by providerUSD per 1M tokens

ProviderInputOutputCachedNotes
HHeliconeLowestqwen3-30b-a3b
$0.08$0.29—LowestOfficial docs
$0.095$0.285—Official docs
LLLM Gatewaygreenference/qwen3-30b-a3b
$0.095$0.285—Official docs
NNanoGPTqwen/qwen3-30b-a3b
$0.1$0.3$0.05Official docs
JJiekou.AIqwen/qwen3-30b-a3b-fp8
$0.09$0.45—Official docs
Deep InfraQwen/Qwen3-30B-A3B
$0.12$0.5—Official docs
Hugging FaceQwen/Qwen3-30B-A3B
$0.12$0.5—Official docs
KKilo Gatewayqwen/qwen3-30b-a3b
$0.12$0.5—Official docs
OpenRouterqwen/qwen3-30b-a3b
$0.12$0.5—Official docs
Vercel AI Gatewayalibaba/qwen-3-30b
$0.12$0.5—Official docs
MMerge Gatewayqwen/qwen3-30b-a3b
$0.108$1.076$0.0216Official docs
3302.AIqwen3-30b-a3b
$0.11$1.08—Official docs
2 more listings
ProviderInputOutputCachedNotes
Cloudflare Workers AIDeprecated@cf/qwen/qwen3-30b-a3b-fp8
$0.0509$0.335—DeprecatedOfficial docs
QQiniuDeprecatedqwen3-30b-a3b
$0.108696$0.434783—DeprecatedOfficial docs

Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.

About

Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning

Description from models.dev.

Specs

Type
Text
Context
41K
Max output
16.4K
Input
Text
Output
Text
Reasoning
Yes
Tool calling
Yes
Structured output
Yes
Knowledge cutoff
2025-04
Open weights
Yes
Released
2025-04-28

Source

Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.