Alibaba logo

Qwen3 30B A3B

Deprecated
Pricing & Specs API
Free REST API for prices, specs and benchmarks
Qwen3 30B A3B is Alibaba's language model with a 131K context window and up to 20K output tokens, available from 6 providers, starting at $0.051 / 1M input and $0.2 / 1M output. A Mixture-of-Experts LLM with 30B total parameters and 3B active parameters per token, balancing efficiency and strong reasoning performance.
Specifications
Canonical IDalibaba-qwen3-30b-a3b
TypeLanguage
StatusDeprecated
CreatorAlibabaAlibaba
Providers
Context Window131K tokens
Max Output20K tokens
Input ModalitiesText
Output ModalitiesText
Reasoning Effortsdefault
Parameters30B
HuggingFace Likes879
HuggingFace Downloads (30d)1,327,516
HuggingFace Downloads (all-time)8,535,617
Release Date · 1 year ago
Knowledge Cutoff · 2 years ago
Deprecation Date
Benchmarks
Intelligence Index
#319
Coding Index
#184
Math Index
#119
MMLU-Pro
#119
GPQA
#265
HLE
#243
LiveCodeBench
#78
AIME
#9
IFBench
#178
Time to First Token
#27
SciCode
#296
MATH-500
#27
AIME 2025
#119
LCR
#200
TerminalBench Hard
#259
TAU2
#267
Output TPS
#104

Capabilities

Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities5/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs✓
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill✓

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandard
Input
$ / 1M
Output
$ / 1M
Cloudflare Workers AI logo
Cloudflare Workers AI
@cf/qwen/qwen3-30b-a3b-fp8
$0.051$0.335
DeepInfra logo
DeepInfra
deepinfra/Qwen/Qwen3-30B-A3B
$0.12$0.5
Fireworks AI logo
Fireworks AI
fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b
$0.15$0.6
Novita logo
Novita
novita/qwen/qwen3-30b-a3b-fp8
$0.09$0.45
OpenRouter logo
OpenRouter
qwen/qwen3-30b-a3b
$0.12$0.5
Pinstripes
pinstripes/ps/qwen3-30b-a3b
$0.09$0.2

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host Qwen3 30B A3B, ranked by cheapest on-demand price. The model needs about 72 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds
FP16 (full precision)
US Dollar ($)
Instance
Cloud
GPU
VRAM
Price
Cheapest region
Standard_NP20sAzure2× AMD Alveo U250 FPGA (64GB)128 GB$3.30/hr
g7e.2xlargeAWSRTX PRO Server 600096 GB$3.36/hr
Standard_NC24ads_A100_v4AzureNVIDIA A10080 GB$3.67/hr
7 more instances can run Qwen3 30B A3B
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
MiroThinker 1.7————Available
Qwen3 30B A3B Thinking262K$0.900$0.900Deprecated
Qwen3 Coder 30B A3B Instruct262K$0.070$0.270Deprecated
Qwen3 30B A3B Instruct262K$0.100$0.300Deprecated
Qwen3 235B A22B Thinking262K$0.220$0.880Deprecated
Qwen3 Coder262K$0.220$1.00Deprecated
Qwen3 235B A22B262K$0.090$0.540Deprecated
Qwen3 30B A3B131K$0.051$0.200Current
Qwen3 235B A22B Instruct—262K$0.090$0.550Deprecated
Qwen3 Coder 480B A35B Instruct—262K$0.220$1.55Deprecated
KwaiPilot KAT Coder—262K$0.900$0.900Available

Model IDs

@cf/qwen/qwen3-30b-a3b-fp8
accounts/fireworks/models/qwen3-30b-a3b
alibaba-qwen3-30b-a3b
cloudflare/@cf/qwen/qwen3-30b-a3b-fp8
dashscope/qwen3-30b-a3b
deepinfra/Qwen/Qwen3-30B-A3B
fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b
huggingface-reasoning-qwen3-30b-a3b
nebius/Qwen/Qwen3-30B-A3B
novita/qwen/qwen3-30b-a3b-fp8
openrouter/qwen/qwen3-30b-a3b
pinstripes/ps/qwen3-30b-a3b
qwen_ai_platform/qwen3-30b-a3b
qwen/qwen3-30b-a3b
Qwen/Qwen3-30B-A3B
qwen/qwen3-30b-a3b-fp8
qwen3-30b-a3b
qwen3-30b-a3b-2507
qwen3-30b-a3b-2507-reasoning
qwen3-30b-a3b-instruct-reasoning
qwencloud/qwen3-30b-a3b