Alibaba logo

Qwen3 30B A3B Instruct

Pricing & Specs API
Free REST API for prices, specs and benchmarks
Qwen3 30B A3B Instruct is Alibaba's language model with a 262K context window and up to 32K output tokens, available from 3 providers, starting at $0.1 / 1M input and $0.3 / 1M output. An instruction-tuned Qwen3 MoE model with 30B total and 3B active parameters, optimized for text generation and instruction-following tasks.
Specifications
Canonical IDalibaba-qwen3-30b-a3b-instruct
TypeLanguage
StatusActive
CreatorAlibabaAlibaba
Providers
Context Window262K tokens
Max Output32K tokens
Input ModalitiesText
Output ModalitiesText
Parameters30B
HuggingFace Likes801
HuggingFace Downloads (30d)983,022
HuggingFace Downloads (all-time)10,380,022
Release Date · 12 months ago
Knowledge Cutoff · 1 year ago
Benchmarks
Intelligence Index
6.8
#370
Math Index
21.7
#198
MMLU-Pro
0.7
#198
GPQA
0.5
#327
HLE
0.0
#341
LiveCodeBench
0.3
#196
AIME
0.3
#82
IFBench
0.3
#322
Time to First Token
0.98s
#356
SciCode
0.3
#300
MATH-500
0.9
#79
AIME 2025
0.2
#198
LCR
0.0
#359
TerminalBench Hard
0.1
#226
TAU2
0.2
#292
Output TPS
113.3
#101

Capabilities

Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities3/13
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
ProviderStandardBatch
Input
$ / 1M
Output
$ / 1M
Input
$ / 1M
Output
$ / 1M
Alibaba Qwen logo
Alibaba Qwen
qwen3-30b-a3b-instruct
$0.2$0.8$0.1$0.4
Fireworks AI logo
Fireworks AI
fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-instruct-2507
$0.5$0.5——
OpenRouter logo
OpenRouter
qwen/qwen3-30b-a3b-instruct-2507
$0.1$0.3——

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host Qwen3 30B A3B Instruct, 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/hrwestus2
g7e.2xlargeAWSRTX PRO Server 600096 GB$3.36/hrus-east-1
Standard_NC24ads_A100_v4AzureNVIDIA A10080 GB$3.67/hrwestus2
7 more instances can run Qwen3 30B A3B Instruct
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$0.130$0.900Available
Qwen3 Coder 30B A3B Instruct262K$0.070$0.270Available
Qwen3 30B A3B Instruct262K$0.100$0.300Current
Qwen3 235B A22B Thinking262K$0.149$0.880Deprecated
Qwen3 Coder1.0M$0.300$1.00Deprecating
Qwen3 30B A3B131K$0.051$0.200Deprecated
Qwen3 235B A22B262K$0.090$0.540Available
Qwen3 Coder 480B A35B Instruct—262K$0.220$1.30Available
Qwen3 235B A22B Instruct—262K$0.090$0.580Available
KwaiPilot KAT Coder—262K$0.900$0.900Available

Model IDs

accounts/fireworks/models/qwen3-30b-a3b-instruct-2507
accounts/fireworks/models/qwen3-30b-a3b-instruct-2507-eagle3-v0
alibaba-qwen3-30b-a3b-instruct
fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-instruct-2507
huggingface-reasoning-qwen3-30b-a3b-instruct-2507
qwen/qwen3-30b-a3b-instruct-2507
qwen3-30b-a3b-instruct
qwen3-30b-a3b-instruct-2507