Qwen3 Omni 30B A3B Instruct is Alibaba's language model with a 66K context window and up to 16K output tokens, starting at $0.250 / 1M input and $0.970 / 1M output. An end-to-end multilingual omni-modal LLM with 30B total and 3B activated parameters, natively processing text, images, audio, and video inputs.
Specifications
Canonical IDalibaba-qwen3-omni-30b-a3b-instruct
TypeLanguage
StatusActive
CreatorAlibabaAlibaba
Providers
Context Window66K tokens
Max Output16K tokens
Input ModalitiesAudioImage
Output ModalitiesAudio
Parameters30B
Benchmarks
Intelligence Index
10.7
#378
Coding Index
7.2
#331
Math Index
52.3
#129
MMLU-Pro
0.7
#185
GPQA
0.6
#242
HLE
0.1
#268
LiveCodeBench
0.4
#161
IFBench
0.3
#323
Time to First Token
0.94s
#322
SciCode
0.2
#347
AIME 2025
0.5
#129
LCR
0.0
#345
TerminalBench Hard
0.0
#308
TAU2
0.2
#321
Output TPS
109.7
#116

Capabilities

Input2/5
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

ProviderStandard
Input
$ / 1M
Output
$ / 1M
Novita logo
Novita
novita/qwen/qwen3-omni-30b-a3b-instruct
$0.250$0.970

Cost Calculator

Preset:

Model IDs