Qwen3 Omni 30B A3B Instruct is Alibaba's language model with a 66K context window and up to 16K output tokens, starting at $0.25 / 1M input and $0.97 / 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
#385
Coding Index
7.2
#336
Math Index
52.3
#129
MMLU-Pro
0.7
#185
GPQA
0.6
#247
HLE
0.1
#275
LiveCodeBench
0.4
#161
IFBench
0.3
#330
Time to First Token
1.03s
#329
SciCode
0.2
#352
AIME 2025
0.5
#129
LCR
0.0
#351
TerminalBench Hard
0.0
#314
TAU2
0.2
#327
Output TPS
106.2
#112

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

US Dollar ($)
Per 1M tokens
ProviderStandard
Input
$ / 1M
Output
$ / 1M
Novita logo
Novita
novita/qwen/qwen3-omni-30b-a3b-instruct
$0.25$0.97

Cost Calculator

US Dollar ($)
Preset:

Model IDs

accounts/fireworks/models/qwen3-omni-30b-a3b-instruct
alibaba-qwen3-omni-30b-a3b-instruct
novita/qwen/qwen3-omni-30b-a3b-instruct
qwen/qwen3-omni-30b-a3b-instruct
qwen3-omni-30b-a3b-instruct