All AI models · LLM benchmarks · Methodology

Alibaba

Qwen3 30B A3B

Qwen instruction model for multilingual chat, reasoning, and tool use

Model facts

Context window
41K tokens
Maximum output
16K tokens
Cheapest paid input
$0.08 per 1M tokens
Cheapest paid output
$0.29 per 1M tokens
Open weights
yes
Providers
13

Capabilities and modalities

reasoning, tool calling, structured output, temperature control, open weights, text, image.

Local hardware estimate

At 4K context: Q4_K_M 17.4 GiB, Q8_0 31.6 GiB, F16 58.2 GiB working memory.

Parameters
30.5 billion
Architecture
qwen3moe
Model license
apache-2.0

Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.

Artificial Analysis benchmarks

Compare this model on the full LLM benchmark leaderboard.

ConfigurationAAICodingMathOutput tokens/s
Reasoning9.2not measured72.3not measured
Non-reasoning6.6not measured21.7not measured

Observed price history

  • 2026-08-24: $0.08 input / $0.29 output per 1M tokens

API providers