All AI models · LLM benchmarks · Methodology

Alibaba

Qwen3 30B A3B Instruct 2507

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

Model facts

Context window
262K tokens
Maximum output
262K tokens
Cheapest paid input
$0.048 per 1M tokens
Cheapest paid output
$0.193 per 1M tokens
Open weights
yes
Providers
10

Capabilities and modalities

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

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
default8.9not measured66.3not measured

Observed price history

  • 2026-08-24: $0.048 input / $0.193 output per 1M tokens

API providers

  • ModelScope — model id Qwen/Qwen3-30B-A3B-Instruct-2507; free input / free output per 1M tokens; provider documentation
  • OpenRouter — model id qwen/qwen3-30b-a3b-instruct-2507; $0.048 input / $0.193 output per 1M tokens; provider documentation
  • Cortecs — model id qwen3-30b-a3b-instruct-2507; $0.099 input / $0.299 output per 1M tokens; provider documentation
  • Nebius Token Factory — model id Qwen/Qwen3-30B-A3B-Instruct-2507; $0.1 input / $0.3 output per 1M tokens; provider documentation
  • Weights & Biases — model id Qwen/Qwen3-30B-A3B-Instruct-2507; $0.1 input / $0.3 output per 1M tokens; provider documentation
  • NanoGPT — model id qwen3-30b-a3b-instruct-2507; $0.2 input / $0.5 output per 1M tokens; provider documentation
  • NEAR AI Cloud — model id Qwen/Qwen3-30B-A3B-Instruct-2507; $0.15 input / $0.55 output per 1M tokens; provider documentation
  • Clarifai — model id qwen/qwenLM/models/Qwen3-30B-A3B-Instruct-2507; $0.3 input / $0.5 output per 1M tokens; provider documentation
  • Arena — model id qwen3-30b-a3b-instruct-2507; not published input / not published output per 1M tokens; provider documentation
  • Qiniu — model id qwen3-30b-a3b-instruct-2507; not published input / not published output per 1M tokens; provider documentation