Qwen: Qwen3 30B A3B

Qwen

Qwen: Qwen3 30B A3B by Qwen costs $0.12 per 1M input tokens and $0.50 per 1M output tokens, with a 41K-token context window.

Pricing

Input (per 1M tokens)

$0.12

Output (per 1M tokens)

$0.50

Cached input (per 1M)

—

Specifications

Provider: Qwen
Context window: 41K tokens
Parameters: —
Released: —
Open weights: —
Frontier model: No
Hugging Face: Qwen/Qwen3-30B-A3B

Benchmarks

Epoch Capabilities Index: 139.6
GPQA Diamond: 70.1
LiveBench: 38.8
LMArena (Chatbot Arena) Elo: 1316.8

Speed & latency

Time to first token

0.21s

Output speed

121 tok/s

Fastest host: deepinfra (via hf-router).

Compare Qwen: Qwen3 30B A3B with…

Qwen: Qwen3 30B A3B vs Claude Haiku 5.5$0.50/1M Qwen: Qwen3 30B A3B vs GPT-6 Luna$0.50/1M Qwen: Qwen3 30B A3B vs Olmo 3 32B Think$0.50/1M Qwen: Qwen3 30B A3B vs Grok 4.1 Fast$0.50/1M Qwen: Qwen3 30B A3B vs Grok 3 Mini$0.50/1M Qwen: Qwen3 30B A3B vs xAI Grok 4.1 Fast Non-Reasoning$0.50/1M

FAQ

How much does Qwen: Qwen3 30B A3B cost?

Qwen: Qwen3 30B A3B is priced at $0.12 per 1M input tokens and $0.50 per 1M output tokens. Output tokens cost more than input.

What is Qwen: Qwen3 30B A3B's context window?

Qwen: Qwen3 30B A3B supports a context window of 41K tokens — the maximum prompt plus response length it can handle in a single request.

Is Qwen: Qwen3 30B A3B open weight?

Open-weight status for Qwen: Qwen3 30B A3B is not recorded in our dataset.

Data as of 2026-10-15. Source: Pricing via OpenRouter API, openrouter.ai. Pricing is per 1M tokens (USD); confirm with the provider before production use.