Qwen 3 30B a3b API

Alibaba's Qwen 3 30B a3b, through an OpenAI-compatible API. Providers quote it on an open exchange, and each request goes to the offer with the lowest estimated charge that meets your rules.

Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send qwen3-30b-a3b as the model.
Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.

Facts

Model name: qwen3-30b-a3b
Maker: Alibaba
Context window: 8,192 tokens
Input price: $0.109 per million tokens
Output price: $0.328 per million tokens
Providers: 1 independent provider
Regions: eu-central

Providers

Greenference: eu-central, $0.109 input and $0.328 output per million tokens, $0.055 cache read per million tokens, 8,192 tokens of context

Scores

HLE: 6.9, #182 of 273
GPQA: 65.9, #162 of 250
AA-LCR: 26.3, #207 of 237
Terminal-Bench Hard: 6.1, #140 of 166
LiveCodeBench: 51.5, #51 of 130
AIME 2025: 66.3, #37 of 100
MMLU-Pro: 77.7, #56 of 133
τ²-Bench: 10.2, #165 of 169
IFBench: 33.1, #151 of 178
SimpleQA Verified: 20.3, #93 of 126

Scores: Artificial Analysis (https://artificialanalysis.ai/)

Scores: Epoch AI, 'Capabilities & Benchmarking' (https://epoch.ai/benchmarks)

Request

curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3-30b-a3b",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is Qwen 3 30B a3b?: Served by intent-router: each job goes to the cheapest healthy upstream for this model.
How much does Qwen 3 30B a3b cost?: Offers now ask $0.109 per million input tokens and $0.328 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.
What is the context length of Qwen 3 30B a3b?: The largest offer takes 8,192 input tokens. One job can generate up to 8,192 tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can Qwen 3 30B a3b do?: Its providers list Frequency penalty, Min-p sampling, Presence penalty, Repetition penalty, Seed, Stop sequences, Top-k sampling, Top-p sampling, Text.
What inputs and outputs does Qwen 3 30B a3b support?: Text → Text.
Which providers serve Qwen 3 30B a3b?: 1 independent provider quote it now, with 1 offer. The table above ranks them by the cost of a typical job.
How do I call Qwen 3 30B a3b?: Send "qwen3-30b-a3b" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was Qwen 3 30B a3b listed?: The exchange first listed it on 10/8/2026. This is not its release date.