Qwq 32B API

Alibaba's Qwq 32B, 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 qwq-32b 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: qwq-32b
Maker: Alibaba
Context window: 131.1K tokens
Input price: $0.150 per million tokens
Output price: $0.401 per million tokens
Providers: 1 independent provider
Regions: us

Providers

Architect: us, $0.150 input and $0.401 output per million tokens, $0.150 cache read per million tokens, 131.1K tokens of context

Scores

HLE: 7.3, #179 of 273
GPQA: 59.3, #181 of 250
AA-LCR: 26.7, #206 of 237
LiveCodeBench: 63.1, #41 of 130
AIME 2025: 29.0, #73 of 100
MMLU-Pro: 76.4, #60 of 133
IFBench: 38.8, #130 of 178

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

Request

curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwq-32b",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is Qwq 32B?: Qwq 32B is a model from Alibaba.
How much does Qwq 32B cost?: Offers now ask $0.150 per million input tokens and $0.401 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 Qwq 32B?: The largest offer takes 131,072 input tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can Qwq 32B do?: Its providers list Reasoning effort, JSON object, JSON schema, Frequency penalty, Logit bias, Log probabilities, Min-p sampling, Presence penalty, Repetition penalty, Seed, Stop sequences, Top-k sampling, Top-p sampling, Text, Tools.
What inputs and outputs does Qwq 32B support?: Text → Text.
Which providers serve Qwq 32B?: 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 Qwq 32B?: Send "qwq-32b" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was Qwq 32B listed?: The exchange first listed it on 10/10/2026. This is not its release date.