Qwen 3.6 35B a3b:thinking API

Alibaba's Qwen 3.6 35B a3b:thinking, 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 qwen3.6-35b-a3b:thinking 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: qwen3.6-35b-a3b:thinking
Maker: Alibaba
Context window: 1M tokens
Input price: $0.112 per million tokens
Output price: $0.800 per million tokens
Providers: 1 independent provider
Regions: us

Providers

Architect: us, $0.112 input and $0.800 output per million tokens, $0.112 cache read per million tokens, 1M tokens of context

Scores

HLE: 22.2, #110 of 273
GPQA: 84.1, #83 of 250
AA-LCR: 71.7, #109 of 237
SciCode: 36.6, #105 of 123
Terminal-Bench Hard: 34.8, #40 of 166
τ²-Bench: 95.3, #18 of 169
IFBench: 64.4, #57 of 178
SimpleQA Verified: 15.9, #115 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": "qwen3.6-35b-a3b:thinking",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is Qwen 3.6 35B a3b:thinking?: Qwen 3.6 35B a3b:thinking is a model from Alibaba.
How much does Qwen 3.6 35B a3b:thinking cost?: Offers now ask $0.112 per million input tokens and $0.800 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 3.6 35B a3b:thinking?: The largest offer takes 1,048,576 input tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can Qwen 3.6 35B a3b:thinking do?: Its providers list Vision, Video input, 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 Qwen 3.6 35B a3b:thinking support?: Text · Images · Video → Text.
Which providers serve Qwen 3.6 35B a3b:thinking?: 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 3.6 35B a3b:thinking?: Send "qwen3.6-35b-a3b:thinking" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was Qwen 3.6 35B a3b:thinking listed?: The exchange first listed it on 10/10/2026. This is not its release date.