Qwen 2.5 72B Instruct API

Alibaba's Qwen 2.5 72B Instruct, 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 qwen-2.5-72b-instruct 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: qwen-2.5-72b-instruct
Maker: Alibaba
Context window: 32.8K · 131.1K tokens
Input price: $0.359 to $0.361 per million tokens
Output price: $0.399 to $0.401 per million tokens
Providers: 1 independent provider
Regions: us

Providers

Architect: us, $0.359 input and $0.399 output per million tokens, $0.359 cache read per million tokens, 32.8K tokens of context
Architect: us, $0.361 input and $0.401 output per million tokens, $0.361 cache read per million tokens, 131.1K tokens of context

Scores

HLE: 3.6, #255 of 273
GPQA: 49.1, #212 of 250
Terminal-Bench Hard: 4.5, #145 of 166
LiveCodeBench: 27.6, #96 of 130
AIME 2025: 14.0, #89 of 100
MMLU-Pro: 72.0, #85 of 133
τ²-Bench: 34.5, #127 of 169
IFBench: 36.9, #138 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": "qwen-2.5-72b-instruct",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is Qwen 2.5 72B Instruct?: Served by intent-router: each job goes to the cheapest healthy upstream for this model.
How much does Qwen 2.5 72B Instruct cost?: Offers now ask $0.359 to $0.361 per million input tokens and $0.399 to $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 Qwen 2.5 72B Instruct?: 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 Qwen 2.5 72B Instruct 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 Qwen 2.5 72B Instruct support?: Text → Text.
Which providers serve Qwen 2.5 72B Instruct?: 1 independent provider quote it now, with 2 offers. The table above ranks them by the cost of a typical job.
How do I call Qwen 2.5 72B Instruct?: Send "qwen-2.5-72b-instruct" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was Qwen 2.5 72B Instruct listed?: The exchange first listed it on 10/8/2026. This is not its release date.