Qwen 2 72B Instruct API
Pricing & Specs

Qwen (Alibaba) · $0.9 input / $0.9 output per 1M tokens · 32.768K context window

No longer offered on OpenMark

$0.9
per 1M input tokens
$0.9
per 1M output tokens
32.768K
context window (tokens)

Qwen 2 72B Instruct API is no longer offered on OpenMark (deprecated or superseded upstream). Its specs are kept here for reference. If you're still running it in production, it's worth benchmarking current alternatives: newer models are often cheaper AND better on the same task.

Qwen 2 72B Instruct API API Pricing

TokensPrice
Input$0.9 / 1M tokens
Output$0.9 / 1M tokens

Batch API pricing is available via Together at 50%; cache pricing is not published.

What that means in practice

1x One typical task (1K input + 500 output tokens): $0.0014
1K 1,000 runs of that task: $1.35
💡 Real cost depends on how verbose the model is on YOUR prompts. Benchmark to measure actual tokens, not estimates.

Qwen 2 72B Instruct API Specs

SpecValue
Context window32.768K tokens
Input modalitiestext
Output modalitiestext
Reasoning modelNo
Tool / function callingNo
JSON modeNo
StreamingYes
Prompt cachingNo
Batch APIYes

Capabilities

text generation streaming

Notes

Removed by host on 2025-08

FAQ

How much does Qwen 2 72B Instruct API cost?

Qwen 2 72B Instruct API costs $0.9 per 1M input tokens and $0.9 per 1M output tokens.

What is Qwen 2 72B Instruct API's context window?

Qwen 2 72B Instruct API has a 32.768K-token context window.

Can I test Qwen 2 72B Instruct API on my own task?

Qwen 2 72B Instruct API is no longer offered on OpenMark, but you can benchmark its current alternatives from Qwen (Alibaba) and other providers on your own task, free tier available.

Still using Qwen 2 72B Instruct API?

It's been superseded. Benchmark its current alternatives on your actual
workload. You'll likely find something cheaper AND better. Free tier available.

Test Current Alternatives Free →

Get the monthly model change report

New models, API price changes, and retirements, straight from the registry that powers OpenMark. One email a month.