OPEN 72BLEGACY QWEN 2.5131K CONTEXTTEXTBATCH -50%
Qwen2.5 72B Instruct API Pricing
Qwen2.5 72B Instruct is Alibaba's legacy open-weight flagship dense Qwen2.5 row for compatibility and invoice checks. Alibaba lists the International/Singapore baseline at $1.4/M input and $5.6/M output; newer workloads should compare Qwen3 235B A22B. Pulled directly from alibabacloud.com daily.
Input - per 1M tokens
$1.40/M
Source Alibaba Cloud flat
Output - per 1M tokens
$5.60/M
Context 131K flat
Cache N/A
$1.40/M
Cache no dollar row not listed
Effective - agentic blend
$1.74/M
92/8 split - no cache
§ 01 / TERMINAL
Run the numbers.
Live calculator pre-loaded with current Qwen2.5 72B Instruct rates. Tweak spend, output mix, or cache assumptions and share the URL to share the calculation.
$ /mo
Workload split
Prompt cache hit rate
Tokens you can process
—
Words equivalent (English)
—
Effective rate
—
§ 02 / SCENARIOS
Real-world presets.
CHATBOT
Support assistant
$0.007/turn
RAG
Knowledge base answer
$0.018/query
CODE REVIEW
Repository review
$0.036/task
CLASSIFY
Intent routing
$0.003/item
§ 03 / TAPE
Price history.
Input · $1.4/M
Output · $5.6/M
Cached · $1.4/M
SEP 19 Qwen2.5 72B Instruct launch-wave pricing stored at $1.4/M input and $5.6/M outputMAY 19 Live verification kept $1.4/M input and $5.6/M output
§ 04 / TOKENIZER
Paste text. See tokens. See cost.
Estimate · qwen-tokenizer-estimate · ≈3.85 chars/token Auto-counts as you type
This is a chars-per-token approximation, not a real tokenizer. Actual tokens vary by language, code density, and tool-call overhead — counts are typically ±10–20% off for English prose, more for code or non-Latin scripts. For exact billing, use the vendor's official tokenizer.
Characters —
Words —
Tokens (estimated) —
Cost as input · uncached —
Cost as output · uncached —
Cost as cached input —
| Model | Input /M | Output /M | Effective blended | Context | Best for |
|---|---|---|---|---|---|
| Qwen 2.5 72B Instruct Current | $1.40 | $5.60 | $1.74 agentic 92/8 | 131K | Legacy 72B open Qwen compatibility |
| Qwen 2.5 32B Instruct | $0.70 | $2.80 | $0.87 cheaper | 131K | Legacy 32B open chat workloads |
| Qwen 2.5 14B Instruct | $0.35 | $1.40 | $0.43 cheaper | 131K | Legacy compact open Qwen apps |
| Qwen 2.5 7B Instruct | $0.17 | $0.70 | $0.22 cheaper | 131K | Legacy small open Qwen deployments |
| Qwen3 235B A22B | $0.70 | $2.80 | $0.87 cheaper | 131K | Current open MoE reasoning baseline |
| Qwen3 32B | $0.16 | $0.64 | $0.20 cheaper | 131K | Current open 32B chat and reasoning |
| Qwen Max (2.5) | $1.60 | $6.40 | $1.98 pricier | 32K | Comparable production workloads |
| GPT-5.4 mini | $0.75 cache $0.07 | $4.50 | $0.54 cheaper | 400K | OpenAI mini coding and CUA |
Frequently asked.
Practical pricing questions, separated from calculator assumptions and regional tiers.
Q · 01 What is Qwen2.5 72B Instruct priced at? +
Qwen2.5 72B Instruct is listed at
$1.4/M input and $5.6/M output in Alibaba Cloud Model Studio's International/Singapore deployment section. The page stores USD per-million-token pricing.Q · 02 What replaced Qwen2.5 72B Instruct? +
Qwen2.5 72B Instruct is a legacy Qwen 2.5 compatibility row. For new workloads, compare Qwen3 235B A22B or the current Qwen3 family before staying on the older SKU.
Q · 03 Does this page use International or Global pricing? +
This page uses Alibaba Cloud Model Studio International deployment pricing, where endpoint and data storage are in Singapore and inference resources are dynamically scheduled globally excluding Chinese Mainland. Global, US, EU, China (Hong Kong), and Chinese Mainland sections can list different prices.
Q · 04 Is prompt caching priced separately? +
Alibaba marks context-cache support on some Qwen rows, but this row does not publish a concrete cache-read dollar price in the pricing table. The calculator therefore treats cached input as the same
$1.4/M baseline instead of inventing a discount.Q · 05 How is the effective price calculated? +
AI//COST uses the same 92/8 agentic blend everywhere. With no separate cache-read price published for this row, Qwen2.5 72B Instruct's effective blended cost is
$1.74/M.Q · 06 Is there a Batch Invocation discount? +
Alibaba documents Batch Invocation as 50% off real-time input and output tokens for supported Qwen rows. The quote tiles show real-time list pricing; batch economics should be treated as a separate calculator variant.
Q · 07 Does Alibaba include a free quota? +
Many International Model Studio rows include a 1 million token free quota that is valid for 90 days after activating Model Studio. Free-quota eligibility is deployment- and model-specific, so production estimates should use the paid list prices shown here.