Qwen model
Qwen2.5 72B Instruct API cost calculator
Qwen2.5 72B Instruct costs $0.36 per 1M input tokens and $0.40 per 1M output tokens on the Qwen API, with a 33K-token context window. A typical request (2K input, 500 output tokens) costs $0.0009 — about $27.60/month at 1,000 requests per day. Use the calculator below to model your exact workload.
Find me a cheaper modelWhat real workloads cost on Qwen2.5 72B Instruct
| Workload | Tokens (in / out) | Per request | Per 1K requests |
|---|---|---|---|
| Chatbot message | 500 / 300 | $0.0003 | $0.30 |
| RAG query with context | 4,000 / 500 | $0.0016 | $1.64 |
| Document summarization | 20,000 / 1,000 | $0.0076 | $7.60 |
| Agent coding session | 100,000 / 5,000 | $0.04 | $38.00 |
Qwen2.5 72B Instruct vs other Qwen models
| Model | Input /1M | Output /1M | Context |
|---|---|---|---|
| Qwen2.5 72B Instruct | $0.36 | $0.40 | 33K |
| Qwen3.8 27B | $0.45 | $3.20 | 1M |
| Qwen3.8 2.4T A95B | $2 | $6 | 1.0M |
| Qwen3.8 Max | $2 | $6 | 1M |
| Qwen3.7 Flash | $0.03 | $0.13 | 1M |
Frequently asked questions
How much does Qwen2.5 72B Instruct cost per 1M tokens?
According to current pricing data, Qwen2.5 72B Instruct costs $0.36 per 1M input tokens and $0.40 per 1M output tokens. Processing 1M tokens each way costs $0.76.
What does a typical API request to Qwen2.5 72B Instruct cost?
A typical request with 2,000 input tokens and 500 output tokens costs $0.0009. At 1,000 requests per day that is $0.92 daily, or about $27.60 per month.
What is Qwen2.5 72B Instruct's context window?
Qwen2.5 72B Instruct supports a 33K-token context window (32,768 tokens).
Does Qwen2.5 72B Instruct support prompt caching?
No cache-read pricing is published for Qwen2.5 72B Instruct, so every input token is billed at the full $0.36 per 1M rate.
What is a cheaper alternative to Qwen2.5 72B Instruct?
Ling-2.6-flash from Inclusionai is currently the cheapest comparable option at $0.01 per 1M input tokens versus $0.36 for Qwen2.5 72B Instruct — roughly 36x cheaper on input.
Compare all current prices on the live model pricing dashboard, see Qwen2.5 72B Instruct vs Ling-2.6-flash pricing, or run Qwen2.5 72B Instruct head-to-head against other models in the side-by-side comparison playground.
Pricing data via the OpenRouter models API.