Qwen2.5 72B Instruct API Pricing

by qwen · 32K context window ·

$0.120
Input /1M tokens
$0.390
Output /1M tokens
32K
Context window

Explore the cost-effective Qwen2.5 72B Instruct API for your large language model needs. Offered by qwen, this powerful model boasts a 32,768 token context window. Understand the pricing structure: input tokens are priced at $0.12000 per 1 million tokens, while output tokens cost $0.39000 per 1 million tokens, totaling $0.5100 per 1 million tokens. For example, a project processing 100 million input tokens and generating 20 million output tokens monthly would cost approximately $19.80. Ideal for ML engineers comparing LLM API options, Qwen2.5 72B provides a balance of performance and affordability.

Monthly Cost Examples

Assuming 50% input / 50% output token split

UsageMonthly cost
100K tokens/month$0.03
1M tokens/month$0.26
10M tokens/month$2.55
100M tokens/month$25.50

Compare with other models

Qwen2.5 72B Instruct vs OpenAI: GPT-4o →Qwen2.5 72B Instruct vs OpenAI: GPT-4o-mini →Qwen2.5 72B Instruct vs OpenAI: o1 →

Automate your model selection

StormRouter sends each request to the cheapest model that can handle it.
Only use Qwen2.5 72B Instruct when your quality requirements demand it.

Try StormRouter free →

Similar models

Qwen: Qwen3 VL 30B A3B ThinkingFree/1MQwen: Qwen3 VL 235B A22B ThinkingFree/1MQwen: Qwen3 Next 80B A3B Instruct (free)Free/1MQwen: Qwen3 235B A22B Thinking 2507Free/1MQwen: Qwen3 Coder 480B A35B (free)Free/1MQwen: Qwen3 4B (free)Free/1M