Context Window
32,768
Input tokens
Full-context input ≈ $0.00
Model Cost Profile
Developer: qwen· Tokenizer: Qwen · Instruct: chatml · Quantization: fp8
Canonical ID: qwen/qwen-2.5-72b-instruct
Pricing updated Apr 25, 2026
Live Pricing
Input: $0.1200
Output: $0.3900
Last synced Apr 25, 2026
Qwen2.5 72B Instruct is designed for advanced natural language processing tasks, making it suitable for applications such as chatbots, content generation, and data analysis. With a context window of 32,768 tokens, this model excels in handling extensive dialogues and complex queries, allowing teams to maintain context over longer interactions. Pricing for the API is competitive, with an input cost of $0.12 per million tokens and an output cost of $0.39 per million tokens, making it a cost-effective choice for organizations requiring scalable language solutions.
Context Window
32,768
Input tokens
Full-context input ≈ $0.00
Max Output
16,384
Completion tokens
Input Price / 1M
$0.1200
Prompt tokens
Output Price / 1M
$0.3900
Completion tokens
Top Benchmark
Pending
No benchmark data yet
Price History
Current Input / 1M
$0.1200
Current Output / 1M
$0.3900
Performance History
Current TPS
0.00
Current Latency
0ms
Uptime
100.0%
| Usage Type | Price / 1M Tokens |
|---|---|
| Input (Prompt) | $0.1200 |
| Output (Completion) | $0.3900 |
Estimate monthly spend for Qwen2.5 72B Instruct based on your workload.
Estimated Monthly Cost
$7.68
25M input + 12M output tokens
Quick links for cost-down decisions before production rollout.