Qwen2.5 72B Instruct
The Qwen2.5 72B Instruct model is a text-based AI tool that supports input and output in multiple modalities, with a maximum context length of 32,768 tokens. It also provides tools for users, but lacks reasoning capabilities. For those seeking a high-capacity text processing solution at an affordable price point, this model may be worth considering. Its blended benchmark score of 31.1 is based on performance across one independent benchmark, and its pricing structure of $0.36 per million input tokens and $0.4 per million output tokens could be competitive for users who need to process large volumes of text data.
Benchmark results
Independent, published benchmarks. Blended score 31.1 across 1 benchmark, last refreshed 2026-09-23. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| EQ-Bench | emotional understanding in dialogue | 33.5 |
- Model ID
- qwen/qwen-2.5-72b-instruct
- Vendor
- qwen
- Released
- September 2024
- Tokenizer
- Qwen
- Input Modalities
- text
- Output Modalities
- text
- Max Output
- 16,384 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- not supported
- Vision
- text only
- Audio
- no
- Moderated
- no
What it costs in practice
Computed from the current $0.36/M input and $0.40/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | $0.01 |
| Classify 1,000 customer emails | 500k in / 50k out | $0.20 |
| A month of a busy support chatbot | 5M in / 2M out | $2.60 |
Price & spec history
Tracked daily by PicksByModel since 2026-07-17.
| Date | Input /M | Output /M | Context |
|---|---|---|---|
| 2026-07-22 | $0.36 | $0.40 | 32,768 |
| 2026-07-17 | $0.36 | $0.40 | 131,072 |
Similar models
Qwen: Qwen2.5 7B Instruct
Qwen: Qwen2.5 VL 72B Instruct
Qwen: Qwen3 30B A3B Thinking 2507
Qwen2.5 Coder 32B Instruct
Qwen: Qwen3 235B A22B Thinking 2507
Qwen: Qwen3 235B A22B
Quick answers
- How much does Qwen2.5 72B Instruct cost?
- $0.36 per million input tokens and $0.40 per million output tokens.
- What is Qwen2.5 72B Instruct's context window?
- 32,768 tokens, roughly 49 pages of text in a single request.
- Does Qwen2.5 72B Instruct support tool calling?
- It supports tool calling, structured output.
- Can Qwen2.5 72B Instruct process images?
- No, it is text-only on the input side.