// model_detail
legacy open-weight
Qwen2.5 72B
by Qwen
Previous-gen open-weight model. 72B dense. Superseded by Qwen3.
Context window 128K 128K tokens
Max output 8K 8K tokens
Pricing /1M tok $0.15 in / $0.40 out per 1M tokens (OpenRouter)
Released Sep 19, 2024
// specifications
Specs & capabilities
API details
- API model ID
qwen/qwen2.5-72b-instruct- Internal ID
qwen2-5-72b- Status
- legacy
- Type
- open-weight
Capabilities
- Vision
- No
- Function calling
- 🔧 Yes
- Knowledge cutoff
- 📅 2024-09
Pricing
- Input
- $0.15 / 1M tokens
- Output
- $0.40 / 1M tokens
- Source
- OpenRouter pricing
Lifecycle
- Successor
- Qwen3 235B-A22B
// data_confidence
Data notes
⚠️ Pricing shown via OpenRouter, not first-party
// notes
Additional notes
Previous-gen open-weight flagship
// more_from_qwen
More Qwen models
Qwen3.5 Plus active balanced
Qwen3.5 series balanced model. Text/image/video input. 1M context, faster and cheaper than Qwen3-Max.
Qwen3.5 Flash active fast
Qwen3.5 speed model. 1M context, lowest cost in Qwen lineup.
Qwen3 Max active frontier
Alibaba's flagship Qwen model. 262K context. Supports thinking mode with chain-of-thought. Tiered pricing by context length.
Qwen3 235B-A22B active open-weight
Open-weight MoE Qwen3. 235B total, 22B active params. 128K context.
Qwen3 32B active open-weight
Open-weight dense Qwen3. 32B params, 128K context.
QwQ 32B active reasoning
Open-weight reasoning model. 32B params, chain-of-thought. Budget reasoning option.
// external_links