Qwen2.5 72B Instruct pricing
Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding… Qwen2.5 72B Instruct from Alibaba (Qwen) costs $0.360 per 1M input tokens and $0.400 per 1M output tokens. Context window 32,768 tokens.
API id qwen-2.5-72b-instruct · Alibaba (Qwen) · source · updated 2026-09-25 · general-purpose
$0.360
Input / 1M tokens
$0.400
Output / 1M tokens
—
Cached input / 1M
33K
Context window
Qwen2.5 72B Instruct specifications
- Provider
- Alibaba (Qwen)
- API id
qwen-2.5-72b-instruct- Model type
- general-purpose
- Context window
- 33K tokens
- Max output
- 16K tokens
- Currency
- USD
- Price source
- Provider API
- Last checked
- 2026-09-25
Qwen2.5 72B Instruct across providers
The same model, priced by every seller we track. Ranked by the cost of 1M input + 1M output tokens, standard tier; savings measured against buying from the vendor directly.
| Provider | Input /1M | Cached /1M | Output /1M | 1M in + 1M out | vs vendor |
|---|---|---|---|---|---|
| $0.360 | — | $0.400 | $0.76 | — | |
OpenRouterHost | $0.360 | — | $0.400 | $0.76 | — |
What Qwen2.5 72B Instruct costs in practice
| Workload | Input tokens | Output tokens | Estimated cost |
|---|---|---|---|
| Short chat turn | 1,000 | 500 | $0.0006 |
| Document summary | 50,000 | 2,000 | $0.02 |
| 1M tokens in, 200K out | 1,000,000 | 200,000 | $0.44 |
Estimates use the standard tier and ignore caching discounts, so real bills with repeated prompt prefixes are typically lower.
Common questions
- How much does Qwen2.5 72B Instruct cost per 1M tokens?
- Qwen2.5 72B Instruct costs $0.360 per 1M input tokens and $0.400 per 1M output tokens on the standard tier.
- What is Qwen2.5 72B Instruct's context window?
- Qwen2.5 72B Instruct accepts up to 32,768 tokens in a single request, and can return up to 16,384 output tokens.
- Is there a cheaper Qwen model than Qwen2.5 72B Instruct?
- Yes. Qwen2.5 7B Instruct is $0.100 per 1M input tokens versus $0.360 for Qwen2.5 72B Instruct, with a 32,768 token context window.
- Where does this Qwen2.5 72B Instruct price come from?
- From the OpenRouter catalogue, because Alibaba (Qwen) does not publish machine-readable pricing. OpenRouter is a reseller, so its rate can differ from Alibaba (Qwen)'s own — verify before committing spend.
Head-to-head comparisons
Other Qwen models
- Qwen3.8 Max Prime $4.00
- Qwen3.8 Omni Flash $0.150
- Qwen3.8 Max (0902) $2.00
- Qwen3.8 Flash $0.150
- Qwen3.8 27B $0.420
- Qwen3.8 2.4T A95B $2.00
- Qwen3.7 Flash $0.030
- Qwen3.7 Plus $0.320
- Qwen3.7 Max $1.48
- Qwen3.5 Plus 2026-04-20 $0.300
- Qwen3.6 Flash $0.188
- Qwen3.6 35B A3B $0.150
- Qwen3.6 Max Preview $1.03
- Qwen3.6 27B $0.320
- Qwen3.6 Plus $0.325
- Qwen3.5-9B $0.100