// Alibaba (Qwen)
Qwen2.5 72B Instruct
A Alibaba (Qwen) model. 2 prices across 2 channels side by side, each with its source and check date – plus specs, licence, speed and benchmarks.
- Official in/out per 1M
- —
- Lowest (DeepInfra)
- $0.36 / $0.4
- Context
- 33K
- Prices listed
- 2
Prices checked 2026-10-22Official sources linked on every rowNo estimates
01Specs at a glance
Official values first; gaps filled from OpenRouter’s API where the vendor page is silent.
| Vendor | Alibaba (Qwen) |
|---|---|
| Context window | 33K (32,768 tokens) |
| Max output | 16K |
| Input | Text |
| Output | Text |
| Tool calling / JSON | Yes / Yes |
| Weights & licence | Open weights · qwen (custom) · Hugging Face |
| Parameters | 72.7B (from weight files) |
| Released | Sep 19, 2024 |
| Model IDs | qwen/qwen-2.5-72b-instruct · qwen/qwen2.5-vl-72b-instruct |
02Prices on 2 channels
Per 1M tokens, in the currency each source publishes (1 USD = 6.7 CNY for the blended column). Sorted: official first, then cheapest.
| Channel | Source | Input | Output | Cache hit | Blended $ | Context | Notes |
|---|---|---|---|---|---|---|---|
| DeepInfra · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.36 | $0.4 | — | 0.37 | 33K | DeepInfra price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0); not checked against DeepInfra's own page |
| Parasail · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.8 | $1 | $0.4 | 0.85 | 128K | Parasail price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0); not checked against Parasail's own page |
“Official” = vendor pricing page; “Platform” = the platform’s own pricing page; “OpenRouter” = price listed on OpenRouter, not checked on the platform’s site. Click a source tag to open the original page.
03Where you can use it
Derived only from the price sources above. Country restrictions are set by each vendor – check their terms before you sign up.
- Via OpenRouter / provider listed there
DeepInfra · Parasail - Self-host the open weights
GPU / VRAM sizing and build plans→
04Performance
All results →Speed and AA index from Artificial Analysis public leaderboards (not our own tests); benchmark scores from our benchmark library, best result per benchmark.
| Benchmark | Best score | Source | Date |
|---|---|---|---|
| LMArena Text | 1303 | official | 2026-10-08 |
| LMArena Vision | 1121 | official | 2026-10-02 |
| Open LLM Leaderboard v2 | 48.0% | official | 2025-03-13 |
| GPQA Diamond | 49.1% | independent | 2025-01-27 |
| MMLU | 85.0% | paper | 2024-09-19 |
| MMLU-Pro | 71.6% | vendor | 2026-03-11 |
| AIME (OTIS Mock AIME 2024–2025) | 8.1% | independent | 2025-02-25 |
| MATH Level 5 | 63.2% | independent | 2025-01-27 |
| OSWorld (Verified) | 5.0% | official | 2025-07-27 |
| CMMLU | 85.7% | official | 2024-12-06 |
05Price changes we recorded
All price changes →From our daily re-checks of the sources above.
No price change recorded since we started tracking (2026-10-10).
06More from Alibaba (Qwen)
FAQ
How much does the Qwen2.5 72B Instruct API cost?
There is no official pay-as-you-go price in our data. The lowest listed price is $0.36 / $0.4 on DeepInfra.
What is the context window of Qwen2.5 72B Instruct?
33K tokens of context, up to 16K output tokens. Platforms may cap it lower – see the table.
Is Qwen2.5 72B Instruct open source?
Yes, the weights are published on Hugging Face (Qwen/Qwen2.5-72B-Instruct). Licence: qwen (custom).