All models
Alibaba (Qwen)
Qwen2.5 VL 72B Instruct fastruns locally
alibaba/qwen2-5-vl-72b
Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.
Input / 1M
$0.80
USD per million tokens
Output / 1M
$1.00
USD per million tokens
Est. cost / token
$0.00000085
$0.85 per 1M, 3:1 mix
Context window
128K
max output 115K
Major features
VisionOpen weightsCachingJSON schema
Task suitability (heuristic 1–5, not a benchmark)
- coding3
- reasoning2
- math2
- summarization4
- extraction4
- classification4
- chat3
- creative3
- translation4
- vision3
- long context3
- agentic1
Run it locally
Will it run on my machine? →ollama run qwen2.5:72b| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 35.6 GB |
| Q3_K_M | fair | 41 GB |
| Q4_K_Mrecommended | good | 50.4 GB |
| Q5_K_M | very good | 58.1 GB |
| Q6_K | excellent | 66.5 GB |
| Q8_0 | near-lossless | 85.2 GB |
| F16 | lossless | 157 GB |
Estimates.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.80 | $1.00 | $0.40 | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.80
- Output
- $1.00
- Cached input
- $0.40
- Blended (3:1)
- $0.85
Details
- Company
- Alibaba (Qwen)
- Version
- 2.5
- Family
- Qwen
- Released
- 2025-02-01
- Parameters
- 73.4B
- Max output
- 115K
- Open weights
- Yes
- Inputs
- image, text
- Last synced
- 25 min ago