Qwen2.5 VL 72B Instruct
Qwen · text, image → text
Strong capability in Chinese domain recognition, comparable to ChatGPT-4.0.
Input$2.4 /M
Output$7.2 /M
← ModelsQwen2.5 VL 72B InstructQwen3.8 Max Preview
Qwen2.5 VL 72B Instruct vs Qwen3.8 Max Preview
Compare Qwen2.5 VL 72B Instruct from Qwen and Qwen3.8 Max Preview from Qwen on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the AIHubMix API.
Qwen2.5 VL 72B InstructQwen3.8 Max Preview+ Add model · 2/4
Qwen3.8 Max Preview
Qwen · text, image → text
Qwen 3.8 Max Preview(Qwen3.8-Max-Preview) is the latest-generation foundation model in the Qwen family, packing 2.4T parameters and still evolving. Compared with the previous flagship Qwen 3.7 Max, it delivers major gains in core capabilities like Coding and Cowork (professional productivity), with world-leading performance on complex, long-horizon tasks such as full-stack development, data analysis, and Office workflows. Launch offer: Credits are consumed at just 20% of the standard rate, effectively 5× your usage. Limited time only.
Input$0.338 /M
Output$1.014 /M
Cache read$0.0338 /M
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Qwen2.5 VL 72B Instruct
Qwen3.8 Max Preview
Input /M
$2.4
$0.338
Output /M
$7.2
$1.014
Cache read /M
-
$0.0338
Context length
0
983,616
Max output
0
131,072
Time to First Token
-
2.4 s
Throughput
-
48.1 tok/s
Modalities
textimage
textimage
Supported Parameters
toolsfunction callingstructured outputsweblong contextthinking
API Formats
Released
-
-
Promotional prices show the discounted rate; see each model page for promotion windows.
Activity Past 30 Days
Daily traffic served through AIHubMix — how demand for each model is trending.
qwen2.5-vl-72b-instructqwen3.8-max-preview
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
qwen2.5-vl-72b-instructqwen3.8-max-preview
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
LMArena Benchmarks
LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.
Vision
qwen2.5-vl-72b-instructqwen3.8-max-preview
1100118012601340
Overall
11211300
OCR
13151315
Diagram
13261326
Homework
13341334
Source: LMArena (arena.ai) leaderboard, imported by AIHubMix. Models without published ratings are omitted per chart.
Cost calculator
Estimate your monthly bill for the same workload on each model.
Qwen3.8 Max Preview
$35.49 /mo
Qwen2.5 VL 72B Instruct
$252 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: Qwen2.5 VL 72B Instruct, Qwen3.8 Max Preview?
Qwen3.8 Max Preview: $1.014/M output tokens; Qwen2.5 VL 72B Instruct: $7.2/M. Use the cost calculator above to estimate your own workload.
What inputs and capabilities does each model support?
Qwen2.5 VL 72B Instruct accepts text and image input; Qwen3.8 Max Preview accepts text and image input and supports tool calling, function calling, structured outputs, web search, long context and thinking.
Can I call Qwen2.5 VL 72B Instruct and Qwen3.8 Max Preview with the same API key?
Yes. AIHubMix serves every model on this page behind one OpenAI-compatible endpoint, so switching between them is a one-line change to the model field — no second account, key or SDK.
Popular comparisons
Related model match-ups readers also look at.
AIHubMix