Qwen/Qwen2.5-72B-Instruct
Qwen · → text
Input$0.8 /M
Output$0.8 /M
← ModelsQwen/Qwen2.5-72B-InstructQwen3.8 Max
Qwen/Qwen2.5-72B-Instruct vs Qwen3.8 Max
Compare Qwen/Qwen2.5-72B-Instruct from Qwen and Qwen3.8 Max 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.
Qwen/Qwen2.5-72B-InstructQwen3.8 Max+ Add model · 2/4
Qwen3.8 Max
Qwen · text, image, video → text
Qwen3.8-Max is Alibaba Cloud Tongyi Qianwen's next-generation flagship large language model, featuring a mixture-of-experts (MoE) architecture with 2.4 trillion parameters. It achieves another breakthrough in encoding depth, enabling it to handle more complex engineering-grade projects and long-term autonomous development; collaborative agent capabilities are significantly enhanced, performing more confidently in multi-tool orchestration and end-to-end delivery; visual understanding is comprehensively improved, with more sensitive and accurate chart reasoning, document parsing, and multimodal perception. Continuing the 1-million-context window, reasoning modes, and a complete tool ecosystem, it continues to evolve at a higher level of intelligence.
Input$1.69 /M
Output$5.07 /M
Cache read$0.169 /M
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Qwen/Qwen2.5-72B-Instruct
Qwen3.8 Max
Input /M
$0.8
$1.69
Output /M
$0.8
$5.07
Cache read /M
-
$0.169
Context length
0
1,000,000
Max output
0
131,072
Time to First Token
-
12.5 s
Throughput
-
28.4 tok/s
Modalities
textimagevideo
Supported Parameters
toolsfunction callingstructured outputsweblong contextthinking
API Formats
Released
-
August 3, 2026
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.
Qwen/Qwen2.5-72B-Instructqwen3.8-max
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
Qwen/Qwen2.5-72B-Instructqwen3.8-max
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
LMArena Benchmarks
LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.
Text
Qwen/Qwen2.5-72B-Instructqwen3.8-max
1220130013801460
Overall
13031482
Coding
13561356
Math
12971297
Hard prompts
13181318
Instruction following
12921292
Multi-turn
12991299
Creative writing
12541254
Longer query
13171317
Chinese
13211321
English
13161316
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.
Qwen/Qwen2.5-72B-Instruct
$60.00 /mo
Qwen3.8 Max
$177 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: Qwen/Qwen2.5-72B-Instruct, Qwen3.8 Max?
Qwen/Qwen2.5-72B-Instruct: $0.8/M output tokens; Qwen3.8 Max: $5.07/M. Use the cost calculator above to estimate your own workload.
Can I call Qwen/Qwen2.5-72B-Instruct and Qwen3.8 Max 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.
