GPT 5.4 Mini
OpenAI · text, image → text
GPT-5.4 mini is a faster, more efficient model that inherits the advantages of GPT-5.4 and is specifically optimized for high-volume workloads.
Input$0.75 /M
Output$4.50 /M
← ModelsGPT 5.4 Mini
Qwen3.8 Max Preview
GPT 5.4 Mini vs Qwen3.8 Max Preview
Output tokens cost $4.50 per million on GPT 5.4 Mini and $1.01 per million on Qwen3.8 Max Preview. Input tokens cost $0.75 per million on GPT 5.4 Mini and $0.34 per million on Qwen3.8 Max Preview. Cached input tokens are billed at $0.08 per million on GPT 5.4 Mini and $0.03 per million on Qwen3.8 Max Preview. Context lengths are 400,000 tokens on GPT 5.4 Mini and 983,616 tokens on Qwen3.8 Max Preview. Time to first token (TTFT) measured on AIHubMix is 2.3s on GPT 5.4 Mini and 2.4s on Qwen3.8 Max Preview. Measured output throughput is 99.1 tok/s on GPT 5.4 Mini and 48.1 tok/s on Qwen3.8 Max Preview. On the LMArena coding leaderboard GPT 5.4 Mini scores 1496 and Qwen3.8 Max Preview scores 1520.
GPT 5.4 MiniQwen3.8 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$0.34 /M
Output$1.01 /M
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
GPT 5.4 Mini
Qwen3.8 Max Preview
Input /M
$0.75
$0.34
Output /M
$4.50
$1.01
Cache read /M
$0.08
$0.03
Context length
400,000
983,616
Max output
128,000
131,072
Time to First Token
2.3 s
2.4 s
Throughput
99.1 tok/s
48.1 tok/s
Modalities
textimage
textimage
Supported Parameters
toolsfunction callingstructured outputsweb
toolsfunction callingstructured outputsweblong contextthinking
API Formats
chat_completions · responses · claude_api
Released
March 17, 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.
gpt-5.4-miniqwen3.8-max-preview
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
gpt-5.4-miniqwen3.8-max-preview
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
LMArena Benchmarks
LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.
Text
gpt-5.4-miniqwen3.8-max-preview
1380144015001560
Overall
14481481
Coding
14961520
Math
14401504
Hard prompts
14701506
Instruction following
14351478
Multi-turn
14691496
Creative writing
14041469
Longer query
14481497
Chinese
14781545
English
14511486
Vision
gpt-5.4-miniqwen3.8-max-preview
1220126013001340
Overall
12521302
OCR
12631317
Diagram
12831331
Homework
12931335
WebDev Arena
gpt-5.4-miniqwen3.8-max-preview
13601460156016601760
Overall
13971669
React
13871678
HTML
14231628
Gaming
14211733
Simulations
14081665
Data analytics
13891614
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
GPT 5.4 Mini
$113 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: GPT 5.4 Mini, Qwen3.8 Max Preview?
Qwen3.8 Max Preview: $1.01/M output tokens; GPT 5.4 Mini: $4.50/M. Use the cost calculator above to estimate your own workload.
How do their coding arena scores compare?
Qwen3.8 Max Preview: 1520; GPT 5.4 Mini: 1496 (LMArena coding leaderboard).
Which responds faster?
GPT 5.4 Mini: 2.3s time to first token measured on AIHubMix; see the live performance charts above for how each model behaves across the day.
How large is each context window?
GPT 5.4 Mini accepts 400,000 and Qwen3.8 Max Preview accepts 983,616 input tokens. Maximum output per request is 128,000 tokens on GPT 5.4 Mini and 131,072 tokens on Qwen3.8 Max Preview.
Which one generates tokens faster?
GPT 5.4 Mini at 99.1 tok/s and Qwen3.8 Max Preview at 48.1 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
What inputs and capabilities does each model support?
GPT 5.4 Mini accepts text and image input and supports tool calling, function calling, structured outputs and web search; 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 GPT 5.4 Mini 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