GPT 5.4 Nano
OpenAI · text, image → text
GPT-5.4 nano is designed for tasks where speed and cost are most important, such as classification, data extraction, ranking, and sub-agent scenarios.
Input$0.20 /M
Output$1.25 /M
← ModelsGPT 5.4 Nano
Qwen3.8 Max Preview
GPT 5.4 Nano vs Qwen3.8 Max Preview
Output tokens cost $1.25 per million on GPT 5.4 Nano and $1.01 per million on Qwen3.8 Max Preview. Input tokens cost $0.20 per million on GPT 5.4 Nano and $0.34 per million on Qwen3.8 Max Preview. Cached input tokens are billed at $0.02 per million on GPT 5.4 Nano and $0.03 per million on Qwen3.8 Max Preview. Context lengths are 400,000 tokens on GPT 5.4 Nano and 983,616 tokens on Qwen3.8 Max Preview. Time to first token (TTFT) measured on AIHubMix is 1.4s on GPT 5.4 Nano and 2.4s on Qwen3.8 Max Preview. Measured output throughput is 130.1 tok/s on GPT 5.4 Nano and 48.1 tok/s on Qwen3.8 Max Preview. On the LMArena coding leaderboard GPT 5.4 Nano scores 1460 and Qwen3.8 Max Preview scores 1520.
GPT 5.4 NanoQwen3.8 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 Nano
Qwen3.8 Max Preview
Input /M
$0.20
$0.34
Output /M
$1.25
$1.01
Cache read /M
$0.02
$0.03
Context length
400,000
983,616
Max output
128,000
131,072
Time to First Token
1.4 s
2.4 s
Throughput
130.1 tok/s
48.1 tok/s
Modalities
textimage
textimage
Supported Parameters
toolsfunction callingstructured outputsthinkingweb
toolsfunction callingstructured outputsweblong contextthinking
API Formats
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-nanoqwen3.8-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-nanoqwen3.8-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-nanoqwen3.8-max-preview
1320140014801560
Overall
14021481
Coding
14601520
Math
14231504
Hard prompts
14211506
Instruction following
13881478
Multi-turn
14141496
Creative writing
13381469
Longer query
14041497
Chinese
14221545
English
14141486
Vision
gpt-5.4-nanoqwen3.8-max-preview
1180124013001360
Overall
12011302
OCR
12151317
Diagram
12281331
Homework
12341335
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.
GPT 5.4 Nano
$30.75 /mo
Qwen3.8 Max Preview
$35.49 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: GPT 5.4 Nano, Qwen3.8 Max Preview?
Qwen3.8 Max Preview: $1.01/M output tokens; GPT 5.4 Nano: $1.25/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 Nano: 1460 (LMArena coding leaderboard).
Which responds faster?
GPT 5.4 Nano: 1.4s 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 Nano 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 Nano and 131,072 tokens on Qwen3.8 Max Preview.
Which one generates tokens faster?
GPT 5.4 Nano at 130.1 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 Nano accepts text and image input and supports tool calling, function calling, structured outputs, thinking 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 Nano 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