// head_to_head
DeepSeek V4 Flash 0423 vs GPT-5.4 Mini
Published LiveBench scores across all seven categories, live list pricing, context windows, and the measured cost of a point of capability — for both models, side by side.
Effectively the same quality — DeepSeek V4 Flash 0423 is the cheaper way to get it.
The two are within 0.9 points overall, which is inside the range that effort settings alone move a LiveBench score, so treat them as quality-equivalent. DeepSeek V4 Flash 0423 lists 18× cheaper per blended million tokens. When quality ties, cost is the whole decision. DeepSeek V4 Flash 0423 also leads on measured cost per point of capability, at $0.0083 per point.
deepseek
DeepSeek V4 Flash 0423
- Blended / 1M
- $0.096
- Context
- 1.0M
- Released
- Apr 24, 2026
- Overall score
- 65.5
openai
GPT-5.4 Mini
- Blended / 1M
- $1.69
- Context
- 400K
- Released
- Mar 17, 2026
- Overall score
- 66.4
Specs and pricing
| Metric | DeepSeek V4 Flash 0423 | GPT-5.4 Mini |
|---|---|---|
| LiveBench overall Mean of the seven LiveBench category scores, 0–100. Higher is better. | 65.5 | 66.4 |
| Cost per point Measured benchmark spend divided by overall score — dollars per point of capability. | $0.0083win | $0.1871 |
| Blended price / 1M 3:1 input:output mix, the usual shape of production traffic. | $0.096win | $1.69 |
| Input price / 1M | $0.077win | $0.750 |
| Output price / 1M | $0.154win | $4.50 |
| Cached input / 1M Price of an input token served from the prompt cache, where the provider publishes one. | $0.015win | $0.075 |
| Context window | 1.0Mwin | 400K |
| Max output tokens | 384Kwin | 128K |
Benchmarks by category
An overall score averages away the thing you probably care about. These are the seven LiveBench categories scored separately — DeepSeek V4 Flash 0423 on top, GPT-5.4 Mini below, both out of 100.
What each one costs to run
Per-token prices are hard to feel. These are monthly list costs for both models across five workload shapes, using each provider's published cached-input rate where there is one.
| Workload | DeepSeek V4 Flash 0423 | GPT-5.4 Mini |
|---|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $26.32/mo | $491.40/mo |
| RAG assistant 8K in / 600 out × 100K requests | $46.12/mo | $600.00/mo |
| Coding agent 40K in / 4K out × 20K requests | $39.35/mo | $582.00/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $85.31/mo | $1053.75/mo |
| Bulk classification 500 in / 20 out × 5M requests | $176.78/mo | $1987.50/mo |
Which should you pick?
You are running this at volume
DeepSeek V4 Flash 0423
Lowest measured cost per point of capability at $0.0083 per point — the gap compounds with every request.
The workload is coding or agentic work
GPT-5.4 Mini
Leads on agentic coding — 41.7 against 37.6.
You need to fit large documents in one call
DeepSeek V4 Flash 0423
Wider context window — 1.0M against 400K.
DeepSeek V4 Flash 0423 vs GPT-5.4 Mini FAQ
Which is better, DeepSeek V4 Flash 0423 or GPT-5.4 Mini?
Effectively the same quality — DeepSeek V4 Flash 0423 is the cheaper way to get it. The two are within 0.9 points overall, which is inside the range that effort settings alone move a LiveBench score, so treat them as quality-equivalent. DeepSeek V4 Flash 0423 lists 18× cheaper per blended million tokens. When quality ties, cost is the whole decision. DeepSeek V4 Flash 0423 also leads on measured cost per point of capability, at $0.0083 per point.
Is DeepSeek V4 Flash 0423 cheaper than GPT-5.4 Mini?
DeepSeek V4 Flash 0423 is cheaper. On a 3:1 input:output blend, DeepSeek V4 Flash 0423 lists at $0.096 per million tokens and GPT-5.4 Mini at $1.69 — DeepSeek V4 Flash 0423 is 18× cheaper. Input and output are priced separately — DeepSeek V4 Flash 0423 charges $0.077 in and $0.154 out, GPT-5.4 Mini charges $0.750 and $4.50 — so the model that looks cheaper flips depending on how output-heavy your workload is.
DeepSeek V4 Flash 0423 vs GPT-5.4 Mini: which scores higher on benchmarks?
DeepSeek V4 Flash 0423 scores 65.5 and GPT-5.4 Mini scores 66.4 overall on LiveBench, the mean of its seven categories. That gap is inside the range that effort settings alone move a score, so treat them as equivalent on published quality. Category scores differ from the overall figure — a model can lead on reasoning and trail on coding, which the per-category table above breaks out.
Which gives better value for money, DeepSeek V4 Flash 0423 or GPT-5.4 Mini?
DeepSeek V4 Flash 0423. Cost per point divides the measured dollars LiveBench spent running the benchmark by the score it earned, so it captures something token pricing misses: a reasoning model can emit many times more tokens than its per-token rate suggests. DeepSeek V4 Flash 0423 works out at $0.0083 per point and GPT-5.4 Mini at $0.1871.
Does DeepSeek V4 Flash 0423 or GPT-5.4 Mini have a bigger context window?
DeepSeek V4 Flash 0423 has the larger context window: 1.0M for DeepSeek V4 Flash 0423 against 400K for GPT-5.4 Mini. Note that a window you can fill is not a window you should fill — retrieval quality usually degrades well before the limit, and you pay for every token you put in it.
Do DeepSeek V4 Flash 0423 and GPT-5.4 Mini support prompt caching?
Both publish a cached-input rate: $0.015 per million for DeepSeek V4 Flash 0423 and $0.075 for GPT-5.4 Mini, against full input rates of $0.077 and $0.750. On a workload with a long stable prefix — a system prompt, a tool schema, a retrieved corpus — that changes the economics more than the headline price does.
Related comparisons
How these numbers are produced
- Price — provider list price from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
- Scores — LiveBench release 2026-06-25, using their own category map. Each model shows its strongest published run. A blank means “not evaluated”, never “bad”.
- Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
- “Win” — awarded only past a threshold: one full point on a benchmark score, 10% on a price, 25% on a context window. Anything tighter reports as a tie, because effort settings alone move a LiveBench score by more than that.
Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.