V4 Flash 0423
DeepSeek · released Apr 24, 2026
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
Specification
- Context window
- 1.05M
- Max output
- 944K
- Knowledge cutoff
- Not stated
- Parameters
- 290.9B
- Licence
- mit
- Serving providers
- 16
- Moderated
- No
- Uptime
- 100.0%
Intelligence
34.3
87th percentile
Coding
69.1
Coding Index
Agentic
26.3
Agentic Index
Output speed
102 t/s
Median across providers
Latency
567ms
Time to first token
Cost per task
$0.02
Estimated
Benchmarks
Where the score comes from
The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.
Evaluation scores
Percentage correct · higher is better
- GPQA Diamond90.8%
- AA-LCR (long context)79.7%
- SciCode50.3%
- τ²-bench (Telecom)39.4%
- Humanity's Last Exam38.6%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| GPQA Diamond | 90.8% |
| AA-LCR (long context) | 79.7% |
| SciCode | 50.3% |
| τ²-bench (Telecom) | 39.4% |
| Humanity's Last Exam | 38.6% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- V4 Flash 0423DeepSeek34.3
- V4 Flash 0731DeepSeek34.3
- Gemini 3.6 FlashGoogle34.0
- KAT-Coder-Pro V2KwaiPilot33.9
- Qwen3.8 27BQwen33.7
- Muse Spark 1.1Meta33.7
- GLM 5.2Z.ai33.7
- Gemini 3.5 FlashGoogle32.6
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| V4 Flash 0423 | 34.3 |
| V4 Flash 0731 | 34.3 |
| Gemini 3.6 Flash | 34.0 |
| KAT-Coder-Pro V2 | 33.9 |
| Qwen3.8 27B | 33.7 |
| Muse Spark 1.1 | 33.7 |
| GLM 5.2 | 33.7 |
| Gemini 3.5 Flash | 32.6 |
Percentile among all indexed models
Pricing
What it costs to run
List prices per million tokens, plus what one representative task works out to.
List price
- Input / 1M tokens
- $0.091
- Output / 1M tokens
- $0.182
- Cached input / 1M
- $0.018
- Blended 3:1
- $0.114
One task, estimated
$0.02
- Input tokens
- 50,000
- Output tokens
- 80,000
- Profile
- Reasoning
Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).
Serving providers
- OpenInference
- Relace
- StreamLake
- DeepInfra
- GMICloud
- Venice
- DigitalOcean
- SiliconFlow
- Baidu
- AtlasCloud
- Parasail
- Alibaba
- Mancer 2
- Azure
- Cloudflare
- Wafer
Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.
Arena
Head-to-head generation quality
Elo from pairwise judgements, broken out by the kind of thing the model was asked to build.
- Overall Elo
- 1,209
- Win rate
- 49.1%
- Strongest at
- Websites
- Tournaments
- 13,461
Elo by category
Dot position on a 1,125–1,225 scale · Elo has no meaningful zero
- 1,209
- 1,200
- 1,189
- 1,166
- 1,153
- 1,128
Agent categories (full-stack apps, mobile apps) are only scored for models tested in agent harnesses.
View as table
| Category | Elo | Win rate |
|---|---|---|
| Websites | 1209 | 49.1% |
| Game development | 1200 | 50.2% |
| 3D scenes | 1189 | 49.3% |
| UI components | 1166 | 44.7% |
| SVG | 1153 | 48.4% |
| Data visualisation | 1128 | 40.7% |