Model specification · DeepSeek
DeepSeek V4 Flash 0423
deepseek/deepseek-v4-flash
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...
SpecificationsReported values
- Context window
- 1.0M
- Maximum output
- 384K
- Architecture
- text->text
- Tokenizer
- DeepSeek
- Knowledge cutoff
- —
- Moderated
- No
- Input modalities
- text
- Output modalities
- text
Full pricingUSD where reported
| Price | Standard |
|---|---|
| Input | $0.089 / M |
| Output | $0.177 / M |
Benchmark indexesReported indexes
- Intelligence
- 24.8
- Coding
- 52
- Agentic
- 27.9
- Design Arena Elo
- 1190
Example workload costsStandard pricing only
| Workload | Input / output | Cache share | Estimated cost |
|---|---|---|---|
| Quick check | 10K / 1K × 1 | 0% | $0.00106 |
| Long analysis | 100K / 4K × 1 | 50% | $0.00603 |
| Workday | 20K / 2K × 1,000 | 30% | $1.70 |
More from DeepSeekAll DeepSeek models
| Model | Context | Input / M | Output / M | Intel. |
|---|---|---|---|---|
| DeepSeek V4 Pro 0813 | 1.0M | $1.05 | $3.15 | 36.3 |
| DeepSeek V4 Flash 0731 | 1.3M | $0.065 | $0.180 | 34.5 |
| DeepSeek V4 Pro 0423 | 1.0M | $0.955 | $1.91 | 30.9 |
| DeepSeek V3.1 Terminus | 164K | $0.270 | $1.00 | 15.4 |
| R1 | 64K | $0.700 | $2.50 | 11.4 |
| DeepSeek V3 0324 | 164K | $0.290 | $1.14 | 9.7 |