Model specification · DeepSeek
DeepSeek V3 0324
deepseek/deepseek-chat-v3-0324
DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...
SpecificationsReported values
- Context window
- 164K
- Maximum output
- 147K
- Architecture
- text->text
- Tokenizer
- DeepSeek
- Knowledge cutoff
- 2024-07-31
- Moderated
- No
- Input modalities
- text
- Output modalities
- text
Full pricingUSD where reported
| Price | Standard |
|---|---|
| Input | $0.250 / M |
| Output | $1.00 / M |
Benchmark indexesReported indexes
- Intelligence
- 9.7
- Coding
- 21.2
- Agentic
- 0.8
- Design Arena Elo
- —
Example workload costsStandard pricing only
| Workload | Input / output | Cache share | Estimated cost |
|---|---|---|---|
| Quick check | 10K / 1K × 1 | 0% | $0.00350 |
| Long analysis | 100K / 4K × 1 | 50% | $0.029 |
| Workday | 20K / 2K × 1,000 | 30% | $7.00 |
More from DeepSeekAll DeepSeek models
| Model | Context | Input / M | Output / M | Intel. |
|---|---|---|---|---|
| DeepSeek V4.1 Flash | 1.0M | $0.150 | $0.600 | 39.5 |
| DeepSeek V4 Pro 0813 | 1.0M | $0.578 | $1.73 | 36.3 |
| DeepSeek V4 Flash 0731 | 1.3M | $0.040 | $0.080 | 34.5 |
| DeepSeek V4 Pro 0423 | 1.0M | $0.442 | $0.885 | 30.9 |
| DeepSeek V4 Flash 0423 | 1.0M | $0.044 | $0.088 | 24.8 |
| DeepSeek V3.1 Terminus | 164K | $0.270 | $1.00 | 15.4 |
| R1 | 64K | $0.700 | $2.50 | 11.4 |