DeepSeek V4 Flash
DeepSeek V4 Flash is DeepSeek's language model with a 1.0M context window and up to 384K output tokens, available from 4 providers, starting at $0.140 / 1M input and $0.280 / 1M output. An efficiency-optimized Mixture-of-Experts LLM from DeepSeek with 284B total and 13B activated parameters, supporting a 1M-token context window with reasoning and tool-use capabilities.
DeepSeek's language model with a 1.0M context window and up to 384K output tokens, available from 4 providers, starting at $0.140 / 1M input and $0.280 / 1M output. An efficiency-optimized Mixture-of-Experts LLM from DeepSeek with 284B total and 13B activated parameters, supporting a 1M-token context window with reasoning and tool-use capabilities.deepseek-v4-flash |
| Language |
| Active |
| DeepSeek |
| 1.0M tokens |
| 384K tokens |
| ImagePdfText |
| Text |
| default |
| 158B |
| 649 |
| 25,391 |
| 25,391 |
| · 9 days ago |
46.5#31 |
38.7#43 |
0.9#13 |
0.3#17 |
0.8#6 |
0.77s#283 |
0.4#34 |
0.6#65 |
0.4#46 |
0.9#19 |
80.5#158 |
Capabilities
Input3/5
✓
✓
·
·
✓
Output1/5
✓
·
·
·
·
Capabilities6/13
✓
·
✓
·
✓
✓
·
·
·
·
·
✓
✓
Pricing by Provider
| Provider | Standard | Batch | ||||
|---|---|---|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | |
DeepSeek | $0.140 | $0.280 | $0.0028 | $0.070 | $0.140 | $0.0014 |
 Hugging Face | $0.140 | $0.280 | N/A | — | — | — |
 OpenRouter | $0.140 | $0.280 | $0.0028 | — | — | — |
 Vercel AI Gateway | $0.140 | $0.280 | $0.0028 | — | — | — |
Cost Calculator
Preset:
Compares every provider & tier in USD
Other models
| Model | Tier | Released | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|---|
| DeepSeek V4 Pro | Pro | 1.0M | $0.435 | $0.870 |