DeepSeek V4 731 Flash
DeepSeek V4 731 Flash is DeepSeek's language model with a 1.3M context window and up to 944K output tokens, available from 17 providers, starting at $0.03 / 1M input and $0.153 / 1M output. An official release of DeepSeek's V4 Flash model with substantially enhanced agentic capabilities including reasoning, tool use, and implicit caching.
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities7/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling✓
Structured Outputs✓
Native JSON Schema✓
Web Search✓
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | Fast | Batch | |||||
|---|---|---|---|---|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | Input $ / 1M | Output $ / 1M | |
| $0.44 | $1.32 | $0.04 | — | — | — | $0.22 | $0.66 | |
| $0.44 | $1.32 | $0.014 | — | — | — | — | — | |
| $0.13 | $0.26 | $0.028 | — | — | — | — | — | |
| $0.44 | $1.32 | $0.014 | — | — | — | — | — | |
| $0.08 | $0.18 | $0.016 | — | — | — | — | — | |
| $0.22 | $0.66 | $0.007 | $0.275 | $0.825 | $0.00875 | — | — | |
| $0.44 | $1.32 | N/A | — | — | — | — | — | |
| $0.14 | $0.28 | N/A | — | — | — | — | — | |
| $0.14 | $0.28 | N/A | — | — | — | — | — | |
| $0.44 | $1.32 | $0.028 | — | — | — | — | — | |
| $0.03 | $0.32 | $0.016 | — | — | — | — | — | |
| $0.13 | $0.26 | $0.028 | — | — | — | — | — | |
| $0.2 | $0.4 | $0.04 | — | — | — | — | — | |
| $0.2 | $0.4 | $0.04 | — | — | — | — | — | |
| $0.4 | $0.8 | $0.08 | — | — | — | — | — | |
| $0.14 | $0.28 | $0.03 | — | — | — | — | — | |
| $0.076 | $0.153 | $0.014 | — | — | — | — | — | |
| $0.13 | $0.28 | $0.07 | — | — | — | — | — | |
Cost Calculator
US Dollar ($)
Preset:
Cheapest Instances to Run It
Cloud GPU instances that can host DeepSeek V4 731 Flash, ranked by cheapest on-demand price. The model needs about 730 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.
All clouds
FP16 (full precision)
US Dollar ($)
Instance | Cloud | GPU | VRAM | Price | Cheapest region | |
|---|---|---|---|---|---|---|
| a3-ultragpu-8g |  GCP | 8× nvidia-h200-141gb | 1128 GB | $13.82/hr | ||
| g7e.48xlarge |  AWS | 8× RTX PRO Server 6000 | 768 GB | $33.14/hr | ||
| g4-standard-384 | GCP | 8× nvidia-rtx-pro-6000 | 768 GB | $36.00/hr | ||