DeepSeek V4 Pro
DeprecatedDeepSeek V4 Pro is DeepSeek's language model with a 1.0M context window and up to 393K output tokens, available from 13 providers, starting at $0.435 / 1M input and $0.87 / 1M output. A large-scale Mixture-of-Experts LLM from DeepSeek with 1.6T total and 49B activated parameters, supporting a 1M-token context window for advanced reasoning and tool-use tasks.
| Benchmarks | |
|---|---|
| Intelligence Index | #20 |
| Coding Index | #25 |
| GPQA | #11 |
| HLE | #23 |
| Time to First Token | #425 |
| SciCode | #44 |
| LCR | #40 |
| Output TPS | #170 |
Capabilities
Input3/5
Text✓
Image✓
Audio·
Video·
PDF✓
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities7/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling✓
Structured Outputs✓
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill✓
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | Batch | ||||
|---|---|---|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | |
| $2.40 | $4.80 | $0.2 | $1.20 | $2.40 | N/A | |
| $1.74 | $3.48 | N/A | — | — | — | |
| $1.93 | $3.83 | $0.165 | — | — | — | |
| $1.30 | $2.60 | $0.1 | — | — | — | |
| $1.32 | $3.96 | $0.044 | $0.66 | $1.98 | $0.022 | |
| $1.74 | $3.48 | $0.145 | — | — | — | |
| $1.60 | $3.20 | N/A | — | — | — | |
| $1.75 | $3.50 | N/A | — | — | — | |
| $1.60 | $3.20 | $0.135 | — | — | — | |
| $1.60 | $3.20 | $0.135 | — | — | — | |
| $0.435 | $0.87 | $0.00363 | — | — | — | |
| $1.74 | $3.48 | $0.2 | — | — | — | |
| $0.66 | $1.98 | $0.022 | — | — | — | |
| $1.15 | $2.55 | $0.2 | — | — | — | |
Cost Calculator
US Dollar ($)
Preset:
Cheapest Instances to Run It
Cloud GPU instances that can host DeepSeek V4 Pro, ranked by cheapest on-demand price. The model needs about 2068 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 |
|---|---|---|---|---|---|
| p6-b300.48xlarge |  AWS | 8× B300 | 2149 GB | $142.42/hr |
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| DeepSeek V4 Pro | 1.0M | $0.660 | $1.98 | Available | |
| DeepSeek V4 Pro | — | — | — | — | Available |
| DeepSeek V4 Pro | 1.0M | $0.435 | $0.870 | Current | |
| DeepSeek V4 Pro US | — | — | $2.40 | $4.80 | Available |
Other Models
| Model | Tier | Released | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|---|
| DeepSeek V4.731 Flash US | Flash | — | — | $0.424 | $1.27 |
| DeepSeek V4 420 Flash | Flash | — | — | — | — |
| DeepSeek V4 Flash Vision Exp | Flash | 1.0M | $0.220 | $0.660 | |
| DeepSeek V4 Flash | Flash | 1.3M | $0.030 | $0.160 | |
| DeepSeek V4 Flash Vision | Flash | — | — | — | — |
| DeepSeek V4 Flash Thinking | Flash | — | 200K | $0.250 | $1.75 |
| DeepSeek V4 Flash US | Flash | — | — | $0.200 | $0.400 |