DeepSeek V4 Pro pricing
DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,... Below you will find 5 current rows with input and output dollars per million. Right now the lowest input is $0.435 and the lowest output is $0.870.
Pricing across providers
Use this table to read DeepSeek V4 Pro list prices. We show 5 sources right now. Lowest input in the grid: Tencent. The chart below the table helps when output prices are much higher than input prices.
| Provider | Input / 1M | Output / 1M | Cached input | Batch |
|---|---|---|---|---|
T Tencent | $0.435 | $0.870 | $0.0036 | — |
O Openrouter | $0.435 | $0.870 | — | — |
D Deepseeknative | $0.435 | $0.870 | $0.0036 | — |
A Azure | $1.74 | $3.48 | — | — |
FA Fireworks AI | $1.74 | $3.48 | $0.145 | — |
Input vs output · per provider
Cost calculator
Use this block to stress test DeepSeek V4 Pro cost without a spreadsheet. All estimates come from public list rates in this page.
Provider
0.043500¢ / req
0.043500¢ / req
Model specifications
These fields describe DeepSeek V4 Pro as we store it (source: Deepseek). They sit next to price so buyers can check limits and tools in one place.
- Context window
- 1,048,576 tokens
- Max output
- 384,000 tokens
- Vision (images)
- No
- Tool / function calling
- Yes
- Streaming
- Yes
- Released
- Apr 2026
- Primary provider
- Deepseek
- Model family
- N/A
Compare DeepSeek V4 Pro
Jump into a comparison when you want one table for two models instead of two tabs. 6 curated matches for DeepSeek V4 Pro.
Locked
Compare with
Pick a model on both sides.
Popular DeepSeek V4 Pro comparisons
- DeepSeek V4 Pro vs GPT-4o
DeepSeek V4 Pro 91% cheaper on output
- DeepSeek V4 Pro vs GPT-4o mini
GPT-4o mini 31% cheaper on output
- DeepSeek V4 Pro vs Claude Sonnet 4.6
DeepSeek V4 Pro 94% cheaper on output
- DeepSeek V4 Pro vs Gemini 2.0 Flash
Gemini 2.0 Flash 54% cheaper on output
- DeepSeek V4 Pro vs o3
DeepSeek V4 Pro 89% cheaper on output
- DeepSeek V4 Pro vs Llama 3.1 70B
Compare pricing side by side
Frequently asked questions
Answers pull from the same numbers you see on this page. The short model note from our index: DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...
Also from Deepseek
Other models by Deepseek with live pricing in our catalog.