DeepSeek V4 Pro 0423 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 15 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 0423 list prices. We show 15 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 |
|---|---|---|---|---|
A Aihubmix | $1.69 | $3.38 | $0.140 | — |
AC Alibaba Cloud | $2.40 | $4.80 | $0.200 | — |
A Azure | $1.74 | $3.48 | $0.145 | — |
B Baseten | $1.74 | $3.48 | $0.145 | — |
D DeepInfra | $1.30 | $2.60 | $0.100 | — |
FA Fireworks AI | $1.20 | $1.20 | $0.600 | — |
N Nebius | $1.75 | $3.50 | — | — |
N Novita | $1.60 | $3.20 | $0.135 | — |
O Openrouter | $0.783 | $1.57 | — | — |
QA Qwen Ai Platform | $2.40 | $4.80 | $0.200 | — |
Q Qwencloud | $2.40 | $4.80 | $0.200 | — |
T Tencent | $0.435 | $0.870 | $0.0036 | — |
TA Together AI | $1.74 | $3.48 | $0.200 | — |
W Wandb | $1.15 | $2.55 | $0.200 | — |
D Deepseeknative | $1.32 | $3.96 | $0.044 | — |
Input vs output · per provider
Pricing history
These entries are only for the primary native listing of DeepSeek V4 Pro 0423, not every reseller row above. The native listing moved from $0.435 in and $0.870 out to $1.32 in and $3.96 out in the latest window.
Since Aug 21, 2026
$1.32 in · $3.96 out(current listing)
Output rate +355% vs previous period
Jun 21, 2026 → Aug 21, 2026
$0.435 in · $0.870 out
Cost calculator
Use this block to stress test DeepSeek V4 Pro 0423 cost without a spreadsheet. All estimates come from public list rates in this page.
Provider
0.169000¢ / req
0.169000¢ / req
Model specifications
These fields describe DeepSeek V4 Pro 0423 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 0423
Jump into a comparison when you want one table for two models instead of two tabs. 6 curated matches for DeepSeek V4 Pro 0423.
Locked
Compare with
Pick a model on both sides.
Popular DeepSeek V4 Pro 0423 comparisons
- DeepSeek V4 Pro 0423 vs GPT-4o
DeepSeek V4 Pro 0423 60% cheaper on output
- DeepSeek V4 Pro 0423 vs Claude Sonnet 4.6
DeepSeek V4 Pro 0423 73% cheaper on output
- DeepSeek V4 Pro 0423 vs Gemini 2.0 Flash
Gemini 2.0 Flash 89% cheaper on output
- DeepSeek V4 Pro 0423 vs Llama 3.1 70B
Compare pricing side by side
- DeepSeek V4 Pro 0423 vs Mistral 7B
Mistral 7B 93% cheaper on output
- DeepSeek V4 Pro 0423 vs GLM 4.7
GLM 4.7 44% cheaper on output
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,...
Related models
Models close to DeepSeek V4 Pro 0423 by family, provider, and context window — each with live pricing in our catalog.