DeepSeek V4 Pro 0423
DeepSeek· released 24 Apr 2026
deepseek/deepseek-v4-pro- Input / 1M tokens
- $0.209
- Output / 1M tokens
- $0.418
Longest answer: 384K tokens
About
DeepSeek V4 Pro 0423 is a text-input, text-output model from DeepSeek, with open weights and tool support. It is a large-scale Mixture-of-Experts model with 1.6T total parameters and 49B activated parameters. Its context window is 1,048,576 tokens, and its maximum output is 384,000 tokens. The listed capabilities include reasoning, and its design summary identifies advanced reasoning and coding as intended uses. Input costs 0.2088 USD per 1 million tokens, while output costs 0.4176 USD per 1 million tokens. The model identifier is deepseek/deepseek-v4-pro, and the Hugging Face identifier is deepseek-ai/DeepSeek-V4-Pro. It was released on 2026-04-24. For builders evaluating model fit, the listed facts establish its text modality, weights availability, tool support, long context, output ceiling, and separate input and output token prices.
Who it is for
It suits builders evaluating a text model for reasoning or coding workflows that may need a large context window, tool support, and open weights.
What is good
- Open weights are available.
- Supports tool use.
- Context window is 1,048,576 tokens.
- Maximum output is 384,000 tokens.
- Input and output token prices are listed separately.
What to know first
- Only text inputs and outputs are listed.
- Output tokens cost more than input tokens.
Verdict
DeepSeek V4 Pro 0423 combines a 1M-token context window with a 384,000-token maximum output and tool support. Its listed input price is 0.2088 USD per 1 million tokens and output price is 0.4176 USD per 1 million tokens.
Details
- Lab
- DeepSeekopenrouter.ai · 3 Oct 2026
- Context
- 1,049Kopenrouter.ai · 3 Oct 2026
- Input price
- $0.209 / 1Mopenrouter.ai · 3 Oct 2026
- Output price
- $0.418 / 1Mopenrouter.ai · 3 Oct 2026
- Max output
- 384,000 tokensopenrouter.ai · 3 Oct 2026
- Inputs
- textopenrouter.ai · 3 Oct 2026
- Open weights
- Yesopenrouter.ai · 3 Oct 2026
More newest models
See the list
Listed on Inferse
- Newest Models in 2026466 listed
- Longest-Context Models in 2026466 listed
- Cheapest Language Models in 2026437 listed
- Models with Tool Calling in 2026395 listed
- Reasoning Models in 2026332 listed
- Open-Weight Models in 2026178 listed
- DeepSeek Models: Pricing per 1M Tokens and Context (2026)18 listed
Sources
- openrouter.ai/deepseek/deepseek-v4-pro· checked 3 Oct 2026