DeepSeek
DeepSeek V4 Pro 0423: price, context window and ranking
As of 18 October 2026, DeepSeek V4 Pro 0423 from DeepSeek costs $0.2088 per million input tokens and $0.4176 per million output tokens on OpenRouter, with a context window of 1.05M tokens. On the LMArena text leaderboard it ranks 49 with a score of 1,451.2. It is number 35 on OpenRouter by usage, with 0.4% of tokens in the past 7 days.
- Input price
- $0.2088
- Output price
- $0.4176
- Context window
- 1.05M
- LMArena score
- 1,451.2
- Usage share, 7 days
- 0.4%
- Providers
- 16
per 1M tokens
per 1M tokens
tokens
rank 49
rank 35
uptime 98.8%
Specifications
| Field | Value |
|---|---|
| Provider | DeepSeek |
| Input price per 1M tokens | $0.2088 |
| Output price per 1M tokens | $0.4176 |
| Blended price per 1M tokens (3:1) | $0.261 |
| Context window | 1,048,576 |
| Providers serving it | 16 |
| Average uptime, past day | 98.8% |
| LMArena | 1,451.2 (rank 49) |
| Arena score per dollar | 5,560.2 |
| Usage share, 7 days | 0.4% (rank 35) |
| Added to OpenRouter | 2026-04-24 |
| Modality | text->text |
| OpenRouter model ID | deepseek/deepseek-v4-pro |
Price history
- Input
- Output
| Date | Input | Output |
|---|---|---|
| 2026-10-16 | $0.4427 | $0.8853 |
| 2026-10-17 | $0.2088 | $0.4176 |
| 2026-10-18 | $0.2088 | $0.4176 |
Usage rank history
- Usage rank
| Date | Usage rank |
|---|---|
| 2026-10-16 | 34 |
| 2026-10-17 | 35 |
| 2026-10-18 | 35 |
Frequently asked questions
How much does DeepSeek V4 Pro 0423 cost per million tokens?
DeepSeek V4 Pro 0423 costs $0.2088 per million input tokens and $0.4176 per million output tokens on OpenRouter, as of 18 October 2026. At a mix of three parts input to one part output the blended price is $0.261 per million tokens.
What is the context window of DeepSeek V4 Pro 0423?
DeepSeek V4 Pro 0423 has a context window of 1.05M tokens (1,048,576 exactly).
How does DeepSeek V4 Pro 0423 rank on LMArena?
DeepSeek V4 Pro 0423 is ranked 49 on the LMArena text leaderboard with a score of 1,451.2 from 57,594 votes. The listing used is "deepseek-v4-pro".
When was DeepSeek V4 Pro 0423 released?
OpenRouter lists DeepSeek V4 Pro 0423 as added on 24 April 2026.
Who provides DeepSeek V4 Pro 0423?
DeepSeek V4 Pro 0423 is served by 16 providers on OpenRouter, with average uptime of 98.8% over the past day.
Methodology and sources
The catalogue, prices, context lengths and provider counts come from OpenRouter's public Models API. They are fetched every day at 06:00 Istanbul time and stored as a daily snapshot. Weekly changes are calculated by Oesnada by comparing those snapshots; there is no data before 16 October 2026.
Usage shares are calculated from the daily token totals of OpenRouter's Data API: a model's tokens over the past 7 days divided by all tokens in the same period, including the aggregated long tail outside the top 50. Token counts come from each provider's own tokenizer and are not directly comparable across providers. The data is published by OpenRouter under CC BY 4.0. Variants such as ":free" are counted separately, so shares here can differ from OpenRouter's own ranking page.
Quality rankings come from LMArena's text (overall) leaderboard. A model is matched only when its name matches exactly; if a model has several listings, the highest-scoring one is used. "Frontier" means a model in the LMArena top 15.
"Best value" divides the LMArena score by the blended price (three parts input to one part output). Arena scores are not a linear scale, so the ratio is a rough guide. This page is produced automatically.
- OpenRouter Models API
- OpenRouter Rankings (Data API) (CC BY 4.0)
- LMArena leaderboard dataset (CC BY 4.0)
Related Oesnada stories: DeepSeek
- Study: Chinese AI Labs Included Developer Safety Results in Just 3.6% of
The dataset tracked releases from nine prominent labs, spanning tech giants ByteDance, Alibaba, Tencent, and Baidu alongside startups such as DeepSeek, Moonshot, Zhipu, MiniMax, and StepFun.
Importance 94/100 - Hacker Targeting South Korean Banks Used LLMs and ARTEX Tool, Analysis Finds
Investigators discovered open directories containing Claude Code session histories, configuration files, and memory logs, which revealed that the perpetrator relied on ARTEX—an open-source Chinese tool designed for autonomous penetration testing, or simulated cyberattacks used to uncover system weaknesses—paired with large language models.
Importance 94/100
All AI models
Download the data
Cite this page
Oesnada, "DeepSeek V4 Pro 0423: price, context window and ranking", https://oesnada.com/ai-models/deepseek-deepseek-v4-pro, accessed 18 October 2026.