// model hub
DeepSeek V4 Pro
DeepSeek V4 Pro is an open model from DeepSeek, released in July 2026, with strong performance in code and mathematics. It offers a 1,048,576 token context window at $0.955 per million input tokens and $1.911 per million output tokens.
Pricing
| model | input / 1M | output / 1M | context |
|---|---|---|---|
| DeepSeek V4 Pro | $0.955 | $1.911 | 1,048,576 |
Rates come from the OpenRouter price list and are checked daily (prices updated 2026-11-11)
Comparison
| model | input / 1M | output / 1M | context |
|---|---|---|---|
| DeepSeek V4 Pro | $0.955 | $1.911 | 1,048,576 |
| DeepSeek V4 Flash | $0.043 | $0.3 | 1,048,576 |
| Gemini 3.7 Flash | $0.75 | $3.75 | 1,048,576 |
| Qwen 3.8 2.4T | $2 | $6 | 1,048,576 |
| GPT-5.6 Luna | $0.2 | $1.2 | 1,050,000 |
Among the models in this comparison, DeepSeek V4 Flash has the lowest output price at $0.3 per million tokens, while Qwen 3.8 2.4T is the most expensive at $6 per million output tokens.
Articles about DeepSeek V4 Pro
No articles about this model have been published yet.
Frequently Asked Questions
- What does DeepSeek V4 Pro cost?
- DeepSeek V4 Pro costs $0.955 per million input tokens and $1.911 per million output tokens. These rates were recorded on 2026-09-09. Pricing can differ significantly depending on which provider you use.
- How does DeepSeek V4 Pro compare to GPT-5.6 Luna?
- DeepSeek V4 Pro costs $0.955 per million input tokens and $1.911 per million output tokens, while GPT-5.6 Luna costs $0.2 input and $1.2 output. Both models offer similar context windows of around 1,048,576 tokens. GPT-5.6 Luna is cheaper, but DeepSeek V4 Pro is an open model with strong coding and math capabilities.
- What is the context window of DeepSeek V4 Pro?
- DeepSeek V4 Pro supports a context window of 1,048,576 tokens. This matches the context length of Gemini 3.7 Flash and Qwen 3.8 2.4T in the same comparison snapshot.
- Is DeepSeek V4 Pro an open model?
- Yes, DeepSeek V4 Pro is an open model. It is known for strong performance in code and mathematics tasks. Being open allows for greater transparency and flexibility in deployment.
- How does DeepSeek V4 Pro compare to DeepSeek V4 Flash?
- DeepSeek V4 Pro costs $0.955 per million input tokens and $1.911 per million output tokens, while DeepSeek V4 Flash costs $0.043 and $0.3. On output, DeepSeek V4 Flash is the cheaper of the two. Context window: DeepSeek V4 Pro 1,048,576 tokens, DeepSeek V4 Flash 1,048,576 tokens (OpenRouter rates, updated 2026-11-11).