API model · 1 comparison
DeepSeek V4 Pro 0813 compared
DeepSeek V4 Pro 0813 costs $0.11 per million input tokens and $4.44 per million output tokens and reads up to 1,048,576 tokens in one request. Here it is compared with DeepSeek V4.1 Flash. Pick a matchup for the full side-by-side, a monthly cost calculator and our verdict.
Prices checked 13 November 2026 from the OpenRouter API.
DeepSeek V4 Pro 0813 at a glance
- Input / 1M tokens
- $0.11
- Output / 1M tokens
- $4.44
- Context window
- 1,048,576 tokens
- Longest reply
- 943,718 tokens
- Accepts
- text
- Providers on OpenRouter
- 20
- Best provider uptime, 24 h
- 100%
What DeepSeek V4 Pro 0813 costs next to the alternatives
Every model it is compared with, on the same two workloads the matchup pages use. A short request is 2,000 tokens in and 500 out; a document summary is 20,000 in and 1,000 out.
| Model | Input / 1M | Output / 1M | 1,000 short requests | 100 document summaries | Context | Also takes |
|---|---|---|---|---|---|---|
| DeepSeek V4 Pro 0813 (this model) | $0.11 | $4.44 | $2.44 | $0.67 | 1,048,576 | text only |
| DeepSeek V4.1 Flash | $0.30 | $1.20 | $1.20 | $0.72 | 1,048,576 | images |
Base rates from OpenRouter (checked 13 November 2026). Cache discounts, media, tools and extra reasoning tokens are not included. Model names link to the full matchup.
- DeepSeek V4 Pro 0813 is the most expensive model here for short requests, at $2.44 per 1,000. DeepSeek V4.1 Flash handles the same 1,000 for $1.20.
- Long prompts change the order. For document summaries, where most tokens are input, DeepSeek V4 Pro 0813 is the cheapest, at $0.67 per 100.
- DeepSeek V4 Pro 0813 cannot take images as input. Alternatives that can: images (DeepSeek V4.1 Flash).
Compare DeepSeek V4 Pro 0813 with
Need a different matchup?
Pick any two API models and we'll build the side-by-side for you.
Build your own comparison