DeepSeek V4 Pro 0423 vs DeepSeek V4 Pro 0813
DeepSeek V4 Pro 0423 (DeepSeek) and DeepSeek V4 Pro 0813 (DeepSeek) are listed at different prices. DeepSeek V4 Pro 0423 costs less: $0.90 per 1M input tokens and $1.50 per 1M output tokens, against $1.32 and $3.96 for DeepSeek V4 Pro 0813. Both hold 1,048,576 tokens of context. DeepSeek V4 Pro 0813 can write up to 943,718 tokens in one response, against 393,216 for DeepSeek V4 Pro 0423. Both accept text and produce text.
DeepSeek: DeepSeek V4 Pro 0423 and DeepSeek: DeepSeek V4 Pro 0813 both accept and produce text, support tools, structured outputs, response formats, and reasoning, and have 1,048,576-token context windows. Their maximum output lengths differ: 393,216 tokens and 943,718 tokens, respectively.
Compared from catalog data checked
Side by side
0.00 the better figure in a row| Specification | DeepSeek V4 Pro 0423 | DeepSeek V4 Pro 0813 |
|---|---|---|
| Maker | DeepSeek | DeepSeek |
| Added to catalog | 24 Apr 2026 | 12 Aug 2026 |
| Input, per 1M tokens | $0.90 | $1.32 |
| Output, per 1M tokens | $1.50 | $3.96 |
| Cached input read, per 1M | $0.20 | $0.044 |
| Context windowTokens | 1,048,576 | 1,048,576 |
| Max outputTokens | 393,216 | 943,718 |
| Accepts | text | text |
| Produces | text | text |
| Tool calling | Yes | Yes |
| Structured outputs | Yes | Yes |
| Reasoning effort control | Yes | Yes |
List prices through OpenRouter, in US dollars. Each model's page has its variants, price history and sample outputs.
What the same task costs
List price for one request, from the token counts shown. The same four tasks are priced on every model page.
| Task | DeepSeek V4 Pro 0423 | DeepSeek V4 Pro 0813 |
|---|---|---|
| Answer a short question500 in / 300 out | $0.0009 | $0.0018 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.024 | $0.036 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.030 | $0.048 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.137 | $0.204 |
Which to choose
Choose DeepSeek V4 Pro 0423 if
- Input tokens cost less: $0.90 against $1.32 per 1M
- Output tokens cost less: $1.50 against $3.96 per 1M
Choose DeepSeek V4 Pro 0813 if
- Cached input costs less: $0.044 against $0.20 per 1M
- You need longer answers in one response: 943,718 tokens against 393,216
Neither maker's quality claims are repeated here. The reliable test is your own task: ask both the same question and read the two answers.