R1 0528 vs DeepSeek V4 Pro 0423
R1 0528 (DeepSeek) and DeepSeek V4 Pro 0423 (DeepSeek) are listed at different prices. R1 0528 costs less for input, $0.571 per 1M tokens against $0.90; DeepSeek V4 Pro 0423 costs less for output, $1.50 per 1M tokens against $2.286. DeepSeek V4 Pro 0423 has the larger context window, 1,048,576 tokens against 163,840 for R1 0528. Only DeepSeek V4 Pro 0423 supports a reasoning effort setting. Both accept text and produce text.
DeepSeek: R1 0528 and DeepSeek: DeepSeek V4 Pro 0423 both accept and produce text and support tools, structured outputs, response formats, and reasoning. V4 Pro 0423 lists a 1,048,576-token context and 393,216-token maximum output, compared with R1 0528’s 163,840-token context and 32,000-token maximum output.
Compared from catalog data checked
Side by side
0.00 the better figure in a row| Specification | R1 0528 | DeepSeek V4 Pro 0423 |
|---|---|---|
| Maker | DeepSeek | DeepSeek |
| Added to catalog | 28 May 2025 | 24 Apr 2026 |
| Input, per 1M tokens | $0.571 | $0.90 |
| Output, per 1M tokens | $2.286 | $1.50 |
| Cached input read, per 1M | n/a | $0.20 |
| Context windowTokens | 163,840 | 1,048,576 |
| Max outputTokens | 32,000 | 393,216 |
| Accepts | text | text |
| Produces | text | text |
| Tool calling | Yes | Yes |
| Structured outputs | Yes | Yes |
| Reasoning effort control | No | 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 | R1 0528 | DeepSeek V4 Pro 0423 |
|---|---|---|
| Answer a short question500 in / 300 out | $0.0010 | $0.0009 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.016 | $0.024 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.022 | $0.030 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.089 | $0.137 |
Which to choose
Choose DeepSeek V4 Pro 0423 if
- Output tokens cost less: $1.50 against $2.286 per 1M
- Cached input costs less: $0.20 against n/a per 1M
- You need the larger context window: 1,048,576 tokens against 163,840
- You need longer answers in one response: 393,216 tokens against 32,000
- You want to set how much it reasons before it answers
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.