Model comparison
Grok 4 vs DeepSeek-R1-0528
- Input
- $3.00 / 1M tokens
- Output
- $15.00 / 1M tokens
- Context
- 256K
- Released
- 2025-07-09
- Input
- $0.50 / 1M tokens
- Output
- $2.15 / 1M tokens
- Context
- 164K
- Released
- 2025-05-28
Grok 4 scores higher on 4 of the 4 benchmarks both models report; DeepSeek-R1-0528 is cheaper on input tokens ($0.5 vs $3 per 1M, 6×); Grok 4 has the larger context window (256K vs 164K); DeepSeek-R1-0528 ships open weights while Grok 4 is API-only.
Specs and pricing side by side
| Spec | Grok 4 | DeepSeek-R1-0528 |
|---|---|---|
| Maker | xAI (Grok) | DeepSeek |
| Released | 2025-07-09 | 2025-05-28 |
| Context window | 256K | 164K |
| Max output | 8K | 32K tokens (64K max generation length) |
| Input price | $3.00 / 1M tokens | $0.50 / 1M tokens |
| Output price | $15.00 / 1M tokens | $2.15 / 1M tokens |
| Parameters | not published | 671B total / 37B active (685B on Hugging Face incl. MTP module) |
| License | Proprietary | MIT |
| Weights | API only | Open weights |
| Modalities | Text, Vision | Text |
| Knowledge cutoff | November 2024 | Not officially disclosed |
Benchmarks both models report
| Benchmark | Grok 4 | DeepSeek-R1-0528 |
|---|---|---|
| Humanity's Last Exam | 41% | 17.7% |
| AIME 2025 | 91.7% | 87.5% |
| HMMT 2025 | 90% | 79.4% |
| LiveCodeBench | 79% | 73.3% |
Scores are as published by each maker or its cited source; harness, reasoning effort and date can differ between rows, so treat small gaps as ties. Sources are listed on each model page.
Which one should you pick?
Pick Grok 4 if…
- You care about Humanity's Last Exam, AIME 2025, HMMT 2025 (it scores higher on 4 shared benchmarks).
- You need the longer context (256K vs 164K).
- You need Vision input, which DeepSeek-R1-0528 lacks.
- Your use case is: hard STEM and competition-math problem solving (AIME/HMMT/USAMO-style reasoning).
Pick DeepSeek-R1-0528 if…
- Cost matters: input tokens cost 6× less ($0.5 vs $3 per 1M).
- You want to self-host or fine-tune (open weights, MIT).
- Your use case is: competition-style math and multi-step logical reasoning.
FAQ
Which is better, Grok 4 or DeepSeek-R1-0528?
Grok 4 scores higher on 4 of the 4 benchmarks both models report; DeepSeek-R1-0528 is cheaper on input tokens ($0.5 vs $3 per 1M, 6×); Grok 4 has the larger context window (256K vs 164K); DeepSeek-R1-0528 ships open weights while Grok 4 is API-only. The better pick depends on whether you value benchmark scores, price per token, context length or openness for your workload.
How much cheaper is DeepSeek-R1-0528?
Grok 4: $3.00 / 1M tokens input, $15.00 / 1M tokens output. DeepSeek-R1-0528: $0.50 / 1M tokens input, $2.15 / 1M tokens output (list API prices as published by each maker).
What are the context windows of Grok 4 and DeepSeek-R1-0528?
Grok 4 offers 256K with up to 8K output; DeepSeek-R1-0528 offers 164K with up to 32K tokens (64K max generation length) output.
Is Grok 4 newer than DeepSeek-R1-0528?
Grok 4 was released 2025-07-09; DeepSeek-R1-0528 was released 2025-05-28.