DeepSeek R1 vs DeepSeek R1 0528
DeepSeek R1 (2025) and DeepSeek R1 0528 (2025) are frontier-tier reasoning models from DeepSeek. DeepSeek R1 ships a 128K-token context window, while DeepSeek R1 0528 ships a 160K-token context window. On Google-Proof Q&A, DeepSeek R1 0528 leads by 9.5 pts. On pricing, DeepSeek R1 costs $0.1/1M input tokens versus $0.1/1M for the alternative. This comparison covers specs, pricing, capabilities, benchmarks, provider availability, and production fit.
Pick DeepSeek R1 0528 for reasoning; DeepSeek R1 is better when coding workflow support matters more.
Specs
| Released | 2025-01-20 | 2025-01-01 |
| Context window | 128K | 160K |
| Parameters | 671B, 37B Active | 671B |
| Architecture | decoder only | decoder only |
| License | Open Source | Open Source |
| Knowledge cutoff | - | - |
Pricing and availability
| DeepSeek R1 | DeepSeek R1 0528 | |
|---|---|---|
| Input price | $0.1/1M tokens | $0.1/1M tokens |
| Output price | $0.3/1M tokens | $0.3/1M tokens |
| Providers |
Capabilities
| DeepSeek R1 | DeepSeek R1 0528 | |
|---|---|---|
| Vision | ||
| Multimodal | ||
| Reasoning | ||
| Function calling | ||
| Tool use | ||
| Structured outputs | ||
| Code execution |
Benchmarks
| Benchmark | DeepSeek R1 | DeepSeek R1 0528 |
|---|---|---|
| Google-Proof Q&A | 71.5 | 81.0 |
| Aider Polyglot | 56.9 | 71.4 |
Deep dive
On shared benchmark coverage, Google-Proof Q&A has DeepSeek R1 at 71.5 and DeepSeek R1 0528 at 81, with DeepSeek R1 0528 ahead by 9.5 points; Aider Polyglot has DeepSeek R1 at 56.9 and DeepSeek R1 0528 at 71.4, with DeepSeek R1 0528 ahead by 14.5 points. The largest visible gap is 14.5 points on Aider Polyglot, which matters most when that benchmark mirrors your workload. Treat isolated benchmark wins as directional, because provider routing, prompt style, and tool access can move real application results.
The capability footprint is close: both models cover reasoning mode, structured outputs, and code execution. That makes context budget, benchmark fit, and provider maturity more important than a simple checklist. If your application depends on one integration detail, verify it against the provider route you plan to use, not just the base model listing.
For cost, DeepSeek R1 lists $0.1/1M input and $0.3/1M output tokens, while DeepSeek R1 0528 lists $0.1/1M input and $0.3/1M output tokens on the cheapest tracked provider. A 70/30 input-output blend puts DeepSeek R1 lower by about $0 per million blended tokens. Availability is 13 providers versus 5, so concentration risk also matters.
Choose DeepSeek R1 when coding workflow support and broader provider choice are central to the workload. Choose DeepSeek R1 0528 when coding workflow support and larger context windows are more important. For production, rerun your own prompts through the exact provider, region, and tool stack you plan to ship.
FAQ
Which has a larger context window, DeepSeek R1 or DeepSeek R1 0528?
DeepSeek R1 0528 supports 160K tokens, while DeepSeek R1 supports 128K tokens. That gap matters most for long documents, large codebases, retrieval-heavy agents, and conversations where earlier context must remain visible.
Which is cheaper, DeepSeek R1 or DeepSeek R1 0528?
DeepSeek R1 is cheaper on tracked token pricing. DeepSeek R1 costs $0.1/1M input and $0.3/1M output tokens. DeepSeek R1 0528 costs $0.1/1M input and $0.3/1M output tokens. Provider discounts or batch pricing can still change the final bill.
Is DeepSeek R1 or DeepSeek R1 0528 open source?
DeepSeek R1 is listed under Open Source. DeepSeek R1 0528 is listed under Open Source. License labels affect whether you can self-host, redistribute weights, or rely only on hosted APIs, so confirm the upstream license before deployment.
Which is better for reasoning mode, DeepSeek R1 or DeepSeek R1 0528?
Both DeepSeek R1 and DeepSeek R1 0528 expose reasoning mode. The better choice depends on benchmark fit, context budget, pricing, and whether your provider route exposes the same capability surface.
Which is better for structured outputs, DeepSeek R1 or DeepSeek R1 0528?
Both DeepSeek R1 and DeepSeek R1 0528 expose structured outputs. The better choice depends on benchmark fit, context budget, pricing, and whether your provider route exposes the same capability surface.
Where can I run DeepSeek R1 and DeepSeek R1 0528?
DeepSeek R1 is available on DeepSeek Platform, OpenRouter, Together AI, Fireworks AI, and NVIDIA NIM. DeepSeek R1 0528 is available on Together AI, Fireworks AI, GCP Vertex AI, Novita AI, and OpenRouter. Provider coverage can affect latency, region availability, compliance posture, and fallback options.
Continue comparing
Last reviewed: 2026-04-24. Data sourced from public model cards and provider documentation.