DeepSeek-R1-0528: API Pricing, Context Window & Benchmarks
DeepSeek-R1-0528 is a language model from DeepSeek, released in May 2025.
DeepSeek-R1-0528 is the May 28, 2025 version of DeepSeek's reasoning model. It features advanced thinking capabilities and serves as a benchmark comparison for newer models like DeepSeek-V3.1. This model excels in complex reasoning tasks,
DeepSeek-R1-0528 benchmarks
Rankings
Quality Tracker
DeepSeek-R1-0528 Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Mon Jul 20 2026DeepSeek-R1-0528 pricing
Providers
DeepSeek-R1-0528 starts at $0.500 per million input tokens and $2.15 per million output tokens via DeepInfra. See all 3 providers below with their per-token pricing, latency, throughput, and modality support.
| Provider | Input $/M | Output $/M | Workload 1M + 100K | Context in / out | TTFT p50 / p95 s | Output avg / p5 c/s | Success 7d | Modalities in / out |
|---|---|---|---|---|---|---|---|---|
 DeepInfra | $0.500 | $2.15 | $0.715 | 131.1K/131.1K | —/0.61 | 45/— | — | / |
 DeepSeek | $0.550 | $2.19 | $0.769 | 131.1K/131.1K | —/0.30 | 9/— | — | / |
 Novita | $0.700 | $2.50 | $0.950 | 131.1K/32.8K | 0.00/0.00 | —/— | 0.00%(19) | / |
Workload cost uses 1M input tokens plus 100K output tokens at published list prices without assuming a cache hit. Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests. Success is calculated from completed versus failed requests over the trailing seven days.
DeepSeek-R1-0528 model size
DeepSeek-R1-0528 has 671 billion parameters. See how it compares to other models in the same parameter range.
DeepSeek-R1-0528 context window
Input and output token limits for DeepSeek-R1-0528, plus how it ranks on long-context understanding.
DeepSeek-R1-0528 API
Available from the model provider
DeepSeek-R1-0528 has an official provider API. It is not currently routed through the LLM Stats gateway.
Read the official API documentationDeepSeek-R1-0528 latency
DeepSeek-R1-0528 time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
Provider operational metrics
Time to first token, output throughput, and failed-request rate from live API traffic
DeepSeek-R1-0528 examples
Recent arena outputs from DeepSeek-R1-0528, picked from the highest-ranked matchups.
DeepSeek-R1-0528 license
DeepSeek-R1-0528 is released under the MIT license, which permits commercial use, has 671.0B parameters.
- License
- MIT
- Commercial use allowed
- Parameters
- 671.0B
MIT License - allows commercial use
DeepSeek-R1-0528 resources
Official sources for DeepSeek-R1-0528: api documentation, official playground, official launch post, model weights.
DeepSeek-R1-0528 vs other models
The most-compared alternatives to DeepSeek-R1-0528 are Step3-VL-10B, Claude Sonnet 4.5, ERNIE 5.0. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like DeepSeek-R1-0528
Models ranked just above and below DeepSeek-R1-0528 by LLM Stats score.
FAQ
Common questions about DeepSeek-R1-0528.