Prototype · closed beta
unOpen.AI
In closed beta: Roxy, a private AI assistant with permanent memory running on infrastructure the user owns. Brand, site, product, backend and conversational design.
DeepSeek · DeepSeek
R1 0528.
R1 0528 is a DeepSeek model, listed on 28 May 2025. It takes text and returns text, with a 163,840-token context window.
- Open weights
- 164k context
Specification
- Provider
- DeepSeek
- Family
- DeepSeek
- Listed
- 28 May 2025
- Catalogue id
- deepseek/deepseek-r1-0528
- Context window
- 163,840 tokens
- Maximum output
- 32,768 tokens
- Inputs and output
- Text in; text out
- Capabilities
- Tool calling, structured outputs and adjustable reasoning
- Weights
- Published: deepseek-ai/DeepSeek-R1-0528
- Knowledge cut-off
- 2025-03-31
- Listed price
- $0.500 input, $2.15 output, $0.350 cached input per million tokens
Provider-published specifications as of 30 October 2026, not figures we measured. Model families move quickly — check the provider's own documentation before committing to a number.
Source: R1 0528 in the OpenRouter catalogue, checked weekly. Confirm current terms in DeepSeek's own documentation before you commit.
What it costs
Price the whole answer.
Illustrative calculation at listed rates: a batch of 10 million input tokens and 1 million output tokens costs $7.15 on R1 0528. A thousand requests of 2,000 input and 500 output tokens each costs $2.08. Calculation: input millions × input rate + output millions × output rate; it excludes reasoning tokens, retries, tools, tax and review time.
Compare cost per accepted result, not per token: replay the same work on two or three candidates and count the answers you would actually ship. Our model-routing approach sends each request to the cheapest model that passes.
THE REST OF THE FAMILY
Other DeepSeek models.
Every DeepSeek model in the catalogue. Our DeepSeek page covers where the family fits and how we evaluate it.
| R1 0528 open | 28 May 2025 | — | — | 164k | $0.500 | $2.15 |
|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 open | 17 Oct 2026 | 32.5 | 159 | 1.05M | $0.150 | $0.600 |
| DeepSeek V4.1 Flash open | 10 Sep 2026 | — | — | 1.05M | $0.045 | $0.500 |
| DeepSeek V4 Pro 0813 open | 13 Aug 2026 | 23.1 | 77 | 1.05M | $0.660 | $1.98 |
| DeepSeek V4 Flash 0731 open | 31 Jul 2026 | — | — | 1.05M | $0.119 | $0.238 |
| DeepSeek V4 Flash 0423 open | 31 Jul 2026 | — | — | 1.05M | $0.091 | $0.182 |
| DeepSeek V4 Pro 0423 open | 13 Aug 2026 | 23.1 | 77 | 1.05M | $0.948 | $1.90 |
| DeepSeek V3.2 open | 1 Dec 2025 | — | — | 164k | $0.260 | $0.380 |
| DeepSeek V3.1 Terminus open | 22 Sep 2025 | — | — | 164k | $0.270 | $1.00 |
| DeepSeek V3.1 open | 21 Aug 2025 | — | — | 164k | $0.250 | $0.950 |
| DeepSeek V3 0324 open | 25 Mar 2025 | — | — | 164k | $0.290 | $1.14 |
| DeepSeek V3 open | 26 Dec 2024 | — | — | 164k | $0.257 | $1.03 |
Intelligence and coding: Artificial Analysis indices at the model's best reasoning setting, and its measured output speed. Context and prices: the OpenRouter catalogue list price in USD per million tokens. Released: the provider's date where Artificial Analysis records one, otherwise the date the catalogue first listed it. Refreshed weekly; not measured by QQuantum.ai. Select a heading to sort.
Questions
Questions about R1 0528.
When was R1 0528 listed?
R1 0528 was listed on 28 May 2025 in the OpenRouter catalogue; the provider's own announcement may predate it.
What is the context window of R1 0528?
163,840 tokens, with up to 32,768 output tokens per response, as listed in the OpenRouter catalogue on 30 October 2026. A long window is not the same as reliable recall across it; evaluate retrieval on your own documents.
How much does R1 0528 cost?
The catalogue lists $0.500 per million input tokens and $2.15 per million output tokens, and $0.350 per million cached input tokens (checked 30 October 2026). DeepSeek's own rates, batch discounts and cloud marketplaces can differ.
Can R1 0528 run on our own hardware?
Its weights are published (on Hugging Face as deepseek-ai/DeepSeek-R1-0528), so it can be self-hosted subject to its licence. Check the licence and size the serving stack before buying hardware.
