R1 0528
deepseek/deepseek-r1-0528- DeepSeek
- Family · R1
- Open weights
- Text → Text
- Tools · JSON
Not on OSMEXO yet
Spec & list price
Context160K
Max output32K
Input / 1M$0.50
Output / 1M$2.154.3× input
Usage
Tokens / day1.5B▼ 16% 7d
Usage rank#176
Requests / day137.5K
Tool calls / req0.01
Per request · 30 days
Avg input7.7K0.5× median
Avg output1.7K2.5× median
Cache hit51%0.7× median
Reasoning share52%about median
Tool-call failures3.4%1.8× median
Consumption
Peak 2.1B 22 OctLow 1.4B 9 OctRank today #176
News & trends
Trending · 14 days
- Search for Cheap R1 05281 upvotes
News · latest from DeepSeek
- Tell HN: Mistrap Pro includes DeepSeek v4.1 Flash 1017docs.mistral.ai · 1 Nov
- Show HN: DeepSeek v4.1 Flash-1017 Safety Evaluationtwitter.com · 26 Oct
- DeepSeek V4 Pro 0813 vs Claude Fable 5 on DeepSWE: Cost, Coding, and RoutingTogether AI · 17 Aug
- DeepSeek-V4 Flash 0731 vs GPT-5.6 Luna on DeepSWE: Cost and CodingTogether AI · 6 Aug
Speed
Output speed#309/33422 tok/s2.9× slower than median
Fastest provider43 tok/sbest of 3 providers
First token#2451.92 s1.8× longer than median
Technical details
- Tokenizer
- DeepSeek
- Knowledge cutoff
- 2025-03-31
- License
- MIT
- Parameters
- 685B
- Moderation
- none
- Downloads · likes
- 104.9K · 2.5K
Request parameters 19
- tools
- tool_choice
- response_format
- structured_outputs
- reasoning
- include_reasoning
- temperature
- top_p
- top_k
- min_p
+9 more
- max_tokens
- stop
- seed
- frequency_penalty
- logit_bias
- logprobs
- presence_penalty
- repetition_penalty
- top_logprobs
When to use
Best for
- Step-by-step reasoning on math and logic
- Tool-calling agents that plan first
- Self-hosted reasoning (open weights)
- Analysis over long documents
Think twice for
- Image understanding
- Latency-sensitive chat
- Simple high-volume tasks (reasoning adds cost)
Research papers
Same family
R1- 6.4
Want R1 0528 on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.