We use cookies. Cookies and browser storage keep you signed in and remember your preferences. With your permission we also measure how the site is used. You can any time. See our cookie policy.
DeepSeek: R1 0528
deepseek/deepseek-r1-0528Try DeepSeek: R1 0528 now
Runs on your balance at the prices above. New accounts start with free usage.
One API. Every model.
Session cost $0.00
Settings
Advanced parameters
DeepSeek: R1 0528 at a glance
- Input price is 11% higher than the median of 434 Text models.
- Context window of 163,840 tokens, enough for long documents and multi-turn conversations.
- Supports tool (function) calling for agents and integrations.
- Supports structured JSON output with a schema.
- Supports reasoning effort control.
- A typical request (1,000 input / 500 output tokens) costs about $0.00551.
About DeepSeek: R1 0528
DeepSeek: R1 0528 is a text model from DeepSeek, released by the provider on 2025-05-28 as the May 28th update to the original DeepSeek R1. It is a 671B parameter model with 37B active parameters, and it is open-sourced with fully open reasoning tokens. DeepSeek describes its performance as on par with OpenAI o1.
The model is text in, text out. It accepts text prompts and returns text, including reasoning output, and it has a context window of 163,840 tokens with a maximum output of 32,768 tokens. Its knowledge cutoff is 2025-03-31. Because the reasoning tokens are fully open, you can inspect the model's intermediate thinking rather than only its final answer, which matters when you need to debug or audit how a conclusion was reached.
That combination of a large context window, open reasoning, and tool support points to a few practical uses. Long documents, such as specifications, contracts, or research papers, fit comfortably in the context window, so summarization, extraction, and question answering over large inputs are reasonable fits. Open reasoning tokens suit tasks where the path to the answer matters: multi-step math, logic problems, code analysis, and any workflow where you want to review the model's chain of thought. Tool calling and structured outputs make it usable in agent pipelines and in systems that need machine-readable responses rather than free text.
You call it through api14's OpenAI-compatible API using the model id "deepseek/deepseek-r1-0528". The supported request parameters are frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, and top_p. The reasoning and include_reasoning parameters are the ones to reach for when you want the reasoning output surfaced in the response, and tools with tool_choice covers function calling.
Since the model is text only, it is not the right choice if your input includes images or audio, and you would need a multimodal model instead. The 32,768 token output cap also means very long generations have to be split or continued across calls. Within those bounds, it is a strong candidate for reasoning-heavy text work.
How to call the DeepSeek: R1 0528 API
- Create an API key in your dashboard.
- Install the official openai SDK for your language.
- Set baseURL to https://api14.com/api/v1 and model to "deepseek/deepseek-r1-0528".
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api14.com/api/v1",
apiKey: process.env.API14_API_KEY,
});
const result = await client.chat.completions.create({
"model": "deepseek/deepseek-r1-0528",
"messages": [
{
"role": "user",
"content": "Explain vector databases in two sentences."
}
]
});
console.log(result.choices[0].message.content);
Supported parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_pSpecifications
- Context length
- 163,840
- Max output
- 32,768
- Input
- text
- Output
- text
- Knowledge cutoff
- 2025-03-31
Requests on api14 · last 7 days
DeepSeek: R1 0528: frequently asked questions
- How much does the DeepSeek: R1 0528 API cost?
- DeepSeek: R1 0528 costs Input $1.75 / 1M tokens. It is charged from your USD balance only for successful requests; failed requests are free.
- What is the context window of DeepSeek: R1 0528?
- DeepSeek: R1 0528 reads up to 163,840 tokens per request: prompt, history and documents together. It writes up to 32,768 output tokens per response.
- What can DeepSeek: R1 0528 do?
- DeepSeek: R1 0528 accepts text and returns text. It supports tool calling, structured JSON output, reasoning effort control.
- How do I call DeepSeek: R1 0528 from my code?
- Point any OpenAI SDK at https://api14.com/api/v1 and set the model to "deepseek/deepseek-r1-0528". No other code changes. Copy a ready example from the code panel on this page.
- What are alternatives to DeepSeek: R1 0528?
- Comparable Text models at a similar price: DeepSeek: DeepSeek V4 Pro 0813, OpenAI: GPT-5.4 Mini (batch), NVIDIA: Nemotron 3 Super. Each runs through the same API key, so switching is one string.
DeepSeek: R1 0528 community
New topicThis community has no topics yet. Open the first one about DeepSeek: R1 0528.