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: DeepSeek Pro Latest
~deepseek/deepseek-pro-latestTry DeepSeek: DeepSeek Pro Latest 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: DeepSeek Pro Latest at a glance
- Input price is 71% lower than the median of 434 Text models.
- Context window of 1,048,576 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 $0.01.
About DeepSeek: DeepSeek Pro Latest
DeepSeek: DeepSeek Pro Latest is a text model from DeepSeek. It is a rolling alias rather than a fixed checkpoint: the provider states that this model always redirects to the latest model in the DeepSeek Pro family. That means the underlying version can change over time as DeepSeek ships new Pro releases, while the model id you call stays the same.
The model is text in and text out, with no image or audio input. Its context window is 1,048,576 tokens, and the maximum output is 943,718 tokens, so it can take in very large inputs and produce very long responses in a single call. It supports reasoning output, including a reasoning effort control and an option to include reasoning in the response, alongside the usual sampling and decoding controls. Structured outputs and response format options are available, as are tools and tool choice, so the model can be used in function calling and schema constrained workflows.
The context size and long output ceiling make it a reasonable fit for tasks where the input itself is large: analysing long documents, codebases or logs, summarising or extracting from lengthy transcripts, and multi step reasoning where the model needs to hold a lot of material in view. Tool support suits agent style applications that call external functions, and structured outputs help when you need responses that conform to a schema for downstream parsing. Reasoning controls let you trade off between quick answers and more deliberate ones depending on the task.
You call it through api14's OpenAI-compatible API using the model id "~deepseek/deepseek-pro-latest". Because the interface follows the OpenAI format, existing OpenAI SDKs and clients work with a change of base URL and key. The request parameters it supports are frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs and top_p.
One thing to keep in mind is that the alias points at a moving target. Behaviour can shift when DeepSeek updates the Pro family, so if you need reproducible outputs across time, pin a specific version where one is offered rather than relying on the latest alias. The model is also text only, so tasks that need image or audio input fall outside its scope.
How to call the DeepSeek: DeepSeek Pro Latest 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-pro-latest".
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-pro-latest",
"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_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_pSpecifications
- Context length
- 1,048,576
- Max output
- 393,216
- Input
- text
- Output
- text
Requests on api14 · last 7 days
DeepSeek: DeepSeek Pro Latest: frequently asked questions
- How much does the DeepSeek: DeepSeek Pro Latest API cost?
- DeepSeek: DeepSeek Pro Latest costs Input $0.46 / 1M tokens. It is charged from your USD balance only for successful requests; failed requests are free.
- What is the context window of DeepSeek: DeepSeek Pro Latest?
- DeepSeek: DeepSeek Pro Latest reads up to 1,048,576 tokens per request: prompt, history and documents together. It writes up to 393,216 output tokens per response.
- What can DeepSeek: DeepSeek Pro Latest do?
- DeepSeek: DeepSeek Pro Latest accepts text and returns text. It supports tool calling, structured JSON output, reasoning effort control.
- How do I call DeepSeek: DeepSeek Pro Latest from my code?
- Point any OpenAI SDK at https://api14.com/api/v1 and set the model to "~deepseek/deepseek-pro-latest". No other code changes. Copy a ready example from the code panel on this page.
- What are alternatives to DeepSeek: DeepSeek Pro Latest?
- Comparable Text models at a similar price: SpaceXAI: Grok 4.7, Sakana: Fugu Max, Qwen: Qwen3.8 Max (0902). Each runs through the same API key, so switching is one string.
DeepSeek: DeepSeek Pro Latest community
New topicThis community has no topics yet. Open the first one about DeepSeek: DeepSeek Pro Latest.