DeepSeek V4 Pro Chat Completions API

deepseek/deepseek-v4-pro
1M tokens · 68.4 input / 136.8 output credits / 1M tokens

DeepSeek V4 Pro Chat Completions turns conversation messages and long text into code, analysis, and reasoned answers across a 1M-token context. Clear instructions and source labels help it connect distant evidence and organize follow-up responses for complex tasks.

DeepSeek V4 Pro

DeepSeek · chat-completions

Chat with DeepSeek V4 Pro

Each model has its own conversation. Switching never sends another model's history, and switching back resumes where you left off. Requests are billed from actual token usage.

Ctrl / ⌘ + Enter to send0 / 32,000

Continue with

DeepSeek V4 Pro Chat Completions

DeepSeek V4 Pro is a DeepSeek language model for analyzing extensive text, reasoning through connected requirements, and producing code or written answers. Its 1M-token context lets a request carry long documents, repository excerpts, and earlier conversation turns together. Send ordered messages through Chat Completions, then inspect the generated response and token usage. For complex work, label source sections and state the expected deliverable so each conclusion can be checked against its context.

Why Choose DeepSeek V4 Pro?

  • 1M-token contextExamine related documents, code files, and prior conversation turns together when key details are far apart.

  • Connected reasoningWork through constraints and evidence across several steps to develop an answer that can be reviewed against the source material.

  • Code and repository analysisUse requirements, implementation excerpts, and error context to explain behavior, draft changes, and inspect tradeoffs.

  • Sustained text workflowsCarry relevant earlier messages into follow-up requests so analysis and revisions build on the same task context.

Parameters

ParameterRequirementDescription
modelRequired

Set to deepseek/deepseek-v4-pro.

messagesRequired

A non-empty ordered array of messages. Each message provides role and content.

max_tokensOptional

A positive integer limiting generated tokens. The Playground control offers 256–8,192 tokens.

temperatureOptional

Sampling temperature from 0 to 2.

Default1
top_pOptional

Nucleus sampling value greater than 0 and at most 1. The Playground slider offers 0.1–1.

Default1
streamOptional

Choose a complete JSON response or an SSE stream.

Defaultfalsetrue

How to Use

  1. Define the taskState the question, expected output, and constraints in the user message.

  2. Organize the contextLabel document sections or code excerpts and add earlier turns when they matter to the answer.

  3. Set response controlsChoose a positive max_tokens value and adjust temperature or top_p to shape the response.

  4. Review the resultCheck the generated text against the supplied material and inspect token usage before the next turn.

Pricing

Input and output tokens are measured separately. These Vidgo rates apply per 1M tokens and settle in credits.

UsageRateDetails
Input tokens$0.342 · 68.4 credits / 1M tokensTokens supplied in the request.
Output tokens$0.684 · 136.8 credits / 1M tokensTokens generated in the response.

Best Use Cases

  • Repository investigationsConnect requirements, implementation excerpts, and observed behavior before proposing a code change.

  • Long-document synthesisCompare sections across reports or manuals and produce an answer tied to the relevant material.

  • Multi-step reasoningBreak a mathematical or analytical problem into explicit constraints, intermediate steps, and a final result.

  • Iterative draftingCarry previous decisions into later turns while refining an explanation, plan, or code response.

Pro Tips

  • Give each source document or code excerpt a stable name so follow-up questions can refer to it precisely.
  • Put the goal, constraints, and desired answer format near the question.
  • Check cited passages, calculations, and code paths against the supplied source material.

Usage Notes

  • DeepSeek V4 Pro has a 1M-token context window; the Playground offers a 256–8,192-token output control.
  • Send a non-empty messages array to /v1/chat/completions with model set to deepseek/deepseek-v4-pro.
  • Set stream to false for a complete JSON response or true for SSE events.

Related Models

DeepSeek V4 Pro Chat Completions API frequently asked questions

What is the DeepSeek V4 Pro Chat Completions API?

DeepSeek V4 Pro Chat Completions is a DeepSeek model for turning ordered conversation messages and long text into code, analysis, and reasoned answers. Its 1M-token context helps connect details across large documents and repository excerpts. Clear instructions and source labels guide how it handles the task. You can call it programmatically or try it in the Playground above.

How can DeepSeek V4 Pro use a 1M-token context?

Place related documents, code excerpts, and earlier turns in one ordered conversation. Label sections and ask a focused question that identifies the evidence to compare.

How does DeepSeek V4 Pro help with repository analysis?

Provide the relevant files, observed behavior, and intended change. The model can connect implementation details, explain likely causes, and draft a reviewable change plan.

How should DeepSeek V4 Pro approach a reasoning task?

State the inputs, constraints, and required output clearly. Ask for intermediate steps when reviewing a calculation or decision, then check the result against the supplied evidence.

How can DeepSeek V4 Pro synthesize long documents?

Give each document a title and stable section markers. Ask a question that names the themes or facts to compare so the response can be checked against the source passages.

How does DeepSeek V4 Pro continue a multi-turn conversation?

Include earlier user and assistant turns in messages, followed by the new user question. The model uses those supplied turns as context for the next answer.

How do I set the DeepSeek V4 Pro response length?

Set max_tokens to a positive integer. The on-page Playground offers values from 256 to 8,192 tokens for interactive requests.

What is the DeepSeek V4 Pro price on Vidgo?

Input is 68.4 credits ($0.342) per 1M tokens; output is 136.8 credits ($0.684) per 1M tokens. Token usage is reported with each response.