DeepSeek V4 Pro Chat Completions API
deepseek/deepseek-v4-proDeepSeek 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
Quick start
Send one POST request to /v1/chat/completions. Non-streaming calls return the model result and usage directly, with no task creation or status polling.
- Endpoint
- POST /v1/chat/completions
- Model ID
- deepseek/deepseek-v4-pro
- Protocol
- Chat Completions
Request fields
| Field | Requirement | Description |
|---|---|---|
| model | Required | deepseek/deepseek-v4-pro |
| messages | Required | A non-empty array of conversation messages. |
| max_tokens | Optional | A positive integer setting the response limit; the playground offers 256–8,192. |
| temperature | Optional | Sampling temperature from 0 to 2. |
| top_p | Optional | Nucleus sampling probability greater than 0 and at most 1; the playground slider offers 0.1–1. |
| stream | Optional | Returns an SSE event stream when true. |
Response and usage
Successful responses include generated content and usage. Billing settles from actual input, output, and cache tokens.
Streaming
Set stream: true to read SSE. Finalize usage accounting from the terminal usage event.
curl --request POST \
--url https://api.vidgo.ai/v1/chat/completions \
--header "Authorization: Bearer $VIDGO_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
"model": "deepseek/deepseek-v4-pro",
"messages": [
{
"role": "user",
"content": "Explain why deterministic retries matter in distributed systems."
}
],
"max_tokens": 1024,
"temperature": 1,
"top_p": 1,
"stream": false
}'Keep API keys on the server. Never expose them in browser code or public repositories.
Continue with
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.