DeepSeek V4 Pro (0813) targets complex reasoning, coding, and agent workflows. It natively supports the Responses API and remains compatible with Chat Completions.
Provider: DeepSeek
Category: text generation
Endpoint: /v1/responses
Status: Available
Cost: --
DeepSeek V4 Pro (0813) targets complex reasoning, coding, and agent workflows. It natively supports the Responses API and remains compatible with Chat Completions.
API access
Endpoint
POST /v1/responses
Base URL
https://www.hiapi.ai
Uses the OpenAI Responses format with streaming required. One HiAPI key works across all available models.
Input price
1,000 Credits
/ 1M tokens
Output price
2,000 Credits
/ 1M tokens
Context
1M
context window
Max output
384K
output tokens
Ask a question to stream the answer and inspect token usage, latency, and estimated cost.
Call DeepSeek V4 Pro with the streaming OpenAI Responses format. Copy a ready-to-use cURL, Python, or Node.js example below.
/v1/responsescurl -N -X POST "https://www.hiapi.ai/v1/responses" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-pro",
"input": [
{
"type": "message",
"role": "user",
"content": [
{
"type": "input_text",
"text": "分析一个复杂代码库中的性能瓶颈，并给出可验证的优化方案。"
}
]
}
],
"stream": true,
"max_output_tokens": 1024,
"reasoning": {
"effort": "high"
}
}'Tip: Replace YOUR_API_KEY with your actual API key from the API Keys page.
Uses the OpenAI Responses format. Keep stream: true, send input as a message array, and set reasoning effort with reasoning.effort.
The example defaults to reasoning.effort=high. Use max for maximum effort or none to disable reasoning.
Responses API
Start with core fields, then enable advanced capabilities as needed.
The fields that form a valid request
Enable reasoning, output control, and tools as needed
DeepSeek Responses is stateless and does not support previous_response_id or conversation. Replay required context in the next input and omit store.
Billing is based on actual input, output, and cached token usage. All prices below are shown per 1 million tokens.
Prompts and context sent to the model
Responses and reasoning generated by the model
These specifications reflect the current public HiAPI text request contract. Undisclosed capabilities are not inferred by the page.
DeepSeek V4 Pro (0813) targets complex reasoning, coding, and agent workflows. It natively supports the Responses API and remains compatible with Chat Completions.
HiAPI exposes this model through /v1/responses. Test prompts and parameters in the Playground, then use the same HiAPI API key in your server application.
The Playground and API share the same model ID, so three steps take a tested prompt into production.
Step 1
Test instructions, input, and reasoning.effort in the Playground.
Step 2
View an existing key or create another after signing in; one key works across all available models.
Step 3
Send requests to /v1/responses and track cost with the usage object.
DeepSeek V4 Pro 0813 is the production release of the V4 Pro API model for demanding reasoning, coding, and Agent workloads. It supports a 1M-token context window, up to 384K output tokens, and thinking and non-thinking modes.
Set model to deepseek-v4-pro. HiAPI recommends POST /v1/responses and also keeps POST /v1/chat/completions for compatible clients.
Responses uses reasoning.effort with none, low, high, or max and defaults to high. Chat Completions uses thinking.type and reasoning_effort.
No. It is stateless. Omit store, previous_response_id, conversation, and background, and replay required context in input.
HiAPI bills actual input, output, and cached-input tokens separately. Final charges follow response usage, the live pricing page, and API logs.
Use Responses for Codex-style workflows. Existing Chat Completions clients can keep the messages request shape and replace the base URL, API key, and model ID.