DeepSeek V4 Pro

Model details

← Back

DeepSeek V4 Pro

Model
deepseek-v4-pro
Provider
deepseek
API
openai-completions
Base URL
https://api.deepseek.com
Input
text
Reasoning
Yes
Context window
1,000,000
Max tokens
384,000
Cost / million input
$1.74
Cost / million output
$3.48
Cost / million cache read
$0.145
Cost / million cache write
$0

Also available from other providers

Model config JSON
{
  "providers": {
    "deepseek": {
      "apiKey": "YOUR_API_KEY",
      "models": [
        {
          "id": "deepseek-v4-pro",
          "name": "DeepSeek V4 Pro",
          "reasoning": true,
          "input": [
            "text"
          ],
          "contextWindow": 1000000,
          "maxTokens": 384000,
          "cost": {
            "input": 1.74,
            "output": 3.48,
            "cacheRead": 0.145,
            "cacheWrite": 0
          },
          "compat": {
            "requiresReasoningContentOnAssistantMessages": true,
            "thinkingFormat": "deepseek",
            "reasoningEffortMap": {
              "minimal": "high",
              "low": "high",
              "medium": "high",
              "high": "high",
              "xhigh": "max"
            }
          }
        }
      ],
      "api": "openai-completions",
      "baseUrl": "https://api.deepseek.com"
    }
  }
}