DeepSeek V4 Pro

Models

Model details

DeepSeek V4 Pro

Model
deepseek-ai/DeepSeek-V4-Pro
Provider
together
API
openai-completions
Base URL
https://api.together.ai/v1
Input
text
Reasoning
Yes
Context window
512,000
Max tokens
384,000
Cost / million input
$2.1
Cost / million output
$4.4
Cost / million cache read
$0.2
Cost / million cache write
$0

Also available from other providers

Model config JSON
{
  "providers": {
    "together": {
      "apiKey": "YOUR_API_KEY",
      "models": [
        {
          "id": "deepseek-ai/DeepSeek-V4-Pro",
          "name": "DeepSeek V4 Pro",
          "reasoning": true,
          "input": [
            "text"
          ],
          "contextWindow": 512000,
          "maxTokens": 384000,
          "cost": {
            "input": 2.1,
            "output": 4.4,
            "cacheRead": 0.2,
            "cacheWrite": 0
          },
          "compat": {
            "supportsStore": false,
            "supportsDeveloperRole": false,
            "supportsReasoningEffort": true,
            "maxTokensField": "max_tokens",
            "supportsStrictMode": false,
            "supportsLongCacheRetention": false,
            "thinkingFormat": "together"
          }
        }
      ],
      "api": "openai-completions",
      "baseUrl": "https://api.together.ai/v1"
    }
  }
}