DeepSeek: DeepSeek V4 Flash

Models

Model details

Model
deepseek/deepseek-v4-flash
Provider
openrouter
API
openai-completions
Base URL
https://openrouter.ai/api/v1
Input
text
Reasoning
Yes
Context window
1,048,576
Max tokens
16,384
Cost / million input
$0.1
Cost / million output
$0.2
Cost / million cache read
$0.02
Cost / million cache write
$0

Also available from other providers

Model config JSON
{
  "providers": {
    "openrouter": {
      "apiKey": "YOUR_API_KEY",
      "models": [
        {
          "id": "deepseek/deepseek-v4-flash",
          "name": "DeepSeek: DeepSeek V4 Flash",
          "reasoning": true,
          "input": [
            "text"
          ],
          "contextWindow": 1048576,
          "maxTokens": 16384,
          "cost": {
            "input": 0.09999999999999999,
            "output": 0.19999999999999998,
            "cacheRead": 0.02,
            "cacheWrite": 0
          },
          "compat": {
            "requiresReasoningContentOnAssistantMessages": true,
            "thinkingFormat": "deepseek"
          }
        }
      ],
      "api": "openai-completions",
      "baseUrl": "https://openrouter.ai/api/v1"
    }
  }
}