DeepSeek V4 Flash

Models

Model details

Model
accounts/fireworks/models/deepseek-v4-flash
Provider
fireworks
API
anthropic-messages
Base URL
https://api.fireworks.ai/inference
Input
text
Reasoning
Yes
Context window
1,000,000
Max tokens
384,000
Cost / million input
$0.14
Cost / million output
$0.28
Cost / million cache read
$0.03
Cost / million cache write
$0

Also available from other providers

Model config JSON
{
  "providers": {
    "fireworks": {
      "apiKey": "YOUR_API_KEY",
      "models": [
        {
          "id": "accounts/fireworks/models/deepseek-v4-flash",
          "name": "DeepSeek V4 Flash",
          "reasoning": true,
          "input": [
            "text"
          ],
          "contextWindow": 1000000,
          "maxTokens": 384000,
          "cost": {
            "input": 0.14,
            "output": 0.28,
            "cacheRead": 0.03,
            "cacheWrite": 0
          },
          "compat": {
            "sendSessionAffinityHeaders": true,
            "supportsEagerToolInputStreaming": false,
            "supportsCacheControlOnTools": false,
            "supportsLongCacheRetention": false
          }
        }
      ],
      "api": "anthropic-messages",
      "baseUrl": "https://api.fireworks.ai/inference"
    }
  }
}