DeepSeek V3.2 Thinking

Model details

← Back

DeepSeek V3.2 Thinking

Model
deepseek/deepseek-v3.2-thinking
Provider
vercel-ai-gateway
API
anthropic-messages
Base URL
https://ai-gateway.vercel.sh
Input
text
Reasoning
Yes
Context window
128,000
Max tokens
64,000
Cost / million input
$0.28
Cost / million output
$0.42
Cost / million cache read
$0.028
Cost / million cache write
$0

Also available from other providers

Model config JSON
{
  "providers": {
    "vercel-ai-gateway": {
      "apiKey": "YOUR_API_KEY",
      "models": [
        {
          "id": "deepseek/deepseek-v3.2-thinking",
          "name": "DeepSeek V3.2 Thinking",
          "reasoning": true,
          "input": [
            "text"
          ],
          "contextWindow": 128000,
          "maxTokens": 64000,
          "cost": {
            "input": 0.28,
            "output": 0.42,
            "cacheRead": 0.028,
            "cacheWrite": 0
          }
        }
      ],
      "api": "anthropic-messages",
      "baseUrl": "https://ai-gateway.vercel.sh"
    }
  }
}