OpenAI 컨텍스트 캐시 사용 가이드

export API_KEY="YOUR_API_KEY"

curl "https://api.apimart.ai/v1/responses" \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gpt-6.1-terra",
  "prompt_cache_options": {
    "ttl": "30m"
  },
  "input": [
    {
      "role": "user",
      "content": [
        {
          "type": "input_text",
          "text": "Long reference material to reuse (at least 1024 tokens)... Summarize the key points."
        }
      ]
    }
  ]
}'

curl "https://api.apimart.ai/v1/responses" \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gpt-6.1-terra",
  "prompt_cache_options": {
    "ttl": "12h"
  },
  "input": [
    {
      "role": "user",
      "content": [
        {
          "type": "input_text",
          "text": "Long reference material to reuse (at least 1024 tokens)... Summarize the key points."
        }
      ]
    }
  ]
}'

curl "https://api.apimart.ai/v1/responses" \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gpt-6.1-terra",
  "prompt_cache_options": {
    "ttl": "12h",
    "mode": "explicit"
  },
  "input": [
    {
      "role": "user",
      "content": [
        {
          "type": "input_text",
          "text": "Long reference material to reuse (at least 1024 tokens)...",
          "prompt_cache_breakpoint": {
            "mode": "explicit"
          }
        }
      ]
    },
    {
      "role": "user",
      "content": [
        {
          "type": "input_text",
          "text": "Summarize the three main points in the reference material."
        }
      ]
    }
  ]
}'

{
  "usage": {
    "input_tokens": 12000,
    "input_tokens_details": {
      "cached_tokens": 4000,
      "cache_write_tokens": 7000,
      "cache_write_tokens_details": {
        "ttl_30m_tokens": 5000,
        "ttl_12h_tokens": 2000
      }
    },
    "output_tokens": 1000,
    "total_tokens": 13000
  }
}

input_tokens - input_tokens_details.cached_tokens - input_tokens_details.cache_write_tokens

cache_write_tokens = ttl_30m_tokens + ttl_12h_tokens
total_tokens = input_tokens + output_tokens