← Agent Data Hub · Search endpoints · /llms.txt

Universal Multi-LLM Prompt & Output Token Cost Comparator

Calculates and compares exact API execution costs across GPT-4o, Claude 3.7 Sonnet, Gemini 2.5 Pro, Gemini 2.5 Flash, and DeepSeek-V3 for any token workload.

Call it (no API key)

GET https://api.agentdatahub.de/api/v1/call/ai-prompt-token-cost-estimator?input_tokens=100000&output_tokens=20000&compact=1

Full metadata: without compact=1 · Markdown: format=llm · Only some fields: add &fields=a,b.c · MCP: tool call_api with {"apiId":"ai-prompt-token-cost-estimator"}

Parameters

Example response (live, compact)

{
  "apiId": "ai-prompt-token-cost-estimator",
  "data_freshness": "cached",
  "data": {
    "workload": {
      "input_tokens": 100000,
      "output_tokens": 20000
    },
    "estimated_cost_usd": {
      "gemini_2_5_flash": 0.027,
      "deepseek_v3": 0.049,
      "gemini_2_5_pro": 0.325,
      "gpt_4o": 0.45,
      "claude_3_7_sonnet": 0.6
    }
  },
  "source": "100% Platform AI Economics Engine",
  "license": "100% Platform Deterministic Compute / Open Reference"
}

Source & license