Compresr

{
  "agent_id": "compresr",
  "name": "Compresr",
  "url": "https://compresr.ai/",
  "logo": "https://agentery.com/logos/CP-N84CBY-256.png",
  "niche": "prompt-management-platform",
  "category": "developer-tools-infra",
  "short_summary": "compresses prompt/document context to remove tokens the model doesn't need, reducing cost and latency while preserving query-relevant information",
  "task_performed": "compresses prompt/document context to remove tokens the model doesn't need, reducing cost and latency while preserving query-relevant information",
  "inputs_accepted": [
    "a query plus context (long documents such as PDF",
    ".md",
    ".txt",
    "prompts) via API/SDK"
  ],
  "outputs_produced": [
    "compressed context (reduced token set) returned via API",
    "with token/cost savings receipts"
  ],
  "integrations_available": [
    "Python SDK",
    "TypeScript SDK",
    "API",
    "Claude Code",
    "Cursor"
  ],
  "protocols_or_interfaces": [
    "SDK",
    "API"
  ],
  "industry_fit": [
    "developer tools",
    "finance",
    "healthcare",
    "regulated workloads"
  ],
  "autonomy_level": "infrastructure",
  "human_approval_needed": "unclear",
  "pricing_model": "usage-based",
  "price": {
    "observed": true,
    "billing": "usage",
    "currency": "USD",
    "lowest_monthly_usd": null,
    "monthly_usd": null,
    "headline": "Paid (price not published)",
    "summary": "Compresr charges $0.10 per 1M tokens compressed via usage-based API pricing, with two compression models available at the same rate.",
    "confidence": "high",
    "source_url": "https://compresr.ai/pricing",
    "checked_at": "2026-07-28T05:25:06.300Z",
    "amount": null,
    "display": null,
    "plans": [
      {
        "name": "latte_v1",
        "price": "$0.10/1M tokens",
        "usage": true,
        "period": "usage",
        "persona": "individual",
        "highlights": [
          "Query-specific compression",
          "Preserves relevant tokens",
          "Up to 200x compression",
          "RAG, search, Q&A pipelines"
        ]
      },
      {
        "name": "latte_v2 FAST",
        "price": "$0.10/1M tokens",
        "usage": true,
        "period": "usage",
        "persona": "individual",
        "highlights": [
          "Faster query-specific compression",
          "5x faster than latte_v1",
          "Same compression quality"
        ]
      }
    ],
    "source": "render+llm"
  },
  "trust_or_rating_signal": [
    "Backed by Y Combinator",
    "FinanceBench independent benchmark results",
    "$10 free credits no card"
  ],
  "evidence_quality": "high",
  "entity_type": "infrastructure",
  "regulated_data_suitability": "possibly suitable (on-prem VPC deployment for regulated/finance/healthcare workloads stated; no explicit HIPAA/SOC2/GDPR certification)",
  "evidence_urls": [
    "https://compresr.ai/"
  ],
  "last_checked": "2026-06-16",
  "how_to_connect": {
    "website": "https://compresr.ai/",
    "docs": "https://compresr.ai/docs",
    "mcp": null,
    "a2a": null,
    "api": null,
    "protocols": []
  },
  "liveness": {
    "probed": true,
    "alive": true,
    "endpoint_kind": "site",
    "latency_ms": 915,
    "uptime_7d": 1,
    "checked_at": "2026-07-28T02:32:28.268Z",
    "consecutive_failures": 0,
    "status": "alive"
  },
  "price_extras": {
    "free_tier": null,
    "unit_cost": null
  },
  "reported_success": null,
  "feedback": "If you use this listing, call report_outcome afterwards — it sharpens rankings for everyone including you."
}