Cheap First
Server Details
Answers cheaply first, then escalates to a premium model only when a checker fails.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- robd-hub/cheap-first
- GitHub Stars
- 0
- ChatGPT
- –
- Claude
- –
TDQS
Score is being calculated.
Available Tools
2 toolsask_cheap_firstAsk Cheap FirstAInspect
Answer a question the Cheap First way: Dolphin answers, SERV Reasoning scores it, and a premium model answers instead only if the score misses the pass mark. Returns the answer, whether it escalated, the check score, the cost and the estimated saving. Free calls use the public demo limits (600 characters, 10 an hour per IP, 300 a day). Send Authorization: Bearer cf_... or an x402 payment of $0.005 USDC on Base for the paid limits (2000 characters). To receive the x402 challenge, send the header X-Cheap-First-Paid: 1. mode: strict escalates more often (pass mark 85), balanced is the default (75), budget escalates less often (60).
Inputs: question (required), mode. Returns: One Cheap First answer, plus what the check decided and what it cost.
cheap_first_statsCheap First benchmarkARead-onlyIdempotentInspect
Published benchmark figures. The main run is 143 questions: what Cheap First spent, what the premium model alone would have cost, how many Dolphin answered, and the average quality scores. Also includes the harder 97-question run. Does not call a model.
Inputs: no named parameters. Returns: benchmark, resultsPage, hardBenchmark
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Checks if a cheaper model agrees with your GPT, Claude or Gemini outputs, and what routing saves.
Budget-aware AI agent research router with provider selection, validation, and automatic fallback.
Get dollar quotes from 200+ LLMs before any work runs; accept, execute, and verify quality.
Ask high-complexity questions where the best answer is required — coding, hard reasoning, and more.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables an AI model to delegate self-contained subtasks to cheaper or free local models and receive answers with cost receipts, while enforcing budgets and sandboxed file access.MIT
- FlicenseNot gradedqualityBmaintenanceIntelligently routes AI tool calls (search, extract, browse) to the cheapest capable provider by default with automatic failover and audit receipts, enabling cost-effective agent workflows.2-
- FlicenseAqualityDmaintenanceRoutes commodity NLP tasks like summarization and translation to free-tier LLMs, saving Claude tokens for complex work.12-
- AlicenseAqualityBmaintenanceEnables parallel queries to multiple LLMs and judge-model synthesis of their perspectives into a single answer, with degraded-response detection, bounded retry/backfill, and cost and latency telemetry.2Apache 2.0
Glama MCP Gateway
Add one secure layer between your agents and this server.