SmitheryListed

Spendline

Spendline is a hosted AI spend governance proxy. Point your OpenAI or Anthropic SDK at Spendline, keep your own provider key, and every call is priced at the moment it happens, attributed to a customer, agent, workflow and cost centre, and checked against budgets before it is forwarded. A call that would breach a cap is refused with HTTP 402 and never reaches the provider. Ten providers are supported: OpenAI, Anthropic, Google Gemini, xAI, Mistral, DeepSeek, Alibaba Qwen, Together AI, Fireworks AI and Groq. The append-only ledger feeds per-customer gross margin and a month-close workflow that reconciles to the provider invoice. Spendline is not an observability or tracing tool; it sits alongside Langfuse, LangSmith or Helicone. The MCP server lets an agent decide whether Spendline fits (spendline_when_to_use), fetch deterministic integration instructions, and, with a Spendline API key, read spend, list budgets and check that traffic is arriving correctly attributed.

First seen 2 Oct 2026. Evidence as of 5 Oct 2026.