io.github.waqarulwahab/llm-cost-estimator
llm-cost-estimator
Token counting & multi-model LLM cost estimates: GPT-4o, Claude, Gemini, 25+. No API key.
alive probed 2026-10-14
3tools
712tokens in Claude Opus 5.5
754tokens in Claude Code
0.4 %of a 200k context window
417o200k_base estimate
161 msto initialize
12 msto list tools
- Run it
- npx -y llm-cost-estimator-mcp@0.3.1 (stdio, probed in a container with the network off)
- Host
- npmjs.com
- Reports itself as
- llm-cost-estimator 0.3.1
- Capabilities
- tools
- Instructions
- none
- Claude count
- Claude Opus 5.5, measured 2026-10-14. Counted again when the tool definitions change. Method.
- Repository
- https://github.com/waqarulwahab/llm-cost-estimator
- Registry
- active, updated 2026-06-21 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| estimate_cost | 237 | 57 % |
| count_tokens | 113 | 27 % |
| list_models | 67 | 16 % |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.waqarulwahab/llm-cost-estimator)
An entry for every probe that changed the result, the tool count or the token cost: Atom feed. Add it to a feed reader or a Slack RSS app to hear when the server stops answering or its tool set grows.