io.github.OptimNow/ai-pricing-hub
OptimToken
Compare LLM API and cloud compute pricing, estimate workload costs, pick a model within budget.
alive probed 2026-10-14 · HTTP 200
5tools
4.8ktokens in Claude Opus 5.5
4.8ktokens in Claude Code
2.4 %of a 200k context window
2.9ko200k_base estimate
1.4 sto initialize
493 msto list tools
- Endpoint
- https://optimtoken-mcp.optimnow.io/mcp (streamable-http)
- Host
- optimtoken-mcp.optimnow.io
- Protocol
- 2025-11-25
- Reports itself as
- ai-pricing-hub 0.4.2
- Capabilities
- resources, 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/OptimNow/ai-pricing-hub-mcp
- Website
- https://optimtoken.optimnow.io/mcp
- Registry
- active, updated 2026-10-07 · registry entry
- Reachable
- 10 of the last 10 probes
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| compare-llm-models | 775 | 27 % |
| recommend-llm-model | 611 | 21 % |
| compare-compute-pricing | 597 | 21 % |
| estimate-llm-cost | 595 | 21 % |
| compare-models-side-by-side | 299 | 10 % |
History
We add a row when the result changes. A server with no change keeps its last row.
| Probed | Result | Init | Tools | Claude | o200k |
|---|---|---|---|---|---|
| 2026-10-14 09:20 | alive | 898 ms | 5 | 4.8k | 2.9k |
| 2026-10-08 11:11 | alive | 1.4 s | 5 | 4.8k | 2.9k |
| 2026-10-07 11:09 | paid (402) | ||||
| 2026-10-06 10:58 | alive | 1.1 s | 5 | 4.8k | 2.9k |
| 2026-10-05 14:24 | alive | 4.4 s | 5 | 4.8k | 2.8k |
| 2026-10-05 00:30 | alive | 679 ms | 5 | 2.8k | |
| 2026-10-04 10:02 | alive | 1.4 s | 5 | 2.8k | |
| 2026-10-04 07:56 | alive | 4.0 s | 5 | 2.8k | |
| 2026-10-03 20:36 | alive | 1.3 s | 5 | 2.8k | |
| 2026-10-03 17:52 | alive | 884 ms | 5 | 2.8k |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.OptimNow/ai-pricing-hub)
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.