ai.llmintel/model-lifecycle
LLMIntel Model Lifecycle
ai.llmintel/model-lifecycle costs 713 tokens of context per session. It has 5 tool definitions. That is 0.4 % of a 200k window. Measured 2026-10-03.
Check whether an LLM model id is deprecated, retiring, or retired, and what to migrate to.
alive probed 2026-10-03 · HTTP 200
5tools
713tokens for the tool definitions
0.4 %of a 200k context window
718 msto initialize
472 msto list tools
- Endpoint
- https://llmintel.ai/v1/mcp (streamable-http)
- Host
- llmintel.ai
- Protocol
- 2025-11-25
- Reports itself as
- llmintel 0.2.0
- Capabilities
- tools
- Instructions
- none
- Repository
- https://github.com/hivemindunit/llmintel-mcp
- Website
- https://llmintel.ai
- Registry
- active, updated 2026-07-28 · registry entry
- Reachable
- 2 of the last 2 probes
Most expensive tools
| Tool | Tokens | Share of this server |
|---|---|---|
| search_models | 167 | 23 % |
| check_model | 160 | 22 % |
| list_retiring_models | 149 | 21 % |
| recent_lifecycle_changes | 138 | 19 % |
| suggest_replacement | 99 | 14 % |
History
We add a row when the result changes. A server with no change keeps its last row.
| Probed | Result | Init | Tools | Tokens |
|---|---|---|---|---|
| 2026-10-03 20:26 | alive | 718 ms | 5 | 713 |
| 2026-10-03 17:45 | alive | 747 ms | 5 | 713 |
Badge
[](https://mcp-pulse.ulehla.dev/s/ai.llmintel/model-lifecycle)