OpenRouter measures token cost of MCP, CLI and skills
Start here
OpenRouter measured the context token cost of three ways to give a model GitHub access — the GitHub MCP server, the gh CLI and a gh skill — on one GitHub task. On Claude Sonnet 5.5 all three answered correctly, but the CLI used 1,421 input tokens, the skill 3,315 and the MCP server 59,417 with its 46 default tools, whose definitions alone add 19,436 tokens per request. Scoping the server to two tools cut the task to 23,228 tokens, capping results at 4,000 characters brought it to 5,357, and Tool Search cut the up-front cost of 46 tools to under 600 tokens. Tool Search halved the whole-task cost on Sonnet 5.5 but raised it on Claude Haiku 5.5, OpenRouter says. Tool Search is in beta and works with any model and provider on the Responses and Messages APIs; Chat Completions rejects it with a 400 error. OpenRouter tested one server on one task and advises running its mcp_cost.py on your own setup before deciding.
Generated from reports · updated 13 h ago
Report timeline
Follow the reports to see the event from different sides.
- OpenRouter AnnouncementsPicksOpenRouter measures the context cost of MCP, CLI and skills on one GitHub task
OpenRouter measured the same GitHub task across the GitHub MCP server, the gh CLI and a gh skill on Claude Sonnet 5.5, GPT-6 Luna and Gemini 3.8 Flash. On Sonnet 5.5 all three answered correctly, but the CLI used 1,421 input tokens, the skill 3,315 and the MCP server 59,417 with its 46 default tools, whose definitions alone add 19,436 tokens per request. Scoping the server to two tools cut the task to 23,228 tokens, capping results at 4,000 characters brought it to 5,357, and Tool Search cut the up-front cost of 46 tools to under 600 tokens, though it halved the whole-task cost on Sonnet 5.5 while raising it on Claude Haiku 5.5.
Heat for this event
Not enough continuous observations yet to draw a trend.