comparedge-llm-costSAFE
MCP server: token cost math for LLM API calls, 69 models across 17 providers, prices verified by ComparEdge
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Someone asks what the AI feature will cost at scale, and the honest answer around most teams is a shrug. Rates moved twice since anyone last checked, and the model itself will happily quote prices from its training data. This MCP server keeps current per-million-token rates for 69 models where your assistant can reach them, and does the arithmetic itself.
Watch it work
$ You: price Claude Opus 4.8 on a 25k-token prompt with a 1k answer, run 5,000 times llm-cost › estimate_cost Cost estimate: Claude Opus 4.8 (Anthropic) Rates: input $5/1M, output $25/1M, cached input $0.5/1M Per call (25,000 in + 1,000 out tokens): input: $0.1250 output: $0.0250 per call total: $0.1500 Across 5,000 calls: $750.00 Ways to pay less for the same 5,000 calls: with cached input: $187.50 via batch API: $375.00
Nothing here is rounded or guessed. The rate is verified, date-stamped, and the server multiplied.
Open a second session: same call across four models, ranked
$ You: compare that call on Opus 4.8, Sonnet 5, GPT-5.6 Terra and Gemini 3.1 Pro llm-cost › compare_models_cost 25,000 in + 1,000 out, cheapest first: 1. Claude Sonnet 5 $0.0600 /call $300.00 /5k 2. Gemini 3.1 Pro $0.0620 /call $310.00 /5k 3. GPT-5.6 Terra $0.0775 /call $387.50 /5k 4. Claude Opus 4.8 $0.1500 /call $750.00 /5k Ranking uses each model's live feed entry, not remembered prices.
The
020d7b39e72cOBSERVED · 2026-10-11Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add llm-cost-mcp -- npx -y @comparedge/[email protected]
Exposed tools (7)
7 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
estimate_my_workflow | read | Estimate the LLM cost of a described workflow. Translates a plain-English description into token counts and a per-run and monthly cost. |
forecast_ai_budget | read | Forecast the monthly and yearly LLM bill for a product feature from expected usage volume. |
model | read | Model to price it on (e.g. |
pick_cheapest_model | read | Recommend the lowest-cost model for a task, respecting any context-window or capability requirement, and price the top candidates. |
task | read | The task and any constraints (e.g. |
usage | read | Expected volume (e.g. |
workflow | read | What the workflow does (e.g. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (2 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
020d7b39e72cfull audit observations/trust-audit/mcp-server/comparedge__llm-cost-mcp.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | 020d7b39e72c | SAFE | B | 89 | first audit |
Questions
What is the comparedge-llm-cost MCP server?
MCP server: token cost math for LLM API calls, 69 models across 17 providers, prices verified by ComparEdge
What tools does comparedge-llm-cost expose?
7 in total: 7 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is comparedge-llm-cost safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does comparedge-llm-cost need?
No credential environment variables were found in its source, so it appears to need none.
How does comparedge-llm-cost run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @comparedge/llm-cost-mcp at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (020d7b39e72c), read on 2026-10-11. The repository is watched and re-audited when it changes.