A remote MCP server that lets an assistant compare live LLM API prices across providers, check provider status, and track price history and changes.
What you can do
Find the cheapest models meeting a minimum context window and provider filter, ranked by blended cost per million tokens, to route an agent to a low-cost operational model. Read dated input and output price history for a single model to spot cuts and trends. Check current operational status for one or all AI API providers, sourced from their public status pages. Subscribe a webhook to be notified of provider price changes, or read recent changes filtered by provider and direction.
When to use it
Useful when choosing or switching LLM providers and models on cost, when you want to confirm a provider is currently operational before routing work to it, or when you want to watch for price cuts and raises over time.
Requirements
Remote streamable HTTP endpoint; no package, environment variables or headers declared. No authentication is declared. Network access to the endpoint is needed, and a reachable webhook URL if you subscribe to price-change alerts.
Before you install
Subscribing a webhook sends that URL to a third party and causes the service to call it when prices change. Price and status data come from the provider's own aggregation of public sources and may lag or be incomplete, so verify before relying on it for spending decisions.
Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/com.dropwatchhq%2Fai-api-radar/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.
Return the cheapest LLM API models that meet a constraint, ranked by blended $/M-token cost. Use this to route an agent to the lowest-cost model with enough context that is currently operational. Filter by minimum context window and provider; weight input vs output cost for your workload.
Return the dated $/M-token price history (input + output) for one model. This is AI API Radar's exclusive time-series — useful for spotting price-war cuts and trend.
Parametersmodelrequired
status
Current operational status for one or all AI API providers (from each provider's public status page).
Parametersprovider
price_change_alerts
Subscribe a webhook to fire when a provider changes prices (or read recent price changes). Pass `webhook` to subscribe (optionally filter by provider and direction 'cut'|'raise'); omit to read recent changes.
Parameterslimitwebhookproviderdirection
Version history
1
v1.0.1LatestSep 16, 2026
Score
72%
72% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
Reached in the last 30 daysRequired25 pts
Auth declaredRequired10 pts
Tools listedRequired15 pts
DescriptionRequired15 pts
Logo10 pts
Publish an icon in the registry entry.
Documentation15 pts
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
LicenseNot applicable
A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.