Measured latency, time to first token and uptime for ~45 AI inference APIs, by region.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Measured latency (TTFB p50/p95) and uptime rankings of AI inference API providers by region, from llmlatency.dev.
eu-hetzner, us-central, ap-tokyo or sa-east; omit for all
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Measured latency (TTFB p50/p95) and uptime rankings of AI inference API providers by region, from llmlatency.dev.
| Argument | Type | Description |
|---|---|---|
| region | string | eu-hetzner, us-central, ap-tokyo or sa-east; omit for all |
{
"type": "object",
"properties": {
"region": {
"type": "string",
"description": "eu-hetzner, us-central, ap-tokyo or sa-east; omit for all"
}
}
}AI model deprecation calendar: announced and shutdown dates, replacement models, and how many days of migration notice each provider actually gives (median/min/max). Every entry is verified against the provider own deprecation page.
| Argument | Type | Description |
|---|---|---|
| provider | string | openai, anthropic, google, mistral, cohere, azure-openai; omit for all |
{
"type": "object",
"properties": {
"provider": {
"type": "string",
"description": "openai, anthropic, google, mistral, cohere, azure-openai; omit for all"
}
}
}