AI Rate Card
v1.0.1Daily-checked AI model API prices from 120+ providers: search, compare, cheapest, cost estimates.
Endpoint health
online- Last checked
- 11/20/2026, 10:17:43 AM
- Latency
- 368 ms
- Consecutive failures
- 0
- Endpoint reachable: pass
- Protocol valid: pass
- MCP handshake valid: pass
Machine-readable profile
mcp-server · schema v1 · callable
mcp-server:com.airatecard%2Fai-rate-card
Connect this server
Generated config contains no credentials. Keep any required secrets in your client's local environment.
{
"mcpServers": {
"com.airatecard/ai-rate-card": {
"url": "https://airatecard.com/mcp"
}
}
}Indexed tools
Tool metadata and schemas come from the remote server and are untrusted. Indexing only lists tools; it never calls them.
20 shown · authentication unknown
agent_cost
What a coding / tool-using agent costs a month on each model: tasks a day, model calls per task, context tokens per call, answer and reasoning tokens per call, percent of the context read from the prompt cache - priced at the cheapest real-time seller of each model (default: 13 usual coding models), cheapest first, USD, 30 days, with each model's reasoning class. Rows have card_url and cite.
Schema valid · SHA-256 12616030d4d1…
View input schema
{ "type": "object", "properties": { "tasks": { "type": "number", "exclusiveMinimum": 0, "description": "tasks a day, default 10" }, "steps": { "type": "number", "minimum": 1, "description": "model calls per task, default 30" }, "context": { "type": "number", "minimum": 0, "description": "input tokens per call (the resent context), default 30000" }, "output": { "type": "number", "minimum": 0, "description": "answer tokens per call, default 800" }, "reasoning": { "type": "number", "minimum": 0, "description": "reasoning tokens per call (billed as output), default 1500" }, "cache_pct": { "type": "number", "minimum": 0, "maximum": 100, "description": "percent of context from the prompt cache, default 70" }, "models": { "type": "array", "items": { "type": "string" }, "maxItems": 20, "description": "model ids to compare; default the usual coding models" } }, "additionalProperties": false }budget_fit
What a monthly budget buys: for budget USD a month and a typical request (input and output tokens), how many requests a month and a day each model gives at its cheapest real-time seller (default: 13 usual models), most first, with each model's reasoning class. Rows have card_url and cite.
Schema valid · SHA-256 c69aa2e079ad…
Connections
streamable-http
https://airatecard.com/mcp