InferIndex
LLM API prices across 70+ providers: cheapest offer, comparisons, history and cost estimates.
사용해야 할까요
품질 및 안전성
도구 정의와 프로토콜 준수에 대한 자동 분석을 기반으로 합니다.
컨텍스트 비용
이는 서버의 도구가 모델의 컨텍스트에 로드될 때마다 소비되는 대략적인 토큰 수입니다. 수치가 높을수록 다른 작업에 사용할 수 있는 주의가 줄어듭니다.
설치
원클릭 설치
`claude_desktop_config.json` 파일에 다음을 추가하세요:
{
"mcpServers": {
"inferindex": {
"url": "https://mcp.inferindex.dev/mcp"
}
}
}원격 엔드포인트
https://mcp.inferindex.dev/mcpstreamable-http할 수 있는 일
도구 목록
도구 (5)
🟢search_models(query)
Find the exact id of an LLM tracked by InferIndex from a name or partial name (e.g. 'deepseek', 'qwen3 max', 'claude opus'). Returns matching model ids and names, best match first.
입력 스키마
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Model name or part of it"
}
},
"required": [
"query"
],
"additionalProperties": false
}🟢cheapest(model, min_context, tools, json, vision, ...)
Cheapest current API offers for one model across direct providers and aggregators, in USD per 1M tokens (input, output, blended 3:1). Stale prices, and flex/batch tiers, are excluded by default. Optional filters (context, tools, JSON, vision, region, no training on prompts, open sign-up) and usage (tokens per request, requests per day) to get an estimated cost per request and per month. Returns the winner and the first offers.
입력 스키마
{
"type": "object",
"properties": {
"model": {
"type": "string",
"description": "Model id or name, e.g. 'deepseek-v3.2', 'deepseek/deepseek-v4-pro', 'gpt-5.6-luna'. Use search_models when unsure."
},
"min_context": {
"type": "integer",
"description": "Minimum context window in tokens",
"minimum": 0
},
"tools": {
"type": "boolean",
"description": "Only offers that support tool calling"
},
"json": {
"type": "boolean",
"description": "Only offers that support JSON output"
},
"vision": {
"type": "boolean",
"description": "Only offers that accept image input"
},
"region": {
"type": "string",
"description": "Only providers that process data in this region: eu, us, …"
},
"no_training": {
"type": "boolean",
"description": "Only providers whose published terms say they do not train on your prompts"
},
"no_waitlist": {
"type": "boolean",
"description": "Only providers with open sign-up (no waitlist or invitation)"
},
"strict": {
"type": "boolean",
"description": "Exclude offers whose provider does not publish the filtered information (by default they are kept and flagged)"
},
"include_tiers": {
"type": "string",
"description": "Also include lower-priority service tiers, comma-separated: flex, batch (hidden by default)"
},
"prompt_tokens": {
"type": "integer",
"description": "Input tokens per request, for the estimated cost",
"minimum": 0
},
"output_tokens": {
"type": "integer",
"description": "Output tokens per request, for the estimated cost",
"minimum": 0
},
"cached_ratio": {
"type": "number",
"minimum": 0,
"maximum": 1,
"description": "Share of input tokens served from the provider's prompt cache (0 to 1)"
},
"requests_per_day": {
"type": "integer",
"description": "Requests per day, to also get an estimated monthly cost",
"minimum": 0
},
"limit": {
"type": "integer",
"description": "Number of offers to return (default 5, max 25)",
"minimum": 1,
"maximum": 25
}
},
"required": [
"model"
],
"additionalProperties": false
}🟢compare_providers(model, sort, limit, region, no_training, ...)
Current offers for one model, one line per provider and source (direct or via an aggregator), cheapest first (10 by default), with price, context, quantization, published conditions (training on prompts, data regions, sign-up) and reliability from official status pages.
입력 스키마
{
"type": "object",
"properties": {
"model": {
"type": "string",
"description": "Model id or name, e.g. 'deepseek-v3.2', 'deepseek/deepseek-v4-pro', 'gpt-5.6-luna'. Use search_models when unsure."
},
"sort": {
"type": "string",
"enum": [
"blended",
"input",
"output",
"estimated_cost"
],
"description": "Sort order (default blended); estimated_cost needs prompt_tokens or output_tokens"
},
"limit": {
"type": "integer",
"description": "Number of offers to return (default 10, max 50)",
"minimum": 1,
"maximum": 50
},
"region": {
"type": "string",
"description": "Only providers that process data in this region: eu, us, …"
},
"no_training": {
"type": "boolean",
"description": "Only providers whose published terms say they do not train on your prompts"
},
"no_waitlist": {
"type": "boolean",
"description": "Only providers with open sign-up (no waitlist or invitation)"
},
"strict": {
"type": "boolean",
"description": "Exclude offers whose provider does not publish the filtered information (by default they are kept and flagged)"
},
"include_tiers": {
"type": "string",
"description": "Also include lower-priority service tiers, comma-separated: flex, batch (hidden by default)"
},
"prompt_tokens": {
"type": "integer",
"description": "Input tokens per request, for the estimated cost",
"minimum": 0
},
"output_tokens": {
"type": "integer",
"description": "Output tokens per request, for the estimated cost",
"minimum": 0
},
"cached_ratio": {
"type": "number",
"minimum": 0,
"maximum": 1,
"description": "Share of input tokens served from the provider's prompt cache (0 to 1)"
},
"requests_per_day": {
"type": "integer",
"description": "Requests per day, to also get an estimated monthly cost",
"minimum": 0
}
},
"required": [
"model"
],
"additionalProperties": false
}🟢price_history(model, days, from, to, at, ...)
Price history of one model: every offer tracked by InferIndex (daily or weekly min/max/last price in USD, or raw price changes), plus the official price of the model's lab over time. Give either days, or from/to (YYYY-MM-DD), or at (a date) for the prices in effect that day.
입력 스키마
{
"type": "object",
"properties": {
"model": {
"type": "string",
"description": "Model id or name, e.g. 'deepseek-v3.2', 'deepseek/deepseek-v4-pro', 'gpt-5.6-luna'. Use search_models when unsure."
},
"days": {
"type": "integer",
"description": "Number of days back from today (default 7)",
"minimum": 1
},
"from": {
"type": "string",
"description": "Start date, YYYY-MM-DD (with to, instead of days)"
},
"to": {
"type": "string",
"description": "End date, YYYY-MM-DD"
},
"at": {
"type": "string",
"description": "A single date, YYYY-MM-DD: prices in effect that day"
},
"granularity": {
"type": "string",
"enum": [
"day",
"week",
"raw"
],
"description": "day (default), week, or raw price changes"
},
"provider": {
"type": "string",
"description": "Only this provider"
},
"limit": {
"type": "integer",
"description": "Maximum number of points (default 100, max 500)",
"minimum": 1,
"maximum": 500
}
},
"required": [
"model"
],
"additionalProperties": false
}🟢estimate_cost(model, prompt_tokens, output_tokens, cached_ratio, requests_per_day, ...)
Estimated cost of a workload on one model at each provider: cost per request, and per month if requests_per_day is given, taking the provider's tiered pricing and prompt-cache price into account. Offers sorted by estimated cost, cheapest first.
입력 스키마
{
"type": "object",
"properties": {
"model": {
"type": "string",
"description": "Model id or name, e.g. 'deepseek-v3.2', 'deepseek/deepseek-v4-pro', 'gpt-5.6-luna'. Use search_models when unsure."
},
"prompt_tokens": {
"type": "integer",
"description": "Input tokens per request, for the estimated cost",
"minimum": 0
},
"output_tokens": {
"type": "integer",
"description": "Output tokens per request, for the estimated cost",
"minimum": 0
},
"cached_ratio": {
"type": "number",
"minimum": 0,
"maximum": 1,
"description": "Share of input tokens served from the provider's prompt cache (0 to 1)"
},
"requests_per_day": {
"type": "integer",
"description": "Requests per day, to also get an estimated monthly cost",
"minimum": 0
},
"limit": {
"type": "integer",
"description": "Number of offers to return (default 5, max 25)",
"minimum": 1,
"maximum": 25
}
},
"required": [
"model"
],
"additionalProperties": false
}커뮤니티
증거