Cheapest LLM API
Compare LLM API prices, search models and providers, and access reviewed benchmark results.
¿Debería usar esto?
Calidad y seguridad
A
Basado en el análisis automatizado de las definiciones de herramientas y el cumplimiento del protocolo.
Costo de contexto
~4,357Tokens (definiciones de herramientas)
~6.3 KBTamaño de respuesta típico
Impacto significativo en la atención (3.40% del contexto de 128k)
Este es el número aproximado de tokens que se consumen cada vez que las herramientas del servidor se cargan en el contexto de un modelo. Los recuentos más altos reducen la atención disponible para otras tareas.
Instalar
Instalación con un clic
Agrega esto a tu archivo `claude_desktop_config.json`:
{
"mcpServers": {
"cheapestllmapi": {
"url": "https://cheapestllmapi.com/mcp"
}
}
}Puntos de conexión remotos
https://cheapestllmapi.com/mcpstreamable-httpQué puede hacer
Inventario de herramientas
Herramientas (7)
🟢 Solo lectura🟡 Escritura🔴 Eliminación⚪ Desconocido
🟢catalog_search(query, provider_slug, category_slug, page, page_size)
Find canonical model slugs, context limits, and provider prices. Optional provider_slug filters availability, not the provider in bestOffer. bestOffer is selected for 10M input + 2M output tokens; use offer_compare for your workload. Follow pagination.hasMore.
Esquema de entrada
{
"type": "object",
"properties": {
"query": {
"default": "",
"type": "string",
"maxLength": 80
},
"provider_slug": {
"default": "",
"type": "string",
"maxLength": 80
},
"category_slug": {
"default": "",
"type": "string",
"maxLength": 80
},
"page": {
"default": 1,
"type": "integer",
"minimum": 1,
"maximum": 10000
},
"page_size": {
"default": 25,
"type": "integer",
"minimum": 1,
"maximum": 50
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}Esquema de salida
{
"type": "object",
"properties": {
"meta": {
"type": "object",
"required": [
"apiVersion",
"currency",
"tokenPriceUnit"
],
"properties": {
"apiVersion": {
"const": "v1"
},
"currency": {
"const": "USD"
},
"tokenPriceUnit": {
"const": "per_million_tokens"
}
}
},
"data": {
"type": "object",
"required": [
"models"
],
"properties": {
"models": {
"type": "array",
"items": {
"type": "object",
"required": [
"id",
"slug",
"name",
"author",
"family",
"releasedAt",
"contextTokens",
"maxOutputTokens",
"weightAvailability",
"offerCount",
"bestOffer"
],
"properties": {
"id": {
"type": "string"
},
"slug": {
"type": "string"
},
"name": {
"type": "string"
},
"author": {
"type": "object",
"required": [
"slug",
"name"
],
"properties": {
"slug": {
"type": "string"
},
"name": {
"type": "string"
}
}
},
"family": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"releasedAt": {
"anyOf": [
{
"type": "string",
"format": "date"
},
{
"type": "null"
}
]
},
"contextTokens": {
"anyOf": [
{
"type": "integer",
"minimum": 1
},
{
"type": "null"
}
]
},
"maxOutputTokens": {
"anyOf": [
{
"type": "integer",
"minimum": 1
},
{
"type": "null"
}
]
},
"weightAvailability": {
"type": "string",
"enum": [
"closed",
"open",
"unknown"
]
},
"offerCount": {
"type": "integer",
"minimum": 0
},
"bestOffer": {
"description": "Provider selected using 10 million input and 2 million output tokens; not independent minima or a quote for every workload.",
"anyOf": [
{
"type": "object",
"required": [
"provider",
"prices"
],
"properties": {
"provider": {
"type": "object",
"required": [
"slug",
"name"
],
"properties": {
"slug": {
"type": "string"
},
"name": {
"type": "string"
}
}
},
"prices": {
"type": "object",
"required": [
"inputPerMillionTokens",
"outputPerMillionTokens"
],
"properties": {
"inputPerMillionTokens": {
"type": "number",
"minimum": 0
},
"outputPerMillionTokens": {
"type": "number",
"minimum": 0
}
}
}
}
},
{
"type": "null"
}
]
}
}
}
}
}
},
"pagination": {
"type": "object",
"properties": {
"total": {
"type": "integer",
"minimum": 0
},
"hasMore": {
"type": "boolean"
},
"page": {
"type": "integer",
"minimum": 1
},
"pageSize": {
"type": "integer",
"minimum": 1
},
"pageCount": {
"type": "integer",
"minimum": 0
},
"offset": {
"type": "integer",
"minimum": 0
},
"limit": {
"type": "integer",
"minimum": 1
}
}
}
},
"required": [
"meta",
"data",
"pagination"
]
}🟢model_detail(model_slug)
Get capabilities, context/output limits, and current sourced provider offers by model_slug from catalog_search. Prices are base-context rates; long-context tiers, cache writes, batch discounts, and free-tier quotas can change actual cost.
Esquema de entrada
{
"type": "object",
"properties": {
"model_slug": {
"type": "string",
"minLength": 1,
"maxLength": 120,
"pattern": "^[a-zA-Z0-9._:-]+$"
}
},
"required": [
"model_slug"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}Esquema de salida
{
"type": "object",
"properties": {
"meta": {
"type": "object",
"required": [
"apiVersion",
"currency",
"tokenPriceUnit"
],
"properties": {
"apiVersion": {
"const": "v1"
},
"currency": {
"const": "USD"
},
"tokenPriceUnit": {
"const": "per_million_tokens"
}
}
},
"data": {
"type": "object",
"required": [
"model"
],
"properties": {
"model": {
"type": "object",
"required": [
"id",
"slug",
"name",
"description",
"author",
"family",
"status",
"releaseChannel",
"releasedAt",
"knowledgeCutoffAt",
"contextTokens",
"maxOutputTokens",
"weightAvailability",
"capabilities",
"categories",
"offers"
],
"properties": {
"id": {
"type": "string"
},
"slug": {
"type": "string"
},
"name": {
"type": "string"
},
"description": {
"type": "string"
},
"author": {
"type": "object",
"required": [
"slug",
"name"
],
"properties": {
"slug": {
"type": "string"
},
"name": {
"type": "string"
}
}
},
"family": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"status": {
"type": "string"
},
"releaseChannel": {
"type": "string"
},
"releasedAt": {
"anyOf": [
{
"type": "string",
"format": "date"
},
{
"type": "null"
}
]
},
"knowledgeCutoffAt": {
"anyOf": [
{
"type": "string",
"format": "date"
},
{
"type": "null"
}
]
},
"contextTokens": {
"anyOf": [
{
"type": "integer",
"minimum": 1
},
{
"type": "null"
}
]
},
"maxOutputTokens": {
"anyOf": [
{
"type": "integer",
"minimum": 1
},
{
"type": "null"
}
]
},
"weightAvailability": {
"type": "string"
},
"capabilities": {
"type": "array",
"items": {
"type": "string"
}
},
"categories": {
"type": "array",
"items": {
"type": "object",
"required": [
"slug",
"name"
],
"properties": {
"slug": {
"type": "string"
},
"name": {
"type": "string"
}
}
}
},
"offers": {
"type": "array",
"items": {
"type": "object",
"required": [
"id",
"model",
"provider",
"routeType",
"prices",
"limits",
"provenance"
],
"properties": {
"id": {
"type": "string"
},
"model": {
"type": "object",
"required": [
"slug",
"name"
],
"properties": {
"slug": {
"type": "string"
},
"name": {
"type": "string"
}
}
},
"provider": {
"type": "object",
"required": [
"slug",
"name"
],
"properties": {
"slug": {
"type": "string"
},
"name": {
"type": "string"
}
}
},
"routeType": {
"type": "string",
"enum": [
"official",
"cloud",
"gateway",
"unverified"
]
},
"prices": {
"type": "object",
"required": [
"inputPerMillionTokens",
"outputPerMillionTokens",
"cachedInputPerMillionTokens"
],
"properties": {
"inputPerMillionTokens": {
"type": "number",
"minimum": 0
},
"outputPerMillionTokens": {
"type": "number",
"minimum": 0
},
"cachedInputPerMillionTokens": {
"anyOf": [
{
"type": "number",
"minimum": 0
},
{
"type": "null"
}
]
}
}
},
"limits": {
"type": "object",
"required": [
"contextTokens",
"maxOutputTokens"
],
"properties": {
"contextTokens": {
"anyOf": [
{
"type": "integer",
"minimum": 1
},
{
"type": "null"
}
]
},
"maxOutputTokens": {
"anyOf": [
{
"type": "integer",
"minimum": 1
},
{
"type": "null"
}
]
}
}
},
"provenance": {
"type": "object",
"required": [
"sourceUrl",
"checkedAt"
],
"properties": {
"sourceUrl": {
"type": "string",
"format": "uri"
},
"checkedAt": {
"type": "string",
"format": "date"
}
}
}
}
}
}
}
}
}
}
},
"required": [
"meta",
"data"
]
}🟢offer_compare(model_slugs, provider_slugs, input_tokens, output_tokens)
Rank current provider offers for up to five canonical model slugs by the USD cost of your input/output token workload. Input tokens are uncached. Estimates use base-context rates and exclude long-context tiers, cache writes, batch discounts, and free-tier quotas. provider_slugs restricts the ranked offers.
Esquema de entrada
{
"type": "object",
"properties": {
"model_slugs": {
"minItems": 1,
"maxItems": 5,
"type": "array",
"items": {
"type": "string",
"minLength": 1,
"maxLength": 120,
"pattern": "^[a-zA-Z0-9._:-]+$"
},
"uniqueItems": true
},
"provider_slugs": {
"default": [],
"maxItems": 10,
"type": "array",
"items": {
"type": "string",
"minLength": 1,
"maxLength": 80
},
"uniqueItems": true
},
"input_tokens": {
"default": 10000000,
"type": "integer",
"minimum": 0,
"maximum": 1000000000000
},
"output_tokens": {
"default": 2000000,
"type": "integer",
"minimum": 0,
"maximum": 1000000000000
}
},
"required": [
"model_slugs"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}Esquema de salida
{
"type": "object",
"properties": {
"meta": {
"type": "object",
"required": [
"apiVersion",
"currency",
"tokenPriceUnit"
],
"properties": {
"apiVersion": {
"const": "v1"
},
"currency": {
"const": "USD"
},
"tokenPriceUnit": {
"const": "per_million_tokens"
}
}
},
"workload": {
"type": "object",
"required": [
"inputTokens",
"outputTokens"
],
"properties": {
"inputTokens": {
"type": "integer",
"minimum": 0
},
"outputTokens": {
"type": "integer",
"minimum": 0
}
}
},
"data": {
"type": "object",
"required": [
"offers"
],
"properties": {
"offers": {
"type": "array",
"items": {
"type": "object",
"required": [
"offer",
"workloadCostUsd"
],
"properties": {
"offer": {
"type": "object",
"required": [
"id",
"model",
"provider",
"routeType",
"prices",
"limits",
"provenance"
],
"properties": {
"id": {
"type": "string"
},
"model": {
"type": "object",
"required": [
"slug",
"name"
],
"properties": {
"slug": {
"type": "string"
},
"name": {
"type": "string"
}
}
},
"provider": {
"type": "object",
"required": [
"slug",
"name"
],
"properties": {
"slug": {
"type": "string"
},
"name": {
"type": "string"
}
}
},
"routeType": {
"type": "string",
"enum": [
"official",
"cloud",
"gateway",
"unverified"
]
},
"prices": {
"type": "object",
"required": [
"inputPerMillionTokens",
"outputPerMillionTokens",
"cachedInputPerMillionTokens"
],
"properties": {
"inputPerMillionTokens": {
"type": "number",
"minimum": 0
},
"outputPerMillionTokens": {
"type": "number",
"minimum": 0
},
"cachedInputPerMillionTokens": {
"anyOf": [
{
"type": "number",
"minimum": 0
},
{
"type": "null"
}
]
}
}
},
"limits": {
"type": "object",
"required": [
"contextTokens",
"maxOutputTokens"
],
"properties": {
"contextTokens": {
"anyOf": [
{
"type": "integer",
"minimum": 1
},
{
"type": "null"
}
]
},
"maxOutputTokens": {
"anyOf": [
{
"type": "integer",
"minimum": 1
},
{
"type": "null"
}
]
}
}
},
"provenance": {
"type": "object",
"required": [
"sourceUrl",
"checkedAt"
],
"properties": {
"sourceUrl": {
"type": "string",
"format": "uri"
},
"checkedAt": {
"type": "string",
"format": "date"
}
}
}
}
},
"workloadCostUsd": {
"type": "number",
"minimum": 0
}
}
}
}
}
}
},
"required": [
"meta",
"workload",
"data"
]
}🟢benchmark_results(benchmark_id, offset, limit)
Get reviewed scores for an exact benchmark_id from benchmark_list. Join result.modelId to catalog_search model.id. Compare scores only within the same benchmark edition and configuration. Includes source provenance and reported coding-agent usage when published. Follow pagination.hasMore.
Esquema de entrada
{
"type": "object",
"properties": {
"benchmark_id": {
"type": "string",
"minLength": 1,
"maxLength": 120,
"pattern": "^[a-z0-9-]+$"
},
"offset": {
"default": 0,
"type": "integer",
"minimum": 0,
"maximum": 10000
},
"limit": {
"default": 50,
"type": "integer",
"minimum": 1,
"maximum": 100
}
},
"required": [
"benchmark_id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}Esquema de salida
{
"type": "object",
"properties": {
"meta": {
"type": "object",
"required": [
"apiVersion",
"currency",
"tokenPriceUnit"
],
"properties": {
"apiVersion": {
"const": "v1"
},
"currency": {
"const": "USD"
},
"tokenPriceUnit": {
"const": "per_million_tokens"
}
}
},
"data": {
"type": "object",
"required": [
"benchmark",
"results"
],
"properties": {
"benchmark": {
"type": "object",
"required": [
"id",
"label",
"description",
"version",
"date",
"scoreUnit",
"evaluator",
"configurationNote",
"cohort",
"cohortLabel",
"provenance"
],
"properties": {
"id": {
"type": "string"
},
"label": {
"type": "string"
},
"description": {
"type": "string"
},
"version": {
"type": "string"
},
"date": {
"type": "string",
"description": "Source date, or an empty string when the upstream source supplies none."
},
"scoreUnit": {
"type": "string",
"enum": [
"points",
"percent"
]
},
"evaluator": {
"type": "string"
},
"configurationNote": {
"type": "string"
},
"cohort": {
"type": "string",
"enum": [
"frontier",
"measured"
]
},
"cohortLabel": {
"type": "string"
},
"provenance": {
"type": "object",
"required": [
"sourceUrl",
"sourceLabel"
],
"properties": {
"sourceUrl": {
"type": "string",
"format": "uri"
},
"sourceLabel": {
"type": "string"
}
}
}
}
},
"results": {
"type": "array",
"items": {
"type": "object",
"required": [
"modelId",
"sourceModel",
"configuration",
"score",
"scoreUnit",
"evaluator",
"harness",
"version",
"date",
"dateKind",
"runStartedAt",
"sampleCount",
"standardError",
"reportedAgentUsage",
"provenance"
],
"properties": {
"modelId": {
"type": "string"
},
"sourceModel": {
"type": "string"
},
"configuration": {
"type": "string"
},
"score": {
"type": "number",
"minimum": 0,
"maximum": 100
},
"scoreUnit": {
"type": "string",
"enum": [
"points",
"percent"
]
},
"evaluator": {
"type": "string"
},
"harness": {
"type": "string"
},
"version": {
"type": "string"
},
"date": {
"type": "string",
"format": "date"
},
"dateKind": {
"type": "string",
"enum": [
"source-update",
"run"
]
},
"runStartedAt": {
"anyOf": [
{
"type": "string",
"format": "date-time"
},
{
"type": "null"
}
]
},
"sampleCount": {
"anyOf": [
{
"type": "integer",
"minimum": 1
},
{
"type": "null"
}
]
},
"standardError": {
"anyOf": [
{
"type": "number",
"minimum": 0
},
{
"type": "null"
}
]
},
"reportedAgentUsage": {
"anyOf": [
{
"type": "object",
"required": [
"agent",
"agentVersion",
"trialCount",
"tokens",
"reportedCostUsd",
"averageTrialDurationSeconds",
"derived"
],
"properties": {
"agent": {
"type": "string"
},
"agentVersion": {
"type": "string"
},
"trialCount": {
"type": "integer",
"minimum": 1
},
"tokens": {
"type": "object",
"required": [
"uncachedInput",
"cachedInput",
"output",
"total"
],
"properties": {
"uncachedInput": {
"type": "integer",
"minimum": 0
},
"cachedInput": {
"type": "integer",
"minimum": 0
},
"output": {
"type": "integer",
"minimum": 0
},
"total": {
"type": "integer",
"minimum": 0
}
}
},
"reportedCostUsd": {
"type": "number",
"minimum": 0
},
"averageTrialDurationSeconds": {
"type": "number",
"minimum": 0
},
"derived": {
"type": "object",
"description": "Values derived from the published run totals and rounded benchmark score.",
"required": [
"costPerTrialUsd",
"costPerSuccessfulTrialUsd",
"inputCacheShare",
"tokensPerSuccessfulTrial"
],
"properties": {
"costPerTrialUsd": {
"type": "number",
"minimum": 0
},
"costPerSuccessfulTrialUsd": {
"type": "number",
"minimum": 0
},
"inputCacheShare": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"tokensPerSuccessfulTrial": {
"type": "number",
"minimum": 0
}
}
}
}
},
{
"type": "null"
}
]
},
"provenance": {
"type": "object",
"required": [
"sourceUrl",
"sourceDataUrl",
"sourceRecordId"
],
"properties": {
"sourceUrl": {
"type": "string",
"format": "uri"
},
"sourceDataUrl": {
"type": "string",
"format": "uri"
},
"sourceRecordId": {
"type": "string"
}
}
}
}
}
}
}
},
"pagination": {
"type": "object",
"properties": {
"total": {
"type": "integer",
"minimum": 0
},
"hasMore": {
"type": "boolean"
},
"page": {
"type": "integer",
"minimum": 1
},
"pageSize": {
"type": "integer",
"minimum": 1
},
"pageCount": {
"type": "integer",
"minimum": 0
},
"offset": {
"type": "integer",
"minimum": 0
},
"limit": {
"type": "integer",
"minimum": 1
}
}
}
},
"required": [
"meta",
"data",
"pagination"
]
}🟢provider_list
Discover accepted provider slugs, roles, and current comparable model/offer counts. Provider minimum input and output prices are independent minima and may belong to different models; use offer_compare for an actual quote.
Esquema de entrada
{
"type": "object",
"properties": {},
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}Esquema de salida
{
"type": "object",
"properties": {
"meta": {
"type": "object",
"required": [
"apiVersion",
"currency",
"tokenPriceUnit"
],
"properties": {
"apiVersion": {
"const": "v1"
},
"currency": {
"const": "USD"
},
"tokenPriceUnit": {
"const": "per_million_tokens"
}
}
},
"data": {
"type": "object",
"required": [
"providers"
],
"properties": {
"providers": {
"type": "array",
"items": {
"type": "object",
"required": [
"id",
"slug",
"name",
"homepageUrl",
"roles",
"modelCount",
"offerCount",
"minimumPrices"
],
"properties": {
"id": {
"type": "string"
},
"slug": {
"type": "string"
},
"name": {
"type": "string"
},
"homepageUrl": {
"anyOf": [
{
"type": "string",
"format": "uri"
},
{
"type": "null"
}
]
},
"roles": {
"type": "array",
"items": {
"type": "string"
}
},
"modelCount": {
"type": "integer",
"minimum": 0
},
"offerCount": {
"type": "integer",
"minimum": 0
},
"minimumPrices": {
"description": "Independent provider-wide minima; input and output may belong to different models.",
"type": "object",
"required": [
"inputPerMillionTokens",
"outputPerMillionTokens"
],
"properties": {
"inputPerMillionTokens": {
"anyOf": [
{
"type": "number",
"minimum": 0
},
{
"type": "null"
}
]
},
"outputPerMillionTokens": {
"anyOf": [
{
"type": "number",
"minimum": 0
},
{
"type": "null"
}
]
}
}
}
}
}
}
}
}
},
"required": [
"meta",
"data"
]
}🟢benchmark_list
Discover exact benchmark IDs, editions, score units, configurations, provenance, and reviewed result counts before calling benchmark_results. Empty benchmarks are retained with resultCount 0.
Esquema de entrada
{
"type": "object",
"properties": {},
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}Esquema de salida
{
"type": "object",
"properties": {
"meta": {
"type": "object",
"required": [
"apiVersion",
"currency",
"tokenPriceUnit"
],
"properties": {
"apiVersion": {
"const": "v1"
},
"currency": {
"const": "USD"
},
"tokenPriceUnit": {
"const": "per_million_tokens"
}
}
},
"data": {
"type": "object",
"required": [
"benchmarks"
],
"properties": {
"benchmarks": {
"type": "array",
"items": {
"type": "object",
"required": [
"id",
"label",
"description",
"version",
"date",
"scoreUnit",
"evaluator",
"configurationNote",
"cohort",
"cohortLabel",
"provenance",
"resultCount"
],
"properties": {
"id": {
"type": "string"
},
"label": {
"type": "string"
},
"description": {
"type": "string"
},
"version": {
"type": "string"
},
"date": {
"type": "string",
"description": "Source date, or an empty string when the upstream source supplies none."
},
"scoreUnit": {
"type": "string",
"enum": [
"points",
"percent"
]
},
"evaluator": {
"type": "string"
},
"configurationNote": {
"type": "string"
},
"cohort": {
"type": "string",
"enum": [
"frontier",
"measured"
]
},
"cohortLabel": {
"type": "string"
},
"provenance": {
"type": "object",
"required": [
"sourceUrl",
"sourceLabel"
],
"properties": {
"sourceUrl": {
"type": "string",
"format": "uri"
},
"sourceLabel": {
"type": "string"
}
}
},
"resultCount": {
"type": "integer",
"minimum": 0
}
}
}
}
}
}
},
"required": [
"meta",
"data"
]
}🟢execute(code)
Run a JavaScript async function in an isolated sandbox, composing catalog_search, model_detail, offer_compare, benchmark_results, provider_list, and benchmark_list as catalog.* methods. Return a small JSON value. Example: async () => { const page = await catalog.catalog_search({query: 'claude', page_size: 5}); return page.data.models.map(m => ({slug: m.slug, prices: m.bestOffer?.prices})); }. No network, secrets, or database binding is exposed. Shared worldwide execution budgets: 100 per UTC minute and 5000 per UTC day. Limits: 30 executions per client per minute (IPv6 /64), 20 catalog calls and read units (offer_compare uses 5), at most two concurrent calls, 5 seconds wall time, 50ms sandbox CPU, 32KiB code, 64KiB JSON output. JavaScript only; no imports or TypeScript syntax. Use /mcp?mode=code for only search + execute.
Esquema de entrada
{
"type": "object",
"properties": {
"code": {
"type": "string",
"minLength": 1,
"maxLength": 32768
}
},
"required": [
"code"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}Esquema de salida
{
"type": "object",
"properties": {
"result": {},
"logs": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 20
},
"calls": {
"type": "integer",
"minimum": 0,
"maximum": 20
}
},
"required": [
"result",
"logs",
"calls"
]
}Comunidad
Evidencia
Observaciones recientes
verificadoversión no registrada7 herramientas