Grandet

Official6 toolsLive

by hanzohanzhe · JavaScript

Cheapest API for any model across official, inference and relay providers; find free credits

MCP Server: io.github.hanzohanzhe/grandet

The MCP server io.github.hanzohanzhe/grandet provides access to an API described as the “cheapest API for any model” across “official, inference and relay providers.” Its stated purpose is to help users find free credits. The catalog data also associates the server with the slug io-github-hanzohanzhe-grandet.

🛠️ Key Features

Provides an API spanning official, inference, and relay providers
Positioned to help users find free credits
Described as the “cheapest API for any model”

🚀 Use Cases

Searching across multiple provider types (official, inference, relay)
Finding available free credits for model access

⚡ Developer Benefits

Single integration point for the described multi-provider API
Developer access to a “free credits” discovery approach

⚠️ Limitations

Catalog data does not specify tools, configuration, authentication details, or supported operations

Topics

aiapi-creditsdeveloper-toolsfree-apifree-tieragent-skillsai-agentsapi-pricingapi-relayclaude-codecodexllmllm-apimcpmcp-serverprice-comparison

Captured live from the server via tools/list.

grandet_find_cheapest_api

Compare Grandet model prices within each unit. Read listings for price-only ordering and conditions; legacy recommended/alternative/cheapest retain their old meanings. Use view=compact for shared connection cards and a short text response. Provide exactly one model or name selector. host records the source only and never selects the inference route. Send targetApp when the user or conversation identifies the intended API application, including explicit use in the current app. With no target, compare directly. An unrecorded app connection permits a price-only recommendation, not a compatibility claim. Omit profile/protocol for a multi-protocol app unless already specified. Existing client remains a legacy target-app alias. Infer coding/chat/long_output from the task; presets are estimates. Use grandet_list_apps only when application facts are needed. Do not request API keys. view defaults to "compact"; pass view="full" for every field.

Parameters19

host	string	optional	The assistant or app making this call, e.g. "claude-code" or "codex". Attribution only; it does not change results.
targetApp	string	optional	Catalogue ID of the app that will use the API, e.g. "openclaw", "claude-code" or "codex". Selects compatible protocols and connection steps. Send it only when the user says where the API will be used.
skillVersion	string	optional	Grandet Skill version when called from the Skill, e.g. "0.3.0". Omit otherwise.
skillBuild	string	optional	Grandet Skill build ID when called from the Skill. Omit otherwise.
model	string	optional	Model to look up: a catalogue ID, an exact model name or a natural name such as "claude-sonnet-5-5". Send exactly one of model or name. An ambiguous name returns NEEDS_CLARIFICATION with candidates.
name	string	optional	The catalogue's 20-character hexadecimal raw-name ID (not the name text). Send exactly one of model or name.
view	string	optional	"compact" (default): a short text summary plus the listings, with connection cards shared in integrationCards; about a third of the size. "full": every legacy field, with the whole JSON repeated as text. "brief": a short text summary plus one structured body preserving required original fields; size varies with the requested limit and results and can exceed 12,000 characters.
mix	string	optional	Workload used to blend input, cache and output prices into one price per million total tokens. Presets "chat" (default), "coding" and "long_output", or custom input/cache-read/output/cache-write shares totalling 100.
endpointType	string	optional	Limit to one API protocol. Send it only when the user named a protocol.
currency	string	optional	Limit to one unit board: USD_CREDIT or CNY_CREDIT (site credit, not cash), USD or CNY (cash). Never compare prices across units.
channel	string	optional	"standard" (default) lists ordinary channels, "declared-nonstandard" only channels the site itself labels nonstandard, "all" both.
plans	string	optional	"best" (default) keeps one group per site; "all" lists every group of every site.
limit	integer	optional	Rows per block, 1–20 (default 5).
releaseSet	string	optional	Pin a published data release by its release-set hash. Omit to use the current release.
asOf	string	optional	Evaluate as of this UTC time (ISO 8601, e.g. "2026-10-16T12:00:00Z"). Omit to evaluate now.
client	string	optional	Legacy alias of targetApp. Prefer targetApp.
targetProfile	string	optional	An inference profile ID of the target app (see grandet_list_apps). Only together with targetApp or client.
lang	string	optional	Answer language: "en" or "zh-CN".
os	string	optional	Operating system the target app runs on, for connection steps: windows, macos, linux or unknown.

Raw schema

{
  "type": "object",
  "properties": {
    "host": {
      "type": "string",
      "pattern": "^[a-zA-Z0-9._/-]{1,64}$",
      "description": "The assistant or app making this call, e.g. \"claude-code\" or \"codex\". Attribution only; it does not change results."
    },
    "targetApp": {
      "type": "string",
      "pattern": "^[a-zA-Z0-9._/-]{1,64}$",
      "description": "Catalogue ID of the app that will use the API, e.g. \"openclaw\", \"claude-code\" or \"codex\". Selects compatible protocols and connection steps. Send it only when the user says where the API will be used."
    },
    "skillVersion": {
      "type": "string",
      "maxLength": 32,
      "description": "Grandet Skill version when called from the Skill, e.g. \"0.3.0\". Omit otherwise."
    },
    "skillBuild": {
      "type": "string",
      "pattern": "^[a-zA-Z0-9._-]{1,96}$",
      "description": "Grandet Skill build ID when called from the Skill. Omit otherwise."
    },
    "model": {
      "type": "string",
      "minLength": 1,
      "maxLength": 256,
      "description": "Model to look up: a catalogue ID, an exact model name or a natural name such as \"claude-sonnet-5-5\". Send exactly one of model or name. An ambiguous name returns NEEDS_CLARIFICATION with candidates."
    },
    "name": {
      "type": "string",
      "minLength": 1,
      "maxLength": 256,
      "description": "The catalogue's 20-character hexadecimal raw-name ID (not the name text). Send exactly one of model or name."
    },
    "view": {
      "type": "string",
      "enum": [
        "full",
        "compact",
        "brief"
      ],
      "description": "\"compact\" (default): a short text summary plus the listings, with connection cards shared in integrationCards; about a third of the size. \"full\": every legacy field, with the whole JSON repeated as text. \"brief\": a short text summary plus one structured body preserving required original fields; size varies with the requested limit and results and can exceed 12,000 characters.",
      "default": "compact"
    },
    "mix": {
      "type": "string",
      "maxLength": 120,
      "description": "Workload used to blend input, cache and output prices into one price per million total tokens. Presets \"chat\" (default), \"coding\" and \"long_output\", or custom input/cache-read/output/cache-write shares totalling 100."
    },
    "endpointType": {
      "type": "string",
      "enum": [
        "openai",
        "openai-response",
        "anthropic",
        "gemini"
      ],
      "description": "Limit to one API protocol. Send it only when the user named a protocol."
    },
    "currency": {
      "type": "string",
      "enum": [
        "USD_CREDIT",
        "CNY_CREDIT",
        "USD",
        "CNY"
      ],
      "description": "Limit to one unit board: USD_CREDIT or CNY_CREDIT (site credit, not cash), USD or CNY (cash). Never compare prices across units."
    },
    "channel": {
      "type": "string",
      "enum": [
        "standard",
        "declared-nonstandard",
        "all"
      ],
      "description": "\"standard\" (default) lists ordinary channels, \"declared-nonstandard\" only channels the site itself labels nonstandard, \"all\" both."
    },
    "plans": {
      "type": "string",
      "enum": [
        "best",
        "all"
      ],
      "description": "\"best\" (default) keeps one group per site; \"all\" lists every group of every site."
    },
    "limit": {
      "type": "integer",
      "maximum": 20,
      "minimum": 1,
      "default": 5,
      "description": "Rows per block, 1–20 (default 5)."
    },
    "releaseSet": {
      "type": "string",
      "minLength": 1,
      "maxLength": 256,
      "description": "Pin a published data release by its release-set hash. Omit to use the current release."
    },
    "asOf": {
      "type": "string",
      "minLength": 1,
      "maxLength": 256,
      "description": "Evaluate as of this UTC time (ISO 8601, e.g. \"2026-10-16T12:00:00Z\"). Omit to evaluate now."
    },
    "client": {
      "type": "string",
      "pattern": "^[a-zA-Z0-9._/-]{1,64}$",
      "description": "Legacy alias of targetApp. Prefer targetApp."
    },
    "targetProfile": {
      "type": "string",
      "pattern": "^[a-zA-Z0-9._/-]{1,64}$",
      "description": "An inference profile ID of the target app (see grandet_list_apps). Only together with targetApp or client."
    },
    "lang": {
      "type": "string",
      "enum": [
        "en",
        "zh-CN"
      ],
      "default": "en",
      "description": "Answer language: \"en\" or \"zh-CN\"."
    },
    "os": {
      "type": "string",
      "enum": [
        "windows",
        "macos",
        "linux",
        "unknown"
      ],
      "default": "unknown",
      "description": "Operating system the target app runs on, for connection steps: windows, macos, linux or unknown."
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

grandet_list_apps

Read the shared Grandet application list and inference profiles before selecting a supplier. App profiles determine API compatibility; MCP capability alone does not prove an inference route or Skill installation. Use only when the target app ID, supported protocol or configuration variant is uncertain.

Parameters6

host	string	optional	The assistant or app making this call, e.g. "claude-code" or "codex". Attribution only; it does not change results.
targetApp	string	optional	Catalogue ID of the app that will use the API, e.g. "openclaw", "claude-code" or "codex". Selects compatible protocols and connection steps. Send it only when the user says where the API will be used.
skillVersion	string	optional	Grandet Skill version when called from the Skill, e.g. "0.3.0". Omit otherwise.
skillBuild	string	optional	Grandet Skill build ID when called from the Skill. Omit otherwise.
app	string	optional	Catalogue app ID to show, e.g. "openclaw". Omit to list every app.
lang	string	optional	Answer language: "en" or "zh-CN".

Raw schema

{
  "type": "object",
  "properties": {
    "host": {
      "type": "string",
      "pattern": "^[a-zA-Z0-9._/-]{1,64}$",
      "description": "The assistant or app making this call, e.g. \"claude-code\" or \"codex\". Attribution only; it does not change results."
    },
    "targetApp": {
      "type": "string",
      "pattern": "^[a-zA-Z0-9._/-]{1,64}$",
      "description": "Catalogue ID of the app that will use the API, e.g. \"openclaw\", \"claude-code\" or \"codex\". Selects compatible protocols and connection steps. Send it only when the user says where the API will be used."
    },
    "skillVersion": {
      "type": "string",
      "maxLength": 32,
      "description": "Grandet Skill version when called from the Skill, e.g. \"0.3.0\". Omit otherwise."
    },
    "skillBuild": {
      "type": "string",
      "pattern": "^[a-zA-Z0-9._-]{1,96}$",
      "description": "Grandet Skill build ID when called from the Skill. Omit otherwise."
    },
    "app": {
      "type": "string",
      "pattern": "^[a-zA-Z0-9._/-]{1,64}$",
      "description": "Catalogue app ID to show, e.g. \"openclaw\". Omit to list every app."
    },
    "lang": {
      "type": "string",
      "enum": [
        "en",
        "zh-CN"
      ],
      "default": "en",
      "description": "Answer language: \"en\" or \"zh-CN\"."
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

grandet_resolve_model

Look up public model identifiers when a requested name is ambiguous. Results are a page of candidates, not a cheapest-provider ranking. Prefer an exact officialId match; do not silently substitute a different model generation.

Parameters7

host	string	optional	The assistant or app making this call, e.g. "claude-code" or "codex". Attribution only; it does not change results.
targetApp	string	optional	Catalogue ID of the app that will use the API, e.g. "openclaw", "claude-code" or "codex". Selects compatible protocols and connection steps. Send it only when the user says where the API will be used.
skillVersion	string	optional	Grandet Skill version when called from the Skill, e.g. "0.3.0". Omit otherwise.
skillBuild	string	optional	Grandet Skill build ID when called from the Skill. Omit otherwise.
name	string	required	Model name text to look up, e.g. "sonnet" or "deepseek v4".
page	integer	optional	Result page, starting at 1.
lang	string	optional	Answer language: "en" or "zh-CN".

Raw schema

{
  "type": "object",
  "properties": {
    "host": {
      "type": "string",
      "pattern": "^[a-zA-Z0-9._/-]{1,64}$",
      "description": "The assistant or app making this call, e.g. \"claude-code\" or \"codex\". Attribution only; it does not change results."
    },
    "targetApp": {
      "type": "string",
      "pattern": "^[a-zA-Z0-9._/-]{1,64}$",
      "description": "Catalogue ID of the app that will use the API, e.g. \"openclaw\", \"claude-code\" or \"codex\". Selects compatible protocols and connection steps. Send it only when the user says where the API will be used."
    },
    "skillVersion": {
      "type": "string",
      "maxLength": 32,
      "description": "Grandet Skill version when called from the Skill, e.g. \"0.3.0\". Omit otherwise."
    },
    "skillBuild": {
      "type": "string",
      "pattern": "^[a-zA-Z0-9._-]{1,96}$",
      "description": "Grandet Skill build ID when called from the Skill. Omit otherwise."
    },
    "name": {
      "type": "string",
      "minLength": 1,
      "maxLength": 256,
      "description": "Model name text to look up, e.g. \"sonnet\" or \"deepseek v4\"."
    },
    "page": {
      "type": "integer",
      "minimum": 1,
      "default": 1,
      "description": "Result page, starting at 1."
    },
    "lang": {
      "type": "string",
      "enum": [
        "en",
        "zh-CN"
      ],
      "default": "en",
      "description": "Answer language: \"en\" or \"zh-CN\"."
    }
  },
  "required": [
    "name"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

grandet_quote_evidence

Read one provider's paged public declarations for a model and optional rowId. Use only when a detail matters, not before every recommendation. A missing row on one page is not proof of absence; follow pagination if needed. This does not test model quality or spend money.

Parameters12

host	string	optional	The assistant or app making this call, e.g. "claude-code" or "codex". Attribution only; it does not change results.
targetApp	string	optional	Catalogue ID of the app that will use the API, e.g. "openclaw", "claude-code" or "codex". Selects compatible protocols and connection steps. Send it only when the user says where the API will be used.
skillVersion	string	optional	Grandet Skill version when called from the Skill, e.g. "0.3.0". Omit otherwise.
skillBuild	string	optional	Grandet Skill build ID when called from the Skill. Omit otherwise.
model	string	optional	Model to look up: a catalogue ID, an exact model name or a natural name such as "claude-sonnet-5-5". Send exactly one of model or name. An ambiguous name returns NEEDS_CLARIFICATION with candidates.
name	string	optional	The catalogue's 20-character hexadecimal raw-name ID (not the name text). Send exactly one of model or name.
provider	string	required	The sourceId of the row to inspect (the site host, e.g. "api.example.com"), not the operator ID.
rowId	string	optional	The rowId of the selected row, to read that exact declaration.
offerPage	integer	optional	Page of this provider's declarations, starting at 1. Follow it when rowId is absent.
releaseSet	string	optional	Pin a published data release by its release-set hash. Omit to use the current release.
asOf	string	optional	Evaluate as of this UTC time (ISO 8601, e.g. "2026-10-16T12:00:00Z"). Omit to evaluate now.
lang	string	optional	Answer language: "en" or "zh-CN".

Raw schema

{
  "type": "object",
  "properties": {
    "host": {
      "type": "string",
      "pattern": "^[a-zA-Z0-9._/-]{1,64}$",
      "description": "The assistant or app making this call, e.g. \"claude-code\" or \"codex\". Attribution only; it does not change results."
    },
    "targetApp": {
      "type": "string",
      "pattern": "^[a-zA-Z0-9._/-]{1,64}$",
      "description": "Catalogue ID of the app that will use the API, e.g. \"openclaw\", \"claude-code\" or \"codex\". Selects compatible protocols and connection steps. Send it only when the user says where the API will be used."
    },
    "skillVersion": {
      "type": "string",
      "maxLength": 32,
      "description": "Grandet Skill version when called from the Skill, e.g. \"0.3.0\". Omit otherwise."
    },
    "skillBuild": {
      "type": "string",
      "pattern": "^[a-zA-Z0-9._-]{1,96}$",
      "description": "Grandet Skill build ID when called from the Skill. Omit otherwise."
    },
    "model": {
      "type": "string",
      "minLength": 1,
      "maxLength": 256,
      "description": "Model to look up: a catalogue ID, an exact model name or a natural name such as \"claude-sonnet-5-5\". Send exactly one of model or name. An ambiguous name returns NEEDS_CLARIFICATION with candidates."
    },
    "name": {
      "type": "string",
      "minLength": 1,
      "maxLength": 256,
      "description": "The catalogue's 20-character hexadecimal raw-name ID (not the name text). Send exactly one of model or name."
    },
    "provider": {
      "type": "string",
      "minLength": 1,
      "maxLength": 256,
      "description": "The sourceId of the row to inspect (the site host, e.g. \"api.example.com\"), not the operator ID."
    },
    "rowId": {
      "type": "string",
      "maxLength": 512,
      "description": "The rowId of the selected row, to read that exact declaration."
    },
    "offerPage": {
      "type": "integer",
      "minimum": 1,
      "default": 1,
      "description": "Page of this provider's declarations, starting at 1. Follow it when rowId is absent."
    },
    "releaseSet": {
      "type": "string",
      "minLength": 1,
      "maxLength": 256,
      "description": "Pin a published data release by its release-set hash. Omit to use the current release."
    },
    "asOf": {
      "type": "string",
      "minLength": 1,
      "maxLength": 256,
      "description": "Evaluate as of this UTC time (ISO 8601, e.g. \"2026-10-16T12:00:00Z\"). Omit to evaluate now."
    },
    "lang": {
      "type": "string",
      "enum": [
        "en",
        "zh-CN"
      ],
      "default": "en",
      "description": "Answer language: \"en\" or \"zh-CN\"."
    }
  },
  "required": [
    "provider"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

grandet_glossary

Look up the published Grandet relay glossary. Site labels are source claims and glossary terms explain them; they do not verify quality. Query q or category and follow pagination.

Parameters5

q	string	optional	Term or phrase to look up, e.g. "倍率" or "token group".
category	string	optional	Limit to one glossary category.
lang	string	optional	Answer language: "en" or "zh-CN".
page	integer	optional	Result page, starting at 1.
limit	integer	optional	Results per page, 1–20.

Raw schema

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "maxLength": 160,
      "description": "Term or phrase to look up, e.g. \"倍率\" or \"token group\"."
    },
    "category": {
      "type": "string",
      "maxLength": 64,
      "description": "Limit to one glossary category."
    },
    "lang": {
      "type": "string",
      "enum": [
        "en",
        "zh-CN"
      ],
      "default": "en",
      "description": "Answer language: \"en\" or \"zh-CN\"."
    },
    "page": {
      "type": "integer",
      "minimum": 1,
      "description": "Result page, starting at 1."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 20,
      "description": "Results per page, 1–20."
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

grandet_find_free_credits

Find current official free tiers, application-based credits and relay free groups. Return the stated benefit, six requirements, deadline, original observation and claim link. userCanMeet=no_card requires an explicit no-card condition; unknown requirements do not satisfy it. Application categories describe programs, not the user’s eligibility. Follow pagination. view defaults to "compact"; pass view="full" for every field.

Parameters13

host	string	optional	The assistant or app making this call, e.g. "claude-code" or "codex". Attribution only; it does not change results.
targetApp	string	optional	Catalogue ID of the app that will use the API, e.g. "openclaw", "claude-code" or "codex". Selects compatible protocols and connection steps. Send it only when the user says where the API will be used.
skillVersion	string	optional	Grandet Skill version when called from the Skill, e.g. "0.3.0". Omit otherwise.
skillBuild	string	optional	Grandet Skill build ID when called from the Skill. Omit otherwise.
view	string	optional	"compact" (default): about 18 KB for a typical query. "full": every field, often over 250 KB.
q	string	optional	Model, vendor or site to search, e.g. "gemini".
kind	string	optional	"official" free tiers and credits, "relay" free groups, or "all".
userCanMeet	string	optional	Only offers the user can meet: "any", "no_card" (no payment card) or "student".
lang	string	optional	Answer language: "en" or "zh-CN".
page	integer	optional	Result page, starting at 1.
limit	integer	optional	Results per page, 1–20.
releaseSet	string	optional	Pin a published data release by its release-set hash. Omit to use the current release.
asOf	string	optional	Evaluate as of this UTC time (ISO 8601, e.g. "2026-10-16T12:00:00Z"). Omit to evaluate now.

Raw schema

{
  "type": "object",
  "properties": {
    "host": {
      "type": "string",
      "pattern": "^[a-zA-Z0-9._/-]{1,64}$",
      "description": "The assistant or app making this call, e.g. \"claude-code\" or \"codex\". Attribution only; it does not change results."
    },
    "targetApp": {
      "type": "string",
      "pattern": "^[a-zA-Z0-9._/-]{1,64}$",
      "description": "Catalogue ID of the app that will use the API, e.g. \"openclaw\", \"claude-code\" or \"codex\". Selects compatible protocols and connection steps. Send it only when the user says where the API will be used."
    },
    "skillVersion": {
      "type": "string",
      "maxLength": 32,
      "description": "Grandet Skill version when called from the Skill, e.g. \"0.3.0\". Omit otherwise."
    },
    "skillBuild": {
      "type": "string",
      "pattern": "^[a-zA-Z0-9._-]{1,96}$",
      "description": "Grandet Skill build ID when called from the Skill. Omit otherwise."
    },
    "view": {
      "type": "string",
      "enum": [
        "full",
        "compact"
      ],
      "description": "\"compact\" (default): about 18 KB for a typical query. \"full\": every field, often over 250 KB.",
      "default": "compact"
    },
    "q": {
      "type": "string",
      "maxLength": 200,
      "description": "Model, vendor or site to search, e.g. \"gemini\"."
    },
    "kind": {
      "type": "string",
      "enum": [
        "official",
        "relay",
        "all"
      ],
      "description": "\"official\" free tiers and credits, \"relay\" free groups, or \"all\"."
    },
    "userCanMeet": {
      "type": "string",
      "enum": [
        "any",
        "no_card",
        "student"
      ],
      "description": "Only offers the user can meet: \"any\", \"no_card\" (no payment card) or \"student\"."
    },
    "lang": {
      "type": "string",
      "enum": [
        "en",
        "zh-CN"
      ],
      "default": "en",
      "description": "Answer language: \"en\" or \"zh-CN\"."
    },
    "page": {
      "type": "integer",
      "minimum": 1,
      "maximum": 99999,
      "description": "Result page, starting at 1."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 20,
      "description": "Results per page, 1–20."
    },
    "releaseSet": {
      "type": "string",
      "minLength": 1,
      "maxLength": 256,
      "description": "Pin a published data release by its release-set hash. Omit to use the current release."
    },
    "asOf": {
      "type": "string",
      "minLength": 1,
      "maxLength": 256,
      "description": "Evaluate as of this UTC time (ISO 8601, e.g. \"2026-10-16T12:00:00Z\"). Omit to evaluate now."
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

README.md7 KBView on GitHub

Grandet: find the cheapest API for any model

简体中文 · Website · Installation

Grandet compares listed API prices for each model across official APIs, inference providers and relay sites. Your AI agent can look them up and connect the cheapest one to your app.

Use it as	How
Website	https://grandet.ai
Remote MCP server	`https://grandet.ai/mcp` (Streamable HTTP, no sign-up, no API key)
Agent Skill	Tell your agent: `Install Grandet Skill for me: https://grandet.ai/download.md`

Install

Paste this into the agent you already use (Codex, Claude Code, Cursor and others):

text

Install Grandet Skill for me: https://grandet.ai/download.md

The agent does the rest. If it needs you to sign in or approve something, it tells you exactly what to click. Then open a new conversation and ask:

I code in Claude Code. Find me the cheapest Claude Sonnet 4.6 API.

No need to mention Grandet or attach files again. Price lookups need no account or API key. To install by hand, or for apps such as ChatGPT or Claude on the web that take an uploaded skill file, see Manual installation.

MCP server

Add it to any MCP client that supports remote servers:

json

{ "mcpServers": { "grandet": { "url": "https://grandet.ai/mcp" } } }

In Claude Code: claude mcp add --transport http grandet https://grandet.ai/mcp

Tools: grandet_find_cheapest_api, grandet_find_free_credits, grandet_resolve_model, grandet_quote_evidence, grandet_glossary, grandet_list_apps.

What it does

1. Finds the lowest listed price. It compares the relay and official prices on grandet.ai for your model and kind of use (chat, coding, long output) and lists the cheapest few: the site, the group to pick when you create the token, the price, its unit and when it was observed.

It ranks by listed price only. It never says which site is "good" and never repeats a site's own claims such as "full strength" or "stable".
USD credit, CNY credit and cash prices are listed separately and never compared with each other.
Conditions such as a minimum top-up or members-only access are shown as a one-line hint. Prices that contradict the site's own text are listed as a reference. Groups a site limits to one client are folded away when your app is a different one.

2. Finds free credit. Ask "is there anything free?" and it lists official free tiers, trial credit and relay sign-up, check-in and free-group offers, with whether a card, ID check or application is needed. If something you already said makes you eligible for a free offer, it mentions it once.

3. Connects it for you. When you say "connect it":

You sign up and top up on the site yourself, and create the token in the group it names.
You run one command in your own terminal to store the key. Typing is hidden and the key never enters the chat.
It shows the exact configuration change, backs up the file, and writes only after you confirm.
It checks the key, group and model name without spending credit.
Say "undo" to restore the previous setup.

For Codex, Claude Code, OpenCode, Kilo Code, Continue, Gemini CLI, Hermes and OpenClaw, the Skill's own connect program (scripts/connect.mjs, also usable as a local MCP server) makes the change the same way every time. Other apps get a field card and their documentation link. In a cloud chat, it can only hand you the command and configuration to run yourself.

Try asking

20 million tokens a month, a quarter input and the rest output, no cache. Which is cheapest, and what does it cost a month?

Is there a free Gemini API? I don't have a credit card.

Use the second one and connect it to Codex on Windows.

What do "官转" and "逆向" mean?

Answers include a link to the price sources. Listed prices and suppliers' claims say nothing about quality. Asked about quality, speed or downgraded models, it reports only what Grandet has on record and says so when there is no measurement.

What Grandet includes

	What it does
grandet.ai	Compare model API prices across official APIs, inference providers and relays; browse suppliers, free credit and promotions; check sources and observation dates
Grandet Skill	Find the lowest price, find free credit and connect the chosen API from inside your agent
MCP server	The same price and free-credit lookup for any MCP client, anonymous and without a key

Feedback

Please open an issue if something goes wrong, with the app, version, system and the step where it stopped. Don't paste API keys or private conversations.

Data and developer entry points

Content	Entry point
Free credit and promotions	Readable · JSON · Release details
Original catalogue and sources	Catalogue · JSON · Manifest
Repository data index	Machine-readable index · Reading guide for AI
Agent price lookup (MCP)	Anonymous Streamable HTTP: `https://grandet.ai/mcp`
HTTP price lookup	`https://grandet.ai/api/v1/board` · API description
HTTP free-credit lookup	`https://grandet.ai/api/v1/free-credits?q=gemini`
Relay jargon glossary	Built into the Skill · Online

Local development needs Node.js 20+ and no third-party packages:

node scripts/catalogue.mjs validate
node scripts/catalogue.mjs generate --check
node scripts/validate-public.mjs
node --test tests/*.test.mjs
node scripts/serve.mjs

serve.mjs opens a local browser view at http://127.0.0.1:8787/. These commands check local files only and never update the website's prices.

Sourced corrections and improvements are welcome; see the contributing guide and methodology.

Licence

Skill files: Apache-2.0.
Catalogue code and documents written by Grandet: AGPL-3.0-only; scope in LICENSE.
Supplier data, original text and trademarks belong to their owners; the factual compilation carries no blanket open-data licence. See DATA-LICENSE.md, TRADEMARKS.md and each release manifest.

Install

Tools (6)

grandet_find_cheapest_apigrandet_list_appsgrandet_resolve_modelgrandet_quote_evidencegrandet_glossarygrandet_find_free_credits

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://grandet.ai/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "grandet": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://grandet.ai/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

MCP Server: io.github.hanzohanzhe/grandet

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

grandet_find_cheapest_api

grandet_list_apps

grandet_resolve_model

grandet_quote_evidence

grandet_glossary

grandet_find_free_credits

Grandet: find the cheapest API for any model

Install

MCP server

What it does

Try asking

What Grandet includes

Feedback

Data and developer entry points

Licence

Install

Remote endpoint

Related servers