LLM pricing, provider and gateway rates, pricing tiers, and inference cost calculations.
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.
Calculate the cost of an AI model inference given token usage
Model ID, e.g. "gpt-4o"
Provider ID, e.g. "openai"
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http narev https://mcp.narev.ai
Calculate the cost of an AI model inference given token usage
| Argument | Type | Description |
|---|---|---|
| model_id* | string | Model ID, e.g. "gpt-4o" |
| provider_id* | string | Provider ID, e.g. "openai" |
| prompt_tokens* | integer | |
| reasoning_tokens | integer | |
| web_search_count | integer | |
| cache_read_tokens | integer | |
| completion_tokens* | integer | |
| cache_write_tokens | integer |
{
"type": "object",
"required": [
"model_id",
"provider_id",
"prompt_tokens",
"completion_tokens"
],
"properties": {
"model_id": {
"type": "string",
"description": "Model ID, e.g. \"gpt-4o\""
},
"provider_id": {
"type": "string",
"description": "Provider ID, e.g. \"openai\""
},
"prompt_tokens": {
"type": "integer",
"minimum": 0
},
"reasoning_tokens": {
"type": "integer",
"minimum": 0
},
"web_search_count": {
"type": "integer",
"minimum": 0
},
"cache_read_tokens": {
"type": "integer",
"minimum": 0
},
"completion_tokens": {
"type": "integer",
"minimum": 0
},
"cache_write_tokens": {
"type": "integer",
"minimum": 0
}
}
}Get pricing for AI models available through gateways (openrouter, kilo) with optional filtering and sorting
| Argument | Type | Description |
|---|---|---|
| page | integer | |
| order | string | |
| sort_by | string | |
| model_id | string | |
| page_size | integer | |
| gateway_id | string | Gateway ID |
| provider_id | string | Provider, e.g. "OpenAI" |
{
"type": "object",
"properties": {
"page": {
"type": "integer",
"minimum": 1
},
"order": {
"enum": [
"asc",
"desc"
],
"type": "string"
},
"sort_by": {
"enum": [
"model_id",
"gateway_id"
],
"type": "string"
},
"model_id": {
"type": "string"
},
"page_size": {
"type": "integer",
"maximum": 1000,
"minimum": 1
},
"gateway_id": {
"enum": [
"openrouter",
"kilo"
],
"type": "string",
"description": "Gateway ID"
},
"provider_id": {
"type": "string",
"description": "Provider, e.g. \"OpenAI\""
}
}
}Get tiered/volume-based pricing for AI models with optional filtering and sorting
| Argument | Type | Description |
|---|---|---|
| page | integer | |
| order | string | |
| region | string | Region, e.g. "us-east-1" |
| sort_by | string | |
| model_id | string | |
| page_size | integer | |
| provider_id | string | |
| service_mode | string | Service mode, e.g. "standard", "batch", "flex", "priority" |
{
"type": "object",
"properties": {
"page": {
"type": "integer",
"minimum": 1
},
"order": {
"enum": [
"asc",
"desc"
],
"type": "string"
},
"region": {
"type": "string",
"description": "Region, e.g. \"us-east-1\""
},
"sort_by": {
"enum": [
"model_id",
"provider_id",
"region",
"service_mode"
],
"type": "string"
},
"model_id": {
"type": "string"
},
"page_size": {
"type": "integer",
"maximum": 1000,
"minimum": 1
},
"provider_id": {
"type": "string"
},
"service_mode": {
"type": "string",
"description": "Service mode, e.g. \"standard\", \"batch\", \"flex\", \"priority\""
}
}
}Get pricing for AI models with optional filtering and sorting
| Argument | Type | Description |
|---|---|---|
| page | integer | |
| order | string | |
| sort_by | string | |
| model_id | string | |
| page_size | integer | |
| provider_id | string |
{
"type": "object",
"properties": {
"page": {
"type": "integer",
"minimum": 1
},
"order": {
"enum": [
"asc",
"desc"
],
"type": "string"
},
"sort_by": {
"enum": [
"model_id",
"provider_id"
],
"type": "string"
},
"model_id": {
"type": "string"
},
"page_size": {
"type": "integer",
"maximum": 1000,
"minimum": 1
},
"provider_id": {
"type": "string"
}
}
}List all supported AI gateways (e.g. openrouter, kilo)
No arguments.
{
"type": "object",
"properties": {}
}List available AI models, optionally filtered by provider
| Argument | Type | Description |
|---|---|---|
| page | integer | |
| page_size | integer | |
| provider_id | string | Comma-separated provider IDs, e.g. "openai,anthropic" |
{
"type": "object",
"properties": {
"page": {
"type": "integer",
"minimum": 1
},
"page_size": {
"type": "integer",
"maximum": 1000,
"minimum": 1
},
"provider_id": {
"type": "string",
"description": "Comma-separated provider IDs, e.g. \"openai,anthropic\""
}
}
}List all supported AI providers
No arguments.
{
"type": "object",
"properties": {}
}Run a read-only shell-like query against a virtualized, in-memory filesystem rooted at `/` that contains ONLY the Narev Docs documentation pages and OpenAPI specs. This is NOT a shell on any real machine — nothing runs on the user's computer, the server host, or any network. The filesystem is a sandbox backed by documentation chunks. This is how you read documentation pages: there is no separate "get page" tool. To read a page, pass its `.mdx` path to `head` or `cat` — a page at the URL path `/some/page` lives at `/some/page.mdx`. To search the docs with exact keyword or regex matches, use `rg`. To understand the docs structure, use `tree` or `ls`. **Paths are specific to this site — never guess them.** Discover real paths with `tree / -L 2`, `ls /`, or the search tool before reading. If a path does not exist, that only means the guess was wrong; it does NOT mean the topic is undocumented — use `rg -il "keyword" /` to find where it is covered. **Workflow:** Start with the search tool for broad or conceptual queries like "how to authenticate" or "rate limiting". Use this tool when you need exact keyword/regex matching, structural exploration, or to read the full content of a specific page by path. Supported commands: rg (ripgrep), grep, find, tree, ls, cat, head, tail, stat, wc, sort, uniq, cut, sed, jq, plus basic text utilities. No writes, no network, no process control. Run `--help` on any command for usage. Each call is STATELESS: the working directory always resets to `/` and no shell variables, aliases, or history carry over between calls. If you need to operate in a subdirectory, chain commands in one call with `&&` or pass absolute paths (e.g., `cd /some-directory && ls` or `ls /some-directory`). Do NOT assume that `cd` in one call affects the next call. Examples (replace the placeholder paths with real ones from `tree` or search): - `tree / -L 2` — see the top-level directory layout - `rg -il "rate limit" /` — find all files mentioning "rate limit" - `rg -C 3 "apiKey" /some-directory/` — show matches with 3 lines of context around each hit - `head -80 /some/page.mdx` — read the top 80 lines of a specific page - `head -80 /page-one.mdx /page-two.mdx /section/page-three.mdx` — read multiple pages in one call - `cat /some/page.mdx` — read a full page when you need everything - `cat /openapi/pricing-api/reference/openapi.json | jq '.paths | keys'` — list OpenAPI endpoints OpenAPI specs for this site are mounted under `/openapi`; run `find /openapi -type f` to list them. Use them to answer questions about endpoints, request/response schemas, parameters, and authentication. Output is truncated to 30KB per call. Prefer targeted `rg -C` or `head -N` over broad `cat` on large files. To read only the relevant sections of a large file, use `rg -C 3 "pattern" /path/file.mdx`. Batch multiple file reads into a single `head` or `cat` call whenever possible. When referencing pages in your response to the user, convert filesystem paths to URL paths by removing the `.mdx` extension. For example, `/some/page.mdx` becomes `/some/page`.
Search across the Narev Docs knowledge base to find relevant information, code examples, API references, and guides. Use this tool when you need to answer questions about Narev Docs, find specific documentation, understand how features work, or locate implementation details. The search returns contextual content with titles and direct links to the documentation pages. If you need the full content of a specific page, use the query_docs_filesystem tool to `head` or `cat` the page path (append `.mdx` to the path returned from search — e.g. a result at `/some/page` is read with `head -200 /some/page.mdx`).
| Argument | Type | Description |
|---|---|---|
| query* | string | Search query |
{
"type": "object",
"required": [
"query"
],
"properties": {
"query": {
"type": "string",
"description": "Search query"
}
},
"additionalProperties": false
}Report a problem with this documentation site so the docs team can fix it. Use when a documentation page is incorrect, outdated, confusing, incomplete, or has a broken example. This is for feedback about the documentation content itself — not for product support requests or feedback about this tool or assistant.
| Argument | Type | Description |
|---|---|---|
| path* | string | The URL path of the documentation page the feedback is about (the page you were reading, without the `.mdx` extension). |
| feedback* | string | A clear description of the documentation issue or suggestion — what is incorrect, outdated, missing, or confusing. |
{
"type": "object",
"required": [
"path",
"feedback"
],
"properties": {
"path": {
"type": "string",
"minLength": 1,
"description": "The URL path of the documentation page the feedback is about (the page you were reading, without the `.mdx` extension)."
},
"feedback": {
"type": "string",
"minLength": 1,
"description": "A clear description of the documentation issue or suggestion — what is incorrect, outdated, missing, or confusing."
}
},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 16, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.
| Argument | Type | Description |
|---|---|---|
| command* | string | A shell command to run against the virtualized documentation filesystem (e.g., `rg -il "keyword" /`, `tree / -L 2`, `head -80 /path/file.mdx`). |
{
"type": "object",
"required": [
"command"
],
"properties": {
"command": {
"type": "string",
"description": "A shell command to run against the virtualized documentation filesystem (e.g., `rg -il \"keyword\" /`, `tree / -L 2`, `head -80 /path/file.mdx`)."
}
},
"additionalProperties": false
}