# LLM Abacus

> Compare up-to-date pricing for 40+ LLMs (incl. Chinese) & estimate cost from tokens. EN/zh.

- name: com.llmabacus/pricing
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 75/100 flags: no-repository
- quality: 91/100 (strong)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.llmabacus%2Fpricing
- tools: https://api.protogrid.dev/v1/servers/com.llmabacus%2Fpricing/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "pricing": {
      "type": "http",
      "url": "https://llmabacus.com/api/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 98
- freshness: 65
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-96% ~updated-92d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 91/100 (strong)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 2 of 2 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 360 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 2, about 360 tokens to load them all
- tool set hash: 64d07703defccaf359b47824e761e63e
- badge: [![protogrid quality](https://protogrid.dev/badge/com.llmabacus/pricing.svg)](https://protogrid.dev/servers/com.llmabacus/pricing)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://llmabacus.com/api/mcp (streamable-http, auth none, reachable true, uptime30d 0.9557522)

## Packages

_none_

## Tools (2)

- `estimate_cost`: 估算一段文本或指定 token 数在某个大模型上的**输入侧**调用成本，以人民币 ¥ 计价。text_or_tokens 支持两种模式：传自然语言文本时自动估算 token 数（中文按字符、英文按词分别计），传纯数字字符串时直接作为已知 token 数使用。返回：所用估算方法、token 数、按原价计的输入成本；若该模型提供缓存输入价，另给出缓存命中成本、相对原价的节省百分比与倍数差价；末尾附该模型的输入 / 输出 / 缓存输入单价（每百万 tokens）。⚠️ 本工具只计算输入成本，不含输出 token 费用——要估算完整往返成本，需另取输出单价自行相加。
- `query_model_price`: 查询指定大模型（如 GPT-5, Claude, DeepSeek）的最新 API 输入、输出和缓存输入单价（单位：每百万 tokens）。