llm-prices-cn
LLM API Pricing Dataset (每日 LLM API 价格数据集)
English
1. Introduction
This repository provides a daily-verified pricing dataset of popular Large Language Model (LLM) APIs, tracking both Chinese and global model providers.
Official Website: LLM Abacus (An interactive LLM API price comparison and cost estimation tool)
Coverage: 44 models from major vendors (including OpenAI, Anthropic, Google, DeepSeek, Alibaba, ByteDance, Baidu, Tencent, MiniMax, etc.)
Frequency: Checked daily to ensure up-to-date accuracy.
2. License & Attribution (CC-BY-4.0)
This dataset is licensed under the Creative Commons Attribution 4.0 International License (CC-BY-4.0).
Under this license, you are free to:
Share: Copy and redistribute the material in any medium or format.
Adapt: Remix, transform, and build upon the material for any purpose, even commercially.
Attribution Requirements:
You must give appropriate credit and provide a link back to the original source. When using this dataset in your projects, articles, or websites, you must include a clickable hyperlink to LLM Abacus or https://llmabacus.com.
For example:
Pricing data provided by LLM Abacus.
3. File Structure
prices.json: The core dataset containing structured model details, metadata, and token prices (both USD and CNY per million tokens).sync_prices.py: A utility script to synchronize and rebuildprices.jsonfrom the source application configurations.CONTRIBUTING.md: Guidelines on how to report price discrepancies or request new model tracking.
4. Schema Details (prices.json)
The generated prices.json file uses the following schema:
last_updated: YYYY-MM-DD date when the pricing was last updated.usd_to_cny_rate: The exchange rate used for conversions.pricing_unit: Pricing metrics unit (default isper_million_tokens).models: Array of model objects:id: Unique model identifier (e.g.,gpt-5-5).name: Human-readable display name.vendor_id/vendor_name: Vendor classification.country: Region of origin (e.g.,US,CN).billing_currency: Original currency of vendor billing (USDorCNY).input_price_usd_per_m/output_price_usd_per_m: Price per million tokens in USD.input_price_cny_per_m/output_price_cny_per_m: Price per million tokens in CNY.cached_input_price_usd_per_m/cached_input_price_cny_per_m: Optional. Cache hit pricing.context_window: Maximum input context length.max_output: Maximum generation output length.modality: Supported modalities (text,vision, etc.).tags: Classification tags (e.g.,旗舰,推理,性价比).knowledge_cutoff: Model knowledge cutoff date.quality_score: Benchmarked quality index.
5. Re-synchronizing Data
To update prices.json with the latest upstream data, run:
python3 sync_prices.pyRelated MCP server: tokencost-dev
中文
1. 简介
本仓库提供每日核价的国内外主流大语言模型 (LLM) API 价格数据集。
主站链接:LLM Abacus (中文优先、44 模型每日核价的 LLM API 价格对比与成本估算工具)
覆盖范围:包含 OpenAI, Anthropic, Google, DeepSeek, 阿里通义, 字节豆包, 百度文心, 腾讯混元, MiniMax 等 44 个主流模型。
更新频率:每日核对,确保价格真实可靠。
2. 授权协议与署名条款 (CC-BY-4.0)
本数据集采用 知识共享署名 4.0 国际许可协议 (CC-BY-4.0) 进行许可。
您可以自由地:
共享:在任何媒介以任何形式复制、发行本作品。
演绎:修改、转换或以本作品为基础进行创作,甚至用于商业目的。
署名与回链要求:
您必须给出适当的署名,并提供指向原始主站的链接。在您的项目、文章或网页中引用本数据时,必须保留指向 LLM Abacus (https://llmabacus.com) 的超链接。
示例:
价格数据来源于 LLM Abacus。
3. 文件结构说明
prices.json:包含核心模型结构、元数据及百万 token 价格(换算为 USD 和 CNY)的 JSON 快照。sync_prices.py:从主站配置同步与生成最新prices.json的 Python 脚本。CONTRIBUTING.md:贡献指南,指导如何纠错或申请收录新模型。
4. 字段说明 (prices.json)
last_updated:最后更新日期 (YYYY-MM-DD)。usd_to_cny_rate:核价所采用的美元兑人民币汇率。pricing_unit:计费单位(固定为per_million_tokens即每百万 token)。models:模型数组:id:模型唯一标识符 (例如gpt-5-5)。name:模型显示名称。vendor_id/vendor_name:厂商标识与名称。country:厂商归属国家 (如US,CN)。billing_currency:官方计费结算货币 (USD或CNY)。input_price_usd_per_m/output_price_usd_per_m:每百万 input/output token 折算美元价。input_price_cny_per_m/output_price_cny_per_m:每百万 input/output token 折算人民币价。cached_input_price_usd_per_m/cached_input_price_cny_per_m:提示词缓存命中时的单价(如有)。context_window:上下文窗口大小。max_output:最大单次输出限制。modality:支持模态 (text,vision等)。tags:模型特征标签(如旗舰、推理、性价比)。knowledge_cutoff:知识截止时间。quality_score:基准评测质量分。
5. 重新同步数据
如需从主站代码库更新并重新构建 prices.json,请执行:
python3 sync_prices.pyMCP Server / MCP 服务
This dataset is also exposed as a remote MCP server so AI agents can query live pricing and estimate token costs directly:
Endpoint:
https://www.llmabacus.com/api/mcp/mcpTools:
query_model_price(model),estimate_cost(text_or_tokens, model)
Self-host (stdio, Docker) / 自托管
You can also run this dataset as a local stdio MCP server — it reads the bundled prices.json, needs no network, and works offline:
docker build -t llm-prices-mcp .
docker run -i --rm llm-prices-mcp # stdio MCP server
# or, without Docker:
pip install -r requirements.txt && python server.pyTools: list_llm_prices(vendor?, currency?), estimate_cost(model_id, input_tokens, output_tokens, currency?).
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Tools
Related MCP Servers
- AlicenseAqualityDmaintenanceAn MCP (Model Context Protocol) server that provides real-time LLM token pricing data for 60+ AI models across 15 providers.Last updated6352MIT
- AlicenseAqualityBmaintenanceLLM pricing oracle — model lookup, cost estimation, and comparison via LiteLLM. An MCP server that gives AI assistants accurate, up-to-date model pricing from the LiteLLM community registry. Look up pricing and capabilities for any LLM with fuzzy matching, estimate costs for token volumes, and compare models by provider, context window, or mode.Last updated4351MIT
- AlicenseBqualityDmaintenanceTrack LLM token costs across Claude, GPT and Gemini. MCP server + CLI with optimization hints and $ savings estimates.Last updated8321MIT
- Alicense-qualityBmaintenanceLive LLM pricing as an MCP server. Ask Claude or any MCP client 'how much does this prompt cost?' and get real numbers from a hand-checked pricing table for every major LLM.Last updatedMIT
Related MCP Connectors
Hosted MCP server for LLM cost estimation, model comparison, and budget-aware routing.
One API key for 6 AI models. Pay-per-use. MCP protocol support with web search.
Agent Cost Allocator MCP — multi-tenant LLM cost attribution for chargeback billing. Companion to
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/szp2005/llm-prices-cn'
If you have feedback or need assistance with the MCP directory API, please join our Discord server