About Tokencost Mcp Server
TokenCost MCP Server provides AI assistants with real-time token pricing for models from multiple providers. Developers and teams can query rates, compare models, and estimate usage costs.
Key features
- 01Look up pricing for a model
- 02Compare model prices side by side
- 03Estimate cost from token counts
- 04Find low-cost models with filters
- 05List models and providers
Use cases
- 01Estimate the cost of a model request
- 02Compare model prices across providers
- 03Find lower-cost models meeting context needs
MCP support
The MCP server exposes tools to query pricing, compare models, estimate costs, find inexpensive models, and list available models and providers.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
6Saved tool list · updated 3w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| model | string | Yes | Model ID or name (e.g., 'gpt-5', 'claude-sonnet-4.6') |
Details
From the project READMETokenCost MCP Server
An MCP (Model Context Protocol) server that provides real-time LLM token pricing data for 60+ AI models across 15 providers.
Query, compare, and estimate costs for models from OpenAI, Anthropic, Google, Meta, xAI, Mistral, DeepSeek, and more — directly from your AI assistant.
Built by TokenCost — the free LLM token cost calculator.
Tools
| Tool | Description |
|---|---|
tokencost_get_model_pricing | Get pricing for a specific model |
tokencost_compare_models | Side-by-side pricing comparison |
tokencost_estimate_cost | Calculate cost for given token counts |
tokencost_find_cheapest | Find cheapest models with filters |
tokencost_list_models | List all available models |
tokencost_list_providers | List all providers with pricing ranges |
Quick Start
Claude Desktop / Cursor / Windsurf
Add to your MCP config:
{
"mcpServers": {
"tokencost": {
"command": "npx",
"args": ["-y", "tokencost-mcp-server"]
}
}
}
From Source
git clone https://github.com/ankit-aglawe/tokencost-mcp-server
cd tokencost-mcp-server
npm install
npm run build
npm start
Example Usage
"How much would it cost to process 1M input tokens with GPT-5?"
→ Uses tokencost_estimate_cost with model="gpt-5", input_tokens=1000000, output_tokens=0
"Compare Claude Sonnet 4.6 vs GPT-5 vs Gemini 3 Pro pricing"
→ Uses tokencost_compare_models with ["claude-sonnet-4.6", "gpt-5", "gemini-3-pro"]
"What's the cheapest model with at least 200K context?"
→ Uses tokencost_find_cheapest with min_context=200000
Supported Providers
OpenAI, Anthropic, Google, xAI, Meta, Mistral, DeepSeek, Alibaba (Qwen), Amazon (Nova), NVIDIA, Cohere, Perplexity, Moonshot (Kimi), Zhipu (GLM), MiniMax
Pricing Data
Pricing is kept accurate and up to date by the TokenCost team. We track official provider announcements and update pricing as soon as changes are published — new models, price cuts, and deprecations are reflected within days.
If you notice outdated pricing or a missing model, open an issue and we'll get it updated.
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.