Tokencost Dev
A lightweight pricing oracle that exposes LiteLLM's model cost database through four MCP tools. You can look up any model's pricing and capabilities with fuzzy matching (get_model_details), estimate costs for token counts (calculate_estimate), compare models by provider or mode (compare_models), and refresh the local price cache (refresh_prices). The data comes from LiteLLM's community registry and updates daily. No API keys or configuration required. Useful when you're prototyping with multiple models and need quick cost comparisons, or when you want your AI assistant to factor pricing into its recommendations without leaving the conversation to check documentation.
- GitHub stars
- 1
- tools
- 4
- transport
- STDIO
- last updated
- Feb 27, 2026
Tools
4 toolsPublic tool metadata for what this MCP can expose to an agent.
get_model_detailsLook up pricing, context window, and capabilities for any model.
Look up pricing, context window, and capabilities for any model.
No parameter schema in public metadata yet.
calculate_estimateEstimate cost for a given number of input and output tokens.
Estimate cost for a given number of input and output tokens.
No parameter schema in public metadata yet.
compare_modelsFind the most cost-effective models matching your requirements.
Find the most cost-effective models matching your requirements.
No parameter schema in public metadata yet.
refresh_pricesForce re-fetch pricing data from the LiteLLM registry (cache is refreshed automatically every 24h).
Force re-fetch pricing data from the LiteLLM registry (cache is refreshed automatically every 24h).
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
tokencost
Ask your AI assistant "how much does GPT-4o cost?" — get an instant, accurate answer.
tokencost demo in Claude Code
Install in 30 seconds
Claude Code:
claude mcp add tokencost-dev -- npx -y tokencost-dev
Then ask: "How much would 1M input tokens cost on claude-sonnet-4-5?"
Cursor (.cursor/mcp.json):
Details
- Repository
- github.com/atriumn/tokencost-dev
- Category
- AI & LLM Tools
- Package
tokencost-dev- Transport
- STDIO
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
Systemores AI Agent & MCP Security Auditorbobcar0/systemores-pluginAI agent security, MCP 2026 schema & graph audits, <250ms guardrails, and compliance dossiers1stars
Cinderwright Apicinderwright-ai/cinderwright-apiCross-protocol agent payments hub. x402, MPP, L402/Lightning. 1551 services indexed.1stars
CloudGPU MCPcloudgpu-app/cloudgpu-mcpAgent GPU compute scheduling: compare billing, approve budgets, run tasks and persist results.1stars
Decision Anchorzse4321/decision-anchor-sdkExternal anchoring layer: records AI agent accountability boundaries on both sides. Content-blind.0stars
Mcpagentsimdev/agentsim-mcpControl plane for agent auth walls. Connector 0 handles SMS OTP with US test numbers.1stars
anysitedwytmcl/anysite-mcpAny website as MCP tools: a real Chrome signed in as you, and shortcuts the agent saves as tools.1stars