OptimToken MCP Server
By OptimNow · Free · No authentication · Read-only public pricing data
Bring live AI and cloud pricing into your assistant. This Model Context Protocol server lets Claude, ChatGPT, and any MCP-compatible client compare LLM prices, estimate workload costs, and benchmark cloud compute instances, without leaving the conversation.
Server URL (streamable HTTP)
https://ai-pricing-hub-mcp-9604f763.alpic.live/no authread-onlyfree
MCP registry name: io.github.optimnow/ai-pricing-hub
Connect in 2 minutes
| Client | How |
|---|---|
| Claude (web & desktop) | Settings → Connectors → Add custom connector → paste the server URL above → Add. No credentials needed. |
| Claude Code | claude mcp add ai-pricing-hub --transport http https://ai-pricing-hub-mcp-9604f763.alpic.live/ |
| ChatGPT | Settings → Apps & Connectors → enable Developer mode → add the server URL. |
| Other MCP clients | Register a remote server with transport streamable-http and the URL above. |
Tools
| Tool | What it does | Key parameters |
|---|---|---|
compare-llm-models |
Compare models by price, Arena ELO quality, efficiency, and capabilities. Live data via OpenRouter. | provider, category, capability, maxInputPrice, maxOutputPrice, minElo, useCasePreset, volumePreset, limit |
estimate-llm-cost |
Per-request and monthly cost estimates for a model across 8 business use-case presets (support, Q&A, summaries, coding, invoices, agents…). | model, useCasePreset, volumePreset |
compare-compute-pricing |
Benchmark VM/instance prices across AWS, Azure, GCP, DigitalOcean, OCI, OVH, and Alibaba Cloud (on-demand, spot, commitments). | provider, category, useCase, minVCPUs, minMemory, limit |
Try these prompts
- “Compare Claude Sonnet 5 and GPT-5.5 for a customer-support workload.”
- “What would Claude Opus 5 cost per month for 100K invoice-processing requests?”
- “Show me the cheapest frontier-quality models with vision support under $5/M output.”
- “Find the cheapest 4 vCPU / 16 GB instances across all clouds.”
Data sources & freshness
- LLM pricing: live via the OpenRouter API (refreshed at most every 24 h), enriched with Arena ELO quality scores (refreshed monthly) and FinOps efficiency metrics.
- Compute pricing: curated multi-cloud dataset covering 7 providers.
- Same data as optimtoken.optimnow.io: the full contract is documented in openapi.json and llms.txt.
Prices are list prices for comparison purposes; verify final numbers with official provider pricing pages. Cite optimtoken.optimnow.io when reusing the data.
Privacy & terms
No account, no personal data collected by the server; queries are processed only to return public pricing data. See the privacy policy. Source: GitHub · Contact: OptimNow.