Categories › AI & Agents › Models, LLM APIs, routing, serving, training & GPUs
Current Claude API prices and cost estimates with prompt caching and Batch API pricing.
Remote server: your requests and data go to agentwright.app. Claude Code: claude mcp add --transport http claude-api-pricing https://agentwright.app/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
list_claude_models — List current Claude API models with their prices in USD per million tokens: input, output, prompt-cache writes (5 min / 1 h), cache reads, aestimate_claude_cost — Estimate the USD cost of Claude API calls from token counts. Handles prompt caching (cache writes and reads), the Batch API 50% discount andcompare_claude_models — Compare what the same workload costs on every Claude model, cheapest first. Give tokens per request and the number of requests (e.g. per useNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.