← Caveman pricing
What we read
This is the text we read from https://caveman.so/pricing at 2026-11-02 08:22 UTC. Every figure in our Caveman pricing guide was extracted from it.
BILLING PERIOD UNCERTAIN — this page has a monthly/yearly toggle and the prices did not change when it was operated. Say which billing each price requires only if the page states it. Live Model routing is now available in Claude Code. Same agent. The right model for each subagent. Get started Report Benchmarking Sonnet 5.5: less thinking for the same answers. Read Live Model routing is now available in Claude Code. Same agent. The right model for each subagent. Get started Report Benchmarking Sonnet 5.5: less thinking for the same answers. Read Caveman Product Models Pricing Docs Resources 117k Sign in Get started Caveman is free. Install it. npx @caveman-ai/cli Caveman Cloud is for teams building their own agents. Free for one person. Your whole team for $300 a month, $300 of usage included. Free free _ caveman /cloud caveman / cloud $0 / month Every feature for one person. For one developer trying everything Caveman does Start free No card needed · add one to go past the allowances Free every month: /cloud Hosted at app.caveman.so Every Cloud feature 100,000 events a month 1 event per started 64 KB sent 600 agent minutes a month 25,000 routing decisions a month $10 of Caveman AI a month Standard rates past the allowances One person app.caveman.so/signup Usage included Team team _ caveman /cloud caveman / cloud $300 / month Includes $300 of usage every month. For teams that want agent costs cut, with proof Try Team free for 7 days Card at checkout · cancel in the trial and pay nothing Everything in Free, plus: /cloud Hosted at app.caveman.so $300 of usage every month Then standard rates Your whole team $100 of Caveman AI a month Semantic cache Project access control and audit log export Content sharing off SSO with the Scale package Pick Team when you sign up Enterprise enterprise _ caveman /cloud in your VPC caveman / cloud in your VPC Custom / year Annual contract. For orgs that keep data in their own cloud Talk to us AWS or GCP, your Kubernetes Everything in Team, plus: /cloud In your VPC, one Helm chart on AWS or GCP Runs in your VPC Your KMS and storage Signed releases Annual contract Security and deployment Usage Past the allowances, per unit Each product has its own unit, monthly allowance and billing limit. 0% markup on tokens. LLM observability: events 100,000 events free every month One recorded LLM call, span or eval score. A gateway call counts one event per started 64 KB it sends, so a coding-agent request is several events. LLM observability: price per event by monthly volume, on Free and Team Monthly events Per event 0–100K Free 100K–150K $0.00035 150K–250K $0.000175 250K–500K $0.0001 500K–1M $0.00008 1M–10M $0.00007 10M–50M $0.000065 50M+ $0.00006 Default billing limit: $50 on Free with a card; on Team, none until you set one. Change it any time. Agent runs: minutes 600 minutes free every month Minutes Caveman's runners spend on your agents, each run rounded up to a whole minute. Model calls stay on your own keys. Agent runs: price per minute by monthly volume, on Free and Team Monthly minutes Per minute 0–600 Free 600–10K $0.02 10K–100K $0.015 100K+ $0.012 Default billing limit: $50 on Free with a card; on Team, $150 past the included usage. Change it any time. Routing: decisions 25,000 decisions free every month One routing decision answered is one unit. The request itself goes to your provider, on your key. Routing: price per decision by monthly volume, on Free and Team Monthly decisions Per decision 0–25K Free 25K–2M $0.001 2M–10M $0.0006 10M–50M $0.0004 50M+ $0.0003 Default billing limit: $50 on Free with a card; on Team, none until you set one. Change it any time. At a billing limit we stop recording. We never block your traffic. Demo Evaluating? Click through Cloud on a sample workspace. No signup. Open the demo Open source Just your machine? The agent and the SDK are free, with no account. Install free Compare every feature Output tokens · 8 live MCP scenarios Without Caveman 1,284 With Caveman 467 −63