Cost across cloud + local
Paste anything — a prompt, source file, transcript, email draft. We count tokens, then show you the cost across 11 cloud providers and your local rig, side by side. Same data for the same input. Decide where each workload belongs.
11 providers across 3 tiers. Prices verified May 2026. Token counts are content-aware approximations (±15%) — provider price differences dwarf tokenizer accuracy, so this is enough to make a decision. URL updates as you change — share by copy.
Calculator
Start with the sample text or paste your own. Pick a local rig + model from your catalog and the cloud providers you want to compare against. Everything is reactive.
| Provider | Model | $/M in | $/M out | Per run | per month | vs cheapest |
|---|---|---|---|---|---|---|
| DeepSeek | DeepSeek V3 (API) Mid-tier | $0.27 | $1.10 | $0.00012 | $0.177 | cheapest |
| Together AI | Llama 3.3 70B (Together) Open-weight | $0.88 | $0.88 | $0.00019 | $0.284 | 1.6× |
| OpenAI | GPT-5 Frontier | $5.00 | $20.00 | $0.00216 | $3.23 | 18.3× |
If the calculator above says cloud is the right call for your workload — frontier-quality one-shot tasks, low-volume agentic loops, day-one access to new models — ClaudeStore is a third-party reseller that bundles Claude API credits at a discount vs Anthropic-direct top-ups. Bundle terms set by ClaudeStore (not us, not Anthropic) and can change — verify the current bundle on their checkout before you pay. We get a small referral commission if you sign up via the link; it doesn’t change what you pay.
Affiliate disclosure: ClaudeStore is an unofficial third-party Claude API reseller — not Anthropic. The $500-for-$49 figure is ClaudeStore’s currently-advertised bundle; pricing can change without notice on their side, so confirm at checkout before paying. We receive a referral commission on sign-ups via the link above. How we make money. The recommendation isn’t influenced by the kickback — the calculator above tells you whether cloud is the right answer for your specific workload.
Where to go from here
Once you know it's worth going local: pick the whole rig + runtime + model + install script in one wizard.
The local cost above assumes Q4_K_M. Drill into which quant fits your specific hardware × model × context.
The break-even number above is volume-driven. Switch view to tune utilization / electricity / amortization assumptions.
Cost is one side of the trade — speed is the other. Watch tokens stream at the rate your rig would produce them, side-by-side with the cloud provider.
Step-by-step guide to swap Claude Sonnet for a local model in your Claude Code workflow. Real commands.