Your cost = Provider price × Live USD/INR rate × 1.10 (5% forex buffer + 5% platform fee). No surprise bills.
Every API request logs tokens used, model, provider, cost in USD, and cost in ₹. Filter by date, model, or API key.
See your exact spend in ₹ with live forex conversion. No more guessing what USD charges will translate to on your bank statement.
Set spend limits per API key. Great for teams, staging environments, and client projects. Stop runaway costs before they happen.
Compare cost vs quality across models. See which models give you the most output per rupee for your specific workloads.
| Model | Input tokens | Output tokens | Cost (₹) |
|---|---|---|---|
| gpt-4o-mini | 12,450 | 3,210 | ₹0.22 |
| claude-3-5-haiku | 8,900 | 2,100 | ₹0.95 |
| gemini-1.5-flash | 22,000 | 5,400 | ₹0.32 |
| deepseek-chat | 15,600 | 4,200 | ₹0.38 |
Sample data. Actual costs vary with model pricing and live USD/INR rate.
We fetch live USD/INR rates every 10 minutes from a forex API. A 5% buffer is applied to protect against rate fluctuations between fetch intervals.
Yes. Every request in your dashboard shows: model, provider, prompt tokens, completion tokens, cost in USD, and final cost in ₹ after forex and markup.
You can set a maximum spend (in ₹) per API key. Once the key's usage reaches the budget, requests are rejected with a clear error message. You can reset or increase the budget at any time.
Yes. Create separate API keys for each team member, project, or client. Each key tracks its own usage and budget independently.
You can view transaction history and usage logs in your dashboard. Export and download features are on our roadmap.