LLM Tools
Model Comparison
Compare LLM pricing and context windows side by side, for your own usage.
Your workload assumptions
Used to estimate a monthly cost for each model below — change these to match your own usage.
| Model | Input | Output | Context window | Est. monthly cost | Action |
|---|---|---|---|---|---|
GPT-4o mini OpenAI | $0.15/1M | $0.6/1M | 128,000 | ₹358.13Cheapest | Use this model |
Gemini 2.5 Flash Google | $0.3/1M | $2.5/1M | 1,000,000 | ₹1,337 | Use this model |
Claude Haiku 4.5 Anthropic | $1/1M | $5/1M | 200,000 | ₹2,865 | Use this model |
Claude Sonnet 5 Anthropic | $2/1M | $10/1M | 1,000,000 | ₹5,730 | Use this model |
GPT-4o OpenAI | $2.5/1M | $10/1M | 128,000 | ₹5,968.75 | Use this model |
Gemini 3.1 Pro Google | $2/1M | $12/1M | 1,000,000 | ₹6,685 | Use this model |
Claude Opus 5 Anthropic | $5/1M | $25/1M | 1,000,000 | ₹14,325 | Use this model |
Pricing was verified against each provider's official pricing page on the date shown per model, then converted to INR at an approximate market exchange rate. Provider pricing changes without notice — confirm current rates before making a purchasing decision.
Want the full picture, including embeddings and infrastructure? Use the AI Budget Planner.
Frequently asked questions
How is 'estimated monthly cost' calculated?
It applies each model's own input/output pricing to the workload assumptions you enter above (monthly requests, average input tokens, average output tokens) — the same formula used across every calculator on this site.
What happens when I click 'Use this model'?
It opens the AI Budget Planner with that model pre-selected, so you can build out the rest of your budget — usage, RAG, and infrastructure — without re-entering the model choice.