Usage assumptions
Describe your API workload
Adjust any number to update every model instantly.
Selected model
LLM API Cost Calculator
Estimate per-call and monthly API spend, then rank leading models from cheapest to most expensive.
Current provider pricingNothing uploadedFree
Verified reference
Prices used
Prices from official provider pricing pages · verified Oct 2026
| Model | Input / 1M | Cached input | Output / 1M | Context |
|---|---|---|---|---|
| GPT-6 Astra | $10 | $1 | $50 | 1.05M |
| GPT-6.1 Sol | $2 | $0.1 | $10 | 1.05M |
| GPT-6 Luna | $0.1 | $0.01 | $0.5 | 1.05M |
| Claude Opus 5.5 | $4 | $0.2 | $20 | 1M |
| Claude Sonnet 5.5 | $2 | $0.1 | $10 | 1M |
| Claude Haiku 5.5 | $0.1 | $0.01 | $0.5 | 1M |
| Gemini 4 Argon | $2 | $0.1 | $10 | 1M |
| Gemini 3.1 Flash Lite | $0.25 | $0.025 | $1.5 | 1M |
| DeepSeek V4.1 Flash | $0.3 | $0.006 | $1.2 | 1M |
| DeepSeek V4 Pro | $1.32 | $0.044 | $3.96 | 1M |
Clear answers
Frequently asked questions
Batch processing handles asynchronous requests at up to 50% lower input and output prices. Results usually return within 24 hours.
Keep calculating