LLM Cost Calculator
Compare token costs across OpenAI, Anthropic, Google, Azure OpenAI, Mistral, and Cohere. See exactly what your AI workload will cost — and how much you can save with smart caching.
Model Selection
Usage Profile
Full Model Comparison
Based on your usage profile above| Model | Input/1M | Output/1M | Monthly Cost | vs Selected |
|---|---|---|---|---|
Mistral NemoMistral AI cheapestOSS | $0.15 | $0.15 | $36.00 | -53% |
Gemini 1.5 FlashGoogle Best value | $0.075 | $0.3 | $38.25 | -50% |
Gemini 2.0 FlashGoogle Newest | $0.1 | $0.4 | $51.00 | -33% |
GPT-4o miniOpenAI selectedBest value | $0.15 | $0.6 | $76.50 | — |
Command RCohere Best value | $0.15 | $0.6 | $76.50 | 0% |
Mistral SmallMistral AI Best value | $0.2 | $0.6 | $84.00 | +10% |
GPT-4o mini (Azure)Azure OpenAI Best value | $0.165 | $0.66 | $84.15 | +10% |
GPT-3.5 TurboOpenAI | $0.5 | $1.5 | $210.00 | +175% |
Claude 3.5 HaikuAnthropic Fast & cheap | $0.8 | $4 | $480.00 | +527% |
o3-miniOpenAI Reasoning | $1.1 | $4.4 | $561.00 | +633% |
Mistral LargeMistral AI | $2 | $6 | $840.00 | +998% |
GPT-4oOpenAI | $2.5 | $10 | $1.3K | +1567% |
GPT-4o (Azure)Azure OpenAI | $2.5 | $10 | $1.3K | +1567% |
Command R+Cohere | $2.5 | $10 | $1.3K | +1567% |
Gemini 1.5 ProGoogle | $3.5 | $10.5 | $1.5K | +1822% |
Claude 3.5 SonnetAnthropic Best balance | $3 | $15 | $1.8K | +2253% |
GPT-4 TurboOpenAI | $10 | $30 | $4.2K | +5390% |
GPT-4 Turbo (Azure)Azure OpenAI | $10 | $30 | $4.2K | +5390% |
o1OpenAI Reasoning | $15 | $60 | $7.7K | +9900% |
Claude 3 OpusAnthropic Most capable | $15 | $75 | $9.0K | +11665% |
Prices are approximate and may not reflect the latest provider rates. Always verify on the provider's pricing page before making decisions.
Cut These Costs With RTD Gateway
RealTimeDetect's LLM gateway adds semantic caching, automatic provider fallback, and per-key rate limiting — reducing your actual token spend by 20–40% with no code changes.
Related Resources
Quickstart
Integrate the gateway in under 10 minutes.
Security
Review compliance and platform hardening controls.
Fraud Detection
Protect payment and account flows in real time.
Bot Detector
Stop malicious automation with low-latency scoring.
Traffic Management
Tune fallback, retries, and smart provider routing.
LLM Gateway Benefits
See architecture and cost outcomes from real teams.
Find this useful? or share on Twitter / X