LLM API Token & Monthly Cost Calculator
Compare real-time monthly API costs across GPT-4o, Claude 3.5 Sonnet, Gemini 2.5 Pro, DeepSeek V3 & R1 with prompt caching discounts.
1. Configure Your Workload
0% (No Caching)
50% Cached
95% Cached
2. Instant Cost Optimization Summary
Lowest Cost Model
Gemini 2.0 Flash
$0.00 / mo
Monthly Token Volume
93.0M
Input + Output / 30 days
💡 Pro Tip for n8n & Make.com Users: Structure your static instructions at the top of your prompt to unlock up to 90% prompt caching discounts on Claude 3.5 and Gemini 2.5, or download our 50 XML Prompt Vault below.
3. Full Model-by-Model Monthly Cost Breakdown (30 Days)
| Model & Provider | Input / 1M | Cached Input / 1M | Output / 1M | Context Window | Est. Monthly Cost (USD) |
|---|---|---|---|---|---|
| GPT-4o OpenAI • Flagship Multimodal |
$2.500 | $1.250 | $10.00 | 128,000 | $0.00 |
| GPT-4o mini OpenAI • High-Efficiency Workhorse |
$0.150 | $0.075 | $0.60 | 128,000 | $0.00 |
| OpenAI o3-mini OpenAI • Reasoning & Coding |
$1.100 | $0.550 | $4.40 | 200,000 | $0.00 |
| Claude 3.5 Sonnet Anthropic • Flagship Coding & Writing |
$3.000 | $0.300 | $15.00 | 200,000 | $0.00 |
| Claude 3.5 Haiku Anthropic • Fast Sub-Agent Model |
$0.800 | $0.080 | $4.00 | 200,000 | $0.00 |
| Gemini 2.5 Pro Google • Long-Context Flagship |
$1.250 | $0.310 | $5.00 | 2,000,000 | $0.00 |
| Gemini 2.0 Flash Google • Ultra-Fast Multimodal |
$0.100 | $0.025 | $0.40 | 1,000,000 | $0.00 |
| DeepSeek V3 DeepSeek • Open-Weights Disruptor |
$0.270 | $0.070 | $1.10 | 64,000 | $0.00 |
| DeepSeek R1 DeepSeek • Open-Source Reasoning |
$0.550 | $0.140 | $2.19 | 64,000 | $0.00 |
| Llama 3.3 70B (Groq/Together) Meta • Real-Time Voice & Speed |
$0.590 | $0.590 | $0.79 | 128,000 | $0.00 |
| Mistral Large 2 Mistral AI • European Enterprise Multilingual |
$2.000 | $2.000 | $6.00 | 128,000 | $0.00 |
| Amazon Nova Pro AWS Bedrock • AWS Enterprise Native |
$0.800 | $0.200 | $3.20 | 300,000 | $0.00 |
🔥 Recommended AI Automation Stack (Verified Free Tiers & High ROI)
Make.com
Visual No-Code AI Automation Platform (1,000 Free Ops/mo)
Try Make.com Free (1,000 Ops)
n8n Cloud
Fair-Code Workflow Automation with Native AI Agents
Launch n8n AI Agents
CustomGPT.ai
Build No-Code RAG Custom Chatbots on Your Business Data
Build Custom RAG Bot