Monthly Cost Calculator
Estimate your monthly LLM API spend. Set your average prompt size, response size, and daily call volume.
| Model | Provider | Per Call | Daily | Monthly | Context |
|---|---|---|---|---|---|
| GPT-OSS 120B | OpenAI | $< 0.01 | $0.173 | $5.19 | 131K |
| Qwen3.5-9B | Alibaba | $< 0.01 | $0.175 | $5.25 | 262K |
| Qwen3.5-Omni Flash | Alibaba | $< 0.01 | $0.260 | $7.80 | 262K |
| GPT-OSS 20B | OpenAI | $< 0.01 | $0.300 | $9.00 | 131K |
| Gemini 2.0 Flash-Lite | $< 0.01 | $0.300 | $9.00 | 1.0M | |
| GPT-5 Nano | OpenAI | $< 0.01 | $0.300 | $9.00 | 128K |
| Llama 4 Scout | Meta | $< 0.01 | $0.310 | $9.30 | 1.0M |
| Devstral Small | Mistral | $< 0.01 | $0.350 | $10.50 | 256K |
| Mistral Small 3.2 | Mistral | $< 0.01 | $0.350 | $10.50 | 128K |
| Ministral 3 8B | Mistral | $< 0.01 | $0.375 | $11.25 | 262K |
| GPT-4.1 Nano | OpenAI | $< 0.01 | $0.400 | $12.00 | 1.0M |
| Gemini 2.5 Flash-Lite | $< 0.01 | $0.400 | $12.00 | 1.0M | |
| Gemini 2.0 Flash | $< 0.01 | $0.400 | $12.00 | 1.0M | |
| Llama 3.3 70B | Meta | $< 0.01 | $0.450 | $13.50 | 131K |
| Gemma 4 26B A4B | $< 0.01 | $0.460 | $13.80 | 262K | |
| Gemma 4 31B | $< 0.01 | $0.480 | $14.40 | 262K | |
| Ministral 3 14B | Mistral | $< 0.01 | $0.500 | $15.00 | 262K |
| GPT-4o Mini | OpenAI | $< 0.01 | $0.600 | $18.00 | 128K |
| Mistral Small 4 | Mistral | $< 0.01 | $0.600 | $18.00 | 256K |
| Grok 4.1 Fast | xAI | $< 0.01 | $0.650 | $19.50 | 2.0M |
| Grok 4.1 Fast Reasoning | xAI | $< 0.01 | $0.650 | $19.50 | 2.0M |
| DeepSeek V3.2 (Chat) | DeepSeek | $< 0.01 | $0.770 | $23.10 | 128K |
| DeepSeek V3.2 (Reasoner) | DeepSeek | $< 0.01 | $0.770 | $23.10 | 128K |
| Grok 3 Mini | xAI | $< 0.01 | $0.850 | $25.50 | 131K |
| Llama 4 Maverick | Meta | $< 0.01 | $0.965 | $28.95 | 1.0M |
| Nemotron 3 Super 120B | NVIDIA | $< 0.01 | $1.00 | $30.00 | 1.0M |
| GPT-5.4 Nano | OpenAI | $< 0.01 | $1.03 | $30.75 | 400K |
| Codestral | Mistral | $< 0.01 | $1.05 | $31.50 | 256K |
| Grok Code Fast | xAI | $< 0.01 | $1.15 | $34.50 | 256K |
| MiniMax M2.5 | MiniMax | $< 0.01 | $1.20 | $36.00 | 128K |
| Gemini 3.1 Flash-Lite | $< 0.01 | $1.25 | $37.50 | 1.0M | |
| Qwen3.6-Plus | Alibaba | $< 0.01 | $1.38 | $41.33 | 1.0M |
| GPT-5 Mini | OpenAI | $< 0.01 | $1.50 | $45.00 | 400K |
| GPT-4.1 Mini | OpenAI | $< 0.01 | $1.60 | $48.00 | 1.0M |
| Mistral Large 3 | Mistral | $< 0.01 | $1.75 | $52.50 | 262K |
| Magistral Small | Mistral | $< 0.01 | $1.75 | $52.50 | 40K |
| Mistral Medium | Mistral | $< 0.01 | $1.80 | $54.00 | 131K |
| Devstral | Mistral | $< 0.01 | $1.80 | $54.00 | 256K |
| Qwen 3.5 27B | Alibaba | $< 0.01 | $1.80 | $54.00 | 128K |
| Gemini 2.5 Flash | $< 0.01 | $1.85 | $55.50 | 1.0M | |
| Nova 2.0 Lite | Amazon | $< 0.01 | $1.85 | $55.50 | 128K |
| DeepSeek R1 | DeepSeek | $< 0.01 | $2.19 | $65.85 | 128K |
| Kimi K2 Thinking | Moonshot | $< 0.01 | $2.45 | $73.50 | 262K |
| Gemini 3 Flash | $< 0.01 | $2.50 | $75.00 | 1.0M | |
| Gemini 3 Flash Reasoning | $< 0.01 | $2.50 | $75.00 | 1.0M | |
| Kimi K2.5 | Moonshot | $< 0.01 | $2.70 | $81.00 | 262K |
| Qwen 3.5 397B | Alibaba | $< 0.01 | $3.00 | $90.00 | 128K |
| Qwen3.5-Omni Plus | Alibaba | $< 0.01 | $3.20 | $96.00 | 262K |
| MiMo-V2-Pro | Xiaomi | $< 0.01 | $3.50 | $105 | 1.0M |
| Claude Haiku 3.5 | Anthropic | $< 0.01 | $3.60 | $108 | 200K |
| GLM-5 | Zhipu | $< 0.01 | $3.60 | $108 | 128K |
| GPT-5.4 Mini | OpenAI | $< 0.01 | $3.75 | $113 | 400K |
| Gemini 3.1 Flash Live | $< 0.01 | $3.75 | $113 | 1.0M | |
| GLM-5 Turbo | Zhipu | $< 0.01 | $4.40 | $132 | 200K |
| o4 Mini | OpenAI | $< 0.01 | $4.40 | $132 | 200K |
| o3 Mini | OpenAI | $< 0.01 | $4.40 | $132 | 200K |
| Claude Haiku 4.5 | Anthropic | $< 0.01 | $4.50 | $135 | 200K |
| Claude 4.5 Haiku Reasoning | Anthropic | $< 0.01 | $4.50 | $135 | 200K |
| Kimi K2 Thinking Turbo | Moonshot | $< 0.01 | $6.30 | $189 | 262K |
| Magistral Medium | Mistral | $< 0.01 | $6.50 | $195 | 40K |
| Grok 4.20 | xAI | $< 0.01 | $7.00 | $210 | 2.0M |
| GPT-5.1 | OpenAI | $< 0.01 | $7.50 | $225 | 400K |
| GPT-5 | OpenAI | $< 0.01 | $7.50 | $225 | 400K |
| GPT-5 Medium | OpenAI | $< 0.01 | $7.50 | $225 | 400K |
| Gemini 2.5 Pro | $< 0.01 | $7.50 | $225 | 1.0M | |
| Nova 2.0 Pro Reasoning | Amazon | $< 0.01 | $7.50 | $225 | 128K |
| GPT-4.1 | OpenAI | $< 0.01 | $8.00 | $240 | 1.0M |
| o3 | OpenAI | $< 0.01 | $8.00 | $240 | 200K |
| o4 Mini Deep Research | OpenAI | $< 0.01 | $8.00 | $240 | 200K |
| Grok 2 | xAI | $< 0.01 | $9.00 | $270 | 131K |
| GPT-4o | OpenAI | $0.010 | $10.00 | $300 | 128K |
| Gemini 3.1 Pro | $0.010 | $10.00 | $300 | 1.0M | |
| Gemini 3 Pro | $0.010 | $10.00 | $300 | 1.0M | |
| Command A | Cohere | $0.010 | $10.00 | $300 | 128K |
| GPT-5.2 | OpenAI | $0.011 | $10.50 | $315 | 400K |
| GPT-5.3 Codex | OpenAI | $0.011 | $10.50 | $315 | 400K |
| Gemini 3.1 Flash TTS | $0.012 | $12.00 | $360 | 32K | |
| GPT-5.4 | OpenAI | $0.013 | $12.50 | $375 | 1.1M |
| Claude Sonnet 4.6 Adaptive | Anthropic | $0.013 | $13.50 | $405 | 200K |
| Claude Sonnet 4.6 | Anthropic | $0.013 | $13.50 | $405 | 200K |
| Claude Sonnet 4.5 | Anthropic | $0.013 | $13.50 | $405 | 200K |
| Claude Sonnet 4 | Anthropic | $0.013 | $13.50 | $405 | 200K |
| Claude 3.7 Sonnet | Anthropic | $0.013 | $13.50 | $405 | 200K |
| Grok 4 | xAI | $0.013 | $13.50 | $405 | 2.0M |
| Grok 3 | xAI | $0.013 | $13.50 | $405 | 131K |
| Sonar Pro | Perplexity | $0.013 | $13.50 | $405 | 128K |
| Claude Opus 4.7 | Anthropic | $0.022 | $22.50 | $675 | 1.0M |
| Claude Opus 4.6 Adaptive | Anthropic | $0.022 | $22.50 | $675 | 200K |
| Claude Opus 4.6 | Anthropic | $0.022 | $22.50 | $675 | 200K |
| Claude Opus 4.5 | Anthropic | $0.022 | $22.50 | $675 | 200K |
| MAI-Image-2 | Microsoft | $0.027 | $26.50 | $795 | 32K |
| Voxtral TTS | Mistral | $0.032 | $32.00 | $960 | 128K |
| o3 Deep Research | OpenAI | $0.040 | $40.00 | $1,200 | 200K |
| o1 | OpenAI | $0.060 | $60.00 | $1,800 | 200K |
| Claude Opus 4.1 | Anthropic | $0.068 | $67.50 | $2,025 | 200K |
| o3-pro | OpenAI | $0.080 | $80.00 | $2,400 | 200K |
| Claude Mythos Preview | Anthropic | $0.113 | $113 | $3,375 | 1.0M |
| GPT-5.4 Pro | OpenAI | $0.150 | $150 | $4,500 | 1.1M |
Costs are estimates based on token counts and published API rates. Actual costs may vary with caching, batching, and rate tier discounts. Exchange rates are approximate.
How to Estimate Monthly LLM API Costs
- 1
Set your usage parameters
Enter your average prompt size, response length, and daily call volume. Pick a preset like Chatbot or RAG to auto-fill typical values.
- 2
Review monthly estimates
The calculator shows estimated monthly costs for every model, sorted from cheapest to most expensive.
- 3
Filter and compare
Narrow results by provider, switch currencies, and find the model that fits your budget and performance needs.
Why Use This Cost Calculator
- Built-in presets for Chatbot, RAG, Code Generation, and Summarizer workloads
- 60+ models compared side by side with real pricing data from each provider
- Multi-currency support — see costs in USD, EUR, GBP, INR, or JPY
- Adjustable prompt size, response size, and daily call volume with instant recalculation
- Provider filtering to focus on the models you're actually considering
Common Use Cases
Startup budgeting
Estimate monthly API costs before you build. Compare providers to find the best price-to-performance ratio for your use case.
Scaling projections
Model how costs grow as your daily call volume increases. Identify where you'd hit budget limits.
Provider comparison
Compare the total monthly cost of running the same workload on GPT-5 vs Claude vs Gemini.
Use case optimization
See how switching from long prompts to shorter ones, or vice versa, affects your bill across models.
Related Tools
Frequently Asked Questions
Common questions about estimating LLM API costs