Skip to main content
TokenCost logoTokenCost

Monthly Cost Calculator

Estimate your monthly LLM API spend. Set your average prompt size, response size, and daily call volume.

Quick Presets
per API call
per API call
30,000/month
Cheapest / month
$5.19
GPT-OSS 120B
Most expensive / month
$4,500
GPT-5.4 Pro
Monthly calls
30,000
2500 tokens/call
ModelProviderPer CallDailyMonthlyContext
GPT-OSS 120BOpenAI$< 0.01$0.173$5.19131K
Qwen3.5-9BAlibaba$< 0.01$0.175$5.25262K
Qwen3.5-Omni FlashAlibaba$< 0.01$0.260$7.80262K
GPT-OSS 20BOpenAI$< 0.01$0.300$9.00131K
Gemini 2.0 Flash-LiteGoogle$< 0.01$0.300$9.001.0M
GPT-5 NanoOpenAI$< 0.01$0.300$9.00128K
Llama 4 ScoutMeta$< 0.01$0.310$9.301.0M
Devstral SmallMistral$< 0.01$0.350$10.50256K
Mistral Small 3.2Mistral$< 0.01$0.350$10.50128K
Ministral 3 8BMistral$< 0.01$0.375$11.25262K
GPT-4.1 NanoOpenAI$< 0.01$0.400$12.001.0M
Gemini 2.5 Flash-LiteGoogle$< 0.01$0.400$12.001.0M
Gemini 2.0 FlashGoogle$< 0.01$0.400$12.001.0M
Llama 3.3 70BMeta$< 0.01$0.450$13.50131K
Gemma 4 26B A4BGoogle$< 0.01$0.460$13.80262K
Gemma 4 31BGoogle$< 0.01$0.480$14.40262K
Ministral 3 14BMistral$< 0.01$0.500$15.00262K
GPT-4o MiniOpenAI$< 0.01$0.600$18.00128K
Mistral Small 4Mistral$< 0.01$0.600$18.00256K
Grok 4.1 FastxAI$< 0.01$0.650$19.502.0M
Grok 4.1 Fast ReasoningxAI$< 0.01$0.650$19.502.0M
DeepSeek V3.2 (Chat)DeepSeek$< 0.01$0.770$23.10128K
DeepSeek V3.2 (Reasoner)DeepSeek$< 0.01$0.770$23.10128K
Grok 3 MinixAI$< 0.01$0.850$25.50131K
Llama 4 MaverickMeta$< 0.01$0.965$28.951.0M
Nemotron 3 Super 120BNVIDIA$< 0.01$1.00$30.001.0M
GPT-5.4 NanoOpenAI$< 0.01$1.03$30.75400K
CodestralMistral$< 0.01$1.05$31.50256K
Grok Code FastxAI$< 0.01$1.15$34.50256K
MiniMax M2.5MiniMax$< 0.01$1.20$36.00128K
Gemini 3.1 Flash-LiteGoogle$< 0.01$1.25$37.501.0M
Qwen3.6-PlusAlibaba$< 0.01$1.38$41.331.0M
GPT-5 MiniOpenAI$< 0.01$1.50$45.00400K
GPT-4.1 MiniOpenAI$< 0.01$1.60$48.001.0M
Mistral Large 3Mistral$< 0.01$1.75$52.50262K
Magistral SmallMistral$< 0.01$1.75$52.5040K
Mistral MediumMistral$< 0.01$1.80$54.00131K
DevstralMistral$< 0.01$1.80$54.00256K
Qwen 3.5 27BAlibaba$< 0.01$1.80$54.00128K
Gemini 2.5 FlashGoogle$< 0.01$1.85$55.501.0M
Nova 2.0 LiteAmazon$< 0.01$1.85$55.50128K
DeepSeek R1DeepSeek$< 0.01$2.19$65.85128K
Kimi K2 ThinkingMoonshot$< 0.01$2.45$73.50262K
Gemini 3 FlashGoogle$< 0.01$2.50$75.001.0M
Gemini 3 Flash ReasoningGoogle$< 0.01$2.50$75.001.0M
Kimi K2.5Moonshot$< 0.01$2.70$81.00262K
Qwen 3.5 397BAlibaba$< 0.01$3.00$90.00128K
Qwen3.5-Omni PlusAlibaba$< 0.01$3.20$96.00262K
MiMo-V2-ProXiaomi$< 0.01$3.50$1051.0M
Claude Haiku 3.5Anthropic$< 0.01$3.60$108200K
GLM-5Zhipu$< 0.01$3.60$108128K
GPT-5.4 MiniOpenAI$< 0.01$3.75$113400K
Gemini 3.1 Flash LiveGoogle$< 0.01$3.75$1131.0M
GLM-5 TurboZhipu$< 0.01$4.40$132200K
o4 MiniOpenAI$< 0.01$4.40$132200K
o3 MiniOpenAI$< 0.01$4.40$132200K
Claude Haiku 4.5Anthropic$< 0.01$4.50$135200K
Claude 4.5 Haiku ReasoningAnthropic$< 0.01$4.50$135200K
Kimi K2 Thinking TurboMoonshot$< 0.01$6.30$189262K
Magistral MediumMistral$< 0.01$6.50$19540K
Grok 4.20xAI$< 0.01$7.00$2102.0M
GPT-5.1OpenAI$< 0.01$7.50$225400K
GPT-5OpenAI$< 0.01$7.50$225400K
GPT-5 MediumOpenAI$< 0.01$7.50$225400K
Gemini 2.5 ProGoogle$< 0.01$7.50$2251.0M
Nova 2.0 Pro ReasoningAmazon$< 0.01$7.50$225128K
GPT-4.1OpenAI$< 0.01$8.00$2401.0M
o3OpenAI$< 0.01$8.00$240200K
o4 Mini Deep ResearchOpenAI$< 0.01$8.00$240200K
Grok 2xAI$< 0.01$9.00$270131K
GPT-4oOpenAI$0.010$10.00$300128K
Gemini 3.1 ProGoogle$0.010$10.00$3001.0M
Gemini 3 ProGoogle$0.010$10.00$3001.0M
Command ACohere$0.010$10.00$300128K
GPT-5.2OpenAI$0.011$10.50$315400K
GPT-5.3 CodexOpenAI$0.011$10.50$315400K
Gemini 3.1 Flash TTSGoogle$0.012$12.00$36032K
GPT-5.4OpenAI$0.013$12.50$3751.1M
Claude Sonnet 4.6 AdaptiveAnthropic$0.013$13.50$405200K
Claude Sonnet 4.6Anthropic$0.013$13.50$405200K
Claude Sonnet 4.5Anthropic$0.013$13.50$405200K
Claude Sonnet 4Anthropic$0.013$13.50$405200K
Claude 3.7 SonnetAnthropic$0.013$13.50$405200K
Grok 4xAI$0.013$13.50$4052.0M
Grok 3xAI$0.013$13.50$405131K
Sonar ProPerplexity$0.013$13.50$405128K
Claude Opus 4.7Anthropic$0.022$22.50$6751.0M
Claude Opus 4.6 AdaptiveAnthropic$0.022$22.50$675200K
Claude Opus 4.6Anthropic$0.022$22.50$675200K
Claude Opus 4.5Anthropic$0.022$22.50$675200K
MAI-Image-2Microsoft$0.027$26.50$79532K
Voxtral TTSMistral$0.032$32.00$960128K
o3 Deep ResearchOpenAI$0.040$40.00$1,200200K
o1OpenAI$0.060$60.00$1,800200K
Claude Opus 4.1Anthropic$0.068$67.50$2,025200K
o3-proOpenAI$0.080$80.00$2,400200K
Claude Mythos PreviewAnthropic$0.113$113$3,3751.0M
GPT-5.4 ProOpenAI$0.150$150$4,5001.1M

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. 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. 2

    Review monthly estimates

    The calculator shows estimated monthly costs for every model, sorted from cheapest to most expensive.

  3. 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