22 Models · OpenAI, Anthropic, Google, DeepSeek, xAI, Qwen & Mistral

AI API Token & Cloud Cost Simulator

Pick a workload preset or paste your prompt, dial in prompt caching hit rates, and compare real monthly bills across 22 leading AI models.

Quick Workload Presets
10,000 / day (300,000/mo)
2,500 tokens
600 tokens
50% cached

Automatically updates input tokens above using real-time length estimation.

Monthly Cost Comparison (22 Models · Cheapest First)

ModelTierInput / Output (1M)Monthly BillCache SavingsDeploy / Credits
GPT-6 LunaOpenAIBudget$0.10 / $0.50$131.25-$33.75Deploy via OpenRouter
Claude Haiku 5.5AnthropicBudget$0.10 / $0.50$131.25-$33.75Claim Cloud Credits
DeepSeek V4.1 FlashDeepSeekBudget$0.15 / $0.60$165.38-$55.13Route via OpenRouter
GPT-OSS 120B (Groq)GroqBudget$0.15 / $0.60$178.13-$42.38Run Fast on Groq
Qwen 3.7 PlusQwenWorkhorse$0.32 / $1.28$362.40-$108.00Route via OpenRouter
Gemini 3.1 Flash-LiteGoogleBudget$0.25 / $1.50$373.13-$84.38Claim $300 GCP Credits
Qwen 3.6 FlashQwenBudget$0.25 / $1.50$373.13-$84.38Route via OpenRouter
Mistral Large 3MistralWorkhorse$0.50 / $1.50$476.25-$168.75Route via OpenRouter
Gemini 3.5 Flash-LiteGoogleBudget$0.30 / $2.50$573.75-$101.25Claim $300 GCP Credits
DeepSeek V4 ProDeepSeekWorkhorse$0.66 / $1.98$612.15-$239.25Route via OpenRouter
Grok 4.20xAIWorkhorse$1.25 / $2.50$965.63-$421.88Route via OpenRouter
Gemini 3.8 FlashGoogleWorkhorse$0.75 / $3.75$984.38-$253.13Claim $300 GCP Credits
GPT-6.1 TerraOpenAIWorkhorse$1.00 / $5.00$1,312.50-$337.50Route via OpenRouter
Mistral Large 4MistralFrontier$1.36 / $4.18$1,313.40-$459.00Route via OpenRouter
Grok 4.5xAIFrontier$2.00 / $6.00$1,905.00-$675.00Route via OpenRouter
Qwen 3.7 MaxQwenFrontier$2.50 / $7.50$2,381.25-$843.75Route via OpenRouter
GPT-6.1 SolOpenAIWorkhorse$2.00 / $10.00$2,587.50-$712.50Route via OpenRouter
Claude Sonnet 5.5AnthropicWorkhorse$2.00 / $10.00$2,587.50-$712.50Deploy on Cloud
Gemini 4 ArgonGoogleFrontier$2.00 / $10.00$2,587.50-$712.50Claim $300 GCP Credits
Claude Opus 5.5AnthropicFrontier$4.00 / $20.00$5,175.00-$1425.00Deploy on Cloud
GPT-6 AstraOpenAIFrontier$10.00 / $50.00$13,125.00-$3375.00Route via OpenRouter
Claude Fable 5.1AnthropicFrontier$10.00 / $50.00$13,125.00-$3375.00Deploy on Cloud

AI API Pricing & Prompt Caching FAQ

How are LLM API tokens calculated?

For English text and code, 1,000 tokens is roughly 750 words or 4,000 characters. Providers bill input tokens (your prompt and context) and output tokens (the generated reply) separately per 1 million tokens.

How much does Prompt Caching save on AI API bills?

Prompt caching discounts repeated system instructions, tools, or RAG context by up to 90% on input tokens across OpenAI, Anthropic, and Google models.

When should I use the Async Batch API?

If your workload does not require instant real-time responses (such as overnight data extraction, classification, or bulk summarization), Batch APIs cut token costs by 50%.

Popular Model Cost Comparisons (231 Total Pairs)

Browse all 231 comparisons →