# LLM Cost & Capacity Calc

Token estimates, API cost, prompt-cache savings, batch discounts, context fit, rate-limit planning and model comparison from your own prices.

## How to pay

Machine-payable over x402. USDC on: Base (eip155:8453), Solana (solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp), Polygon (eip155:137), Arbitrum One (eip155:42161).
No accounts. No API keys. No signup. The paying wallet is the account.

## Machine-readable

- OpenAPI: https://llm-cost-calc.x402tookit.com/openapi.json
- x402 manifest: https://llm-cost-calc.x402tookit.com/.well-known/x402
- Catalog (free): https://llm-cost-calc.x402tookit.com/catalog
- Health (free): https://llm-cost-calc.x402tookit.com/health
- Uptime (free): https://llm-cost-calc.x402tookit.com/uptime

## Endpoints (8)

### GET /batch-discount — $0.02
Compare realtime and batch API cost for a workload with your discount fraction, and the money saved by waiting.
Params: inputTokens: number, outputTokens: number, requests: integer, inputPricePerMTok: number, outputPricePerMTok: number, batchDiscount?: number
Example: https://llm-cost-calc.x402tookit.com/batch-discount?inputTokens=2000&outputTokens=300&requests=100000&inputPricePerMTok=3&outputPricePerMTok=15&batchDiscount=0.5

### GET /cache-savings — $0.02
Prompt-cache savings for a shared prefix: cost with and without caching, break-even requests and percent saved.
Params: prefixTokens: number, uncachedTokens?: number, requests: integer, inputPricePerMTok: number, writeMultiplier?: number, readMultiplier?: number
Example: https://llm-cost-calc.x402tookit.com/cache-savings?prefixTokens=20000&uncachedTokens=500&requests=50&inputPricePerMTok=3

### GET /context-fit — $0.02
Check whether a prompt fits a context window with output reserve, and how many more chat turns fit.
Params: contextWindow: number, promptTokens: number, maxOutputTokens?: number, tokensPerTurn?: number, safetyPercent?: number
Example: https://llm-cost-calc.x402tookit.com/context-fit?contextWindow=200000&promptTokens=150000&maxOutputTokens=4096&tokensPerTurn=1500

### GET /llm-cost — $0.02
Cost of LLM API calls from input and output tokens and your per-million-token prices, per request and in total.
Params: inputTokens: number, outputTokens: number, inputPricePerMTok: number, outputPricePerMTok: number, requests?: integer
Example: https://llm-cost-calc.x402tookit.com/llm-cost?inputTokens=3000&outputTokens=500&inputPricePerMTok=3&outputPricePerMTok=15&requests=1000

### GET /model-compare — $0.02
Rank 2 to 20 models by cost for a workload from your own prices; flags models whose context window is too small.
Params: models: string, inputTokens: number, outputTokens: number, requests?: integer
Example: https://llm-cost-calc.x402tookit.com/model-compare?models=%5B%7B%22name%22%3A%22Big%22%2C%22inputPricePerMTok%22%3A15%2C%22outputPricePerMTok%22%3A75%2C%22contextWindow%22%3A200000%7D%2C%7B%22name%22%3A%22Mid%22%2C%22inputPricePerMTok%22%3A3%2C%22outputPricePerMTok%22%3A15%2C%22contextWindow%22%3A200000%7D%2C%7B%22name%22%3A%22Small%22%2C%22inputPricePerMTok%22%3A0.25%2C%22outputPricePerMTok%22%3A1.25%2C%22contextWindow%22%3A32000%7D%5D&inputTokens=5000&outputTokens=800&requests=10000

### GET /monthly-budget — $0.02
Forecast monthly and yearly LLM spend from daily requests, tokens and prices, with monthly growth and per-user cost.
Params: requestsPerDay: number, inputTokens: number, outputTokens: number, inputPricePerMTok: number, outputPricePerMTok: number, monthlyGrowthPercent?: number, months?: integer, users?: integer
Example: https://llm-cost-calc.x402tookit.com/monthly-budget?requestsPerDay=2000&inputTokens=1500&outputTokens=400&inputPricePerMTok=3&outputPricePerMTok=15&monthlyGrowthPercent=10&months=12&users=500

### GET /rate-limit-plan — $0.02
Sustainable requests per minute under RPM and TPM limits, job duration for N requests, and concurrency needed.
Params: requestsPerMinuteLimit: number, tokensPerMinuteLimit: number, tokensPerRequest: number, totalRequests?: integer, secondsPerRequest?: number
Example: https://llm-cost-calc.x402tookit.com/rate-limit-plan?requestsPerMinuteLimit=1000&tokensPerMinuteLimit=400000&tokensPerRequest=2500&totalRequests=20000&secondsPerRequest=6

### GET /token-estimate — $0.02
Rough LLM token estimate of text from characters and words, as a low-high range by content type. Not a tokenizer.
Params: text: string, kind?: string
Example: https://llm-cost-calc.x402tookit.com/token-estimate?text=The+quick+brown+fox+jumps+over+the+lazy+dog.&kind=english

## Terms

Arithmetic on prices, limits and token counts that the CALLER supplies: no provider price list is built in, because prices change. Token estimates are rough heuristics, not a tokenizer; real counts differ by model and language. Not a quote or a billing statement.