LLM Cost Explorer

Monthly LLM API cost per model for your workload, with prompt-caching and batch savings.

Prices from

Model prices (USD per 1M tokens)

Model prices (USD per 1M tokens)
#	Model	Input	Output	Cache read	Cache write	Context window
1
2
3
4

OpenRouter model ids

e.g. openai/gpt-4o-mini – one per line. Empty in paste mode = all pasted models.

OpenRouter models JSON

Requests per day (required)

Input tokens per request (required) tokens

Output tokens per request (required) tokens

Cacheable prompt prefix %

Share of input tokens that repeat across requests (system prompt, tools, documents).

Cache hit rate %

Share of requests sent via batch API %

Batch discount %

Days per month

Monthly budget (optional) USD

Try an example: Support bot: 5,000 requests/day, cached system prompt (example prices you entered) · RAG workload on real OpenRouter prices (pasted snapshot 2026-10-14)

How it works

Calculates what an LLM workload costs per request and per month on each model – requests per day, input and output tokens, the share of the prompt that can be cached, cache hit rate and batch discounts – using live prices from OpenRouter's public models API, a pasted copy of it, or prices you enter. Shows caching and batch savings, the cheapest models that fit your context and budget, and a cost comparison chart.

Per request: input cost = uncached tokens × input price + cacheable tokens × (hit rate × cache-read price + (1 − hit rate) × cache-write price); output cost = output tokens × output price. Prices are per 1M tokens.
If a model has no cache-read price, caching is not modelled for it (all input at the normal input price). If no cache-write price is listed, misses are charged at the normal input price.
Batch: the batch share of requests gets the batch discount on the whole request (as with typical 50 % batch APIs).
Monthly = per request × requests/day × days per month (default 30.4). Context check: input + output tokens must fit the context window when it is known.
OpenRouter prices come from GET https://openrouter.ai/api/v1/models (pricing.prompt, completion, input_cache_read, input_cache_write in USD per token).

For scripts and AI agents

JSON API: POST https://llmcostexplorer.usefulweb.site/api/v1/calculate (same calculation as this page)
Interface description: OpenAPI 3.1 · AI guide: llms.txt
MCP server (Streamable HTTP): https://llmcostexplorer.usefulweb.site/mcp · tool name llm_cost_explorer

Example request

curl -s -X POST https://llmcostexplorer.usefulweb.site/api/v1/calculate \
  -H 'content-type: application/json' \
  -d '{"priceSource":"manual","prices":[{"model":"Large model (example)","inputPerM":3,"outputPerM":15,"cacheReadPerM":0.3,"cacheWritePerM":3.75,"contextTokens":200000},{"model":"Mid model (example)","inputPerM":0.4,"outputPerM":1.6,"cacheReadPerM":0.1,"contextTokens":1000000},{"model":"Small model (example)","inputPerM":0.1,"outputPerM":0.4,"contextTokens":8000}],"requestsPerDay":5000,"inputTokens":12000,"outputTokens":400,"cacheablePct":75,"cacheHitRate":90,"budget":2000}'

Related tools

AI Model Compatibility Explorer – Which LLMs take images, audio or files, fit your context and support tools or structured outputs?
Model Behavior Regression Explorer – Compare eval results of two model versions: accuracy, regressions, McNemar p-value, flaky items.