LLM API Pricing Calculator 2026
Compare token prices for 29 models from OpenAI, Anthropic, Google, xAI, DeepSeek, Mistral and Meta — and estimate your real monthly bill, including prompt-caching and batch discounts.
1 · Describe your workload
2 · Compare monthly cost across models
| Vendor | Model | Context | Input $/1M | Output $/1M | $ / request | Monthly ▲ |
|---|
Cache-hit input is billed at each vendor's cached rate (≈10% of input) where supported; models without published cached pricing ignore the cache slider. Batch −50% is applied to both input and output where offered. Claude Sonnet 5 shows a promotional rate through Aug 31, 2026 (standard $3 / $15).
Token counter — paste text, get a token estimate
Rule of thumb for English: 1 token ≈ 4 characters ≈ 0.75 words. Korean, Japanese and code typically use more tokens per character. Exact counts depend on each model's tokenizer.
How LLM API pricing works in 2026
Every major AI provider bills by the token — roughly a word fragment. You pay separately for input tokens (your prompt, system message, retrieved context) and output tokens (the model's reply). Output tokens cost 2–6× more than input tokens, so long-form generation is what really drives your bill.
Two discounts matter more than the sticker price. Prompt caching bills repeated prompt prefixes (system prompts, few-shot examples, long documents) at about 10% of the normal input rate — a chatbot with a 3,000-token system prompt saves dramatically at scale. The Batch API gives roughly 50% off both directions when you can wait minutes-to-hours for results, which suits evals, ETL and bulk summarization.
The spread between models is enormous: as of August 2026, a million output tokens runs from about $0.05 (Llama 3.1 8B via providers) to $180 (GPT‑5.5 Pro) — a 3,600× range. Picking the smallest model that clears your quality bar is the single biggest cost lever, ahead of caching, batching, or prompt trimming.