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

Prompt cache hit rate 0%

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

0≈ tokens (chars ÷ 4)
0words
0characters

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.

Frequently asked questions

How much does the GPT‑5.6 API cost?
As of August 2026, per million tokens: GPT‑5.6 Sol $5 in / $30 out, GPT‑5.6 Terra $2 / $12, GPT‑5.6 Luna $0.20 / $1.20. Cached input bills at ~10% of the input rate, and the Batch API takes a further 50% off.
How much does the Claude API cost?
Anthropic prices Claude Fable 5 at $10 / $50 per million tokens, Claude Opus 5 at $5 / $25, Claude Sonnet 5 at $2 / $10 (promo through Aug 31, 2026; standard $3 / $15), and Claude Haiku 4.5 at $1 / $5.
What's the cheapest LLM API right now?
For rock-bottom cost: Llama 3.1 8B via inference providers (~$0.02 / $0.05), DeepSeek V4 Flash ($0.14 / $0.28), Gemini 2.5 Flash‑Lite ($0.10 / $0.40), or GPT‑5.6 Luna ($0.20 / $1.20). Use the calculator above to see which is cheapest for your input/output mix.
How many tokens is 1,000 words?
Roughly 1,330 tokens for English prose (1 token ≈ 0.75 words). CJK languages and source code usually tokenize less efficiently, so budget extra.
Do caching and batch discounts stack?
Provider-dependent. Some allow batch requests to also hit the prompt cache; others don't. This calculator applies both when toggled, as an optimistic estimate — check your provider's docs before committing.
Where do these prices come from?
Compiled from providers' public pricing pages and reputable trackers, last verified on the date shown in the header. Prices change often — always confirm on the official pricing page before signing a contract.

Go deeper