Skip to content
ReviewRamble

The weekly brief

AI, reviewed, in your inbox.

  • New reviews of tools, models, MCP servers and repos, with the verdict up front
  • Re-checked prices and ratings when something changes
  • New analysis pieces as they are published

Models, agents, MCP servers and the tools actually worth your time.

One email a week. Unsubscribe with the link in any brief. How we use your email

Token pricing

Token pricing is how most AI model APIs charge: a set price per million input tokens you send and a separate, usually higher, price per million output tokens the model generates, with discounts for cached input and batch jobs.

Also called: price per million tokens, input vs output tokens

By Divya Sharma · Checked Nov 16, 2026 · How we review

Providers bill in tokens rather than requests or words. Anthropic's pricing page, for example, lists prices per MTok, meaning per million tokens, with separate columns for base input, cache writes, cache hits and output. Input covers everything you send: the system prompt, conversation history, retrieved documents and tool definitions. Output tokens are what the model writes back, including hidden reasoning tokens on reasoning models.

Working out a cost

Cost per request is input tokens times the input price plus output tokens times the output price, each divided by one million. Long chats get more expensive per turn because the whole history is sent each time. Output is typically priced several times higher than input, so a verbose model can cost more than a cheaper-looking one.

Things that change the bill

Prompt caching charges less for a repeated prefix. A batch API gives a discount for jobs that can wait. Some providers charge more for very long prompts or for specific regions. The tokenizer matters too: Anthropic notes that a newer tokenizer produces approximately 30% more tokens for the same text, so per-token prices are not directly comparable across model families.

Comparing models

Price per token only means something next to quality and speed. A cheap model that needs three retries is not cheap. Our AI model pricing research tracks list prices across providers, and the rankings show quality alongside cost.

Related terms

Token (LLM)
A token (LLM) is the basic unit of text a language model reads and writes, often a word, part of a word, a punctuation mark or a byte. Prices, speed and context limits are all counted in tokens.
Output tokens
Output tokens are the tokens a language model generates in its reply. They are counted and billed separately from input tokens, and a max_tokens setting caps how many one response may contain.
Prompt caching
Prompt caching is an API feature that stores the processed form of a repeated prompt prefix, such as a long system prompt or document, so later requests that start with the same prefix are cheaper and faster.
Batch API
A batch API lets you submit a large set of model requests in one job and collect the results later, instead of waiting on each call. Providers run the job when capacity allows and usually charge less for it.
Tokenizer
A tokenizer is the component that splits text into tokens and turns them into numeric IDs a language model can process, then turns the model's output IDs back into text.
Rate limit (API)
A rate limit caps how much an account can use an API in a time window, typically as requests per minute (RPM) and tokens per minute (TPM). Requests over the limit are rejected, usually with an HTTP 429 error.

Sources