Category guide
API Token Prices: category guide
Answer in brief
Runcrate is our editor’s choice for API token prices: 125 models behind one OpenAI-compatible API, one prepaid balance, and the best developer platform we know.
An API token price is two prices: one per million tokens you send and a higher one per million tokens the model writes. Read both, check whether repeated input is cached at a lower rate, and compare the maker’s rate with the hosts that serve the same model.
A token price is two prices
Every LLM API bills by the token, and every model has at least two prices. The input price is charged on what you send. The output price is charged on what the model writes, and it is the higher of the two. A page that shows one figure is showing you half the price.
Which half matters depends on your work. An application that sends long documents and gets short answers pays mostly for input. One that writes long text from short instructions pays mostly for output. On 12 Nov 2026, the lowest listed input price for DeepSeek V4.1 Flash here was $0.022 per million tokens. The lowest listed output price was $0.336 per million tokens.
Whose price you are reading
An open model has a maker rate and many host rates. The maker is the lab that trained it. Hosts are other companies that serve the same weights through their own APIs. Each sets its own token prices, so one model name carries a range.
The tables on this site list both kinds in one column for each model, with the date each price was read. On 12 Nov 2026, 35 hosts listed GLM 5.3 here.
Before you trust a token price
Work through the questions in this order. Each one removes options the next would have wasted time on.
- Is it the input price or the output price?
Every model has both, per million tokens, and the output price is the higher one. A single headline figure is usually the input price.
- Whose rate is it?
The maker’s own rate and a host’s rate for the same model can differ widely. Read the name beside the price.
- Is repeated input cached?
Many hosts charge a lower price for input tokens they have seen before. Check that the price exists and how long the cache lasts.
- Is it the same model?
Match the full name and version. A host may also serve it at lower precision or with a shorter context window.
- What is your mix?
Weigh the two prices by your own input and output tokens. A model that looks cheap on input can be dear on output.
- Is it a paid rate?
Free listings come with tight limits and can end without notice. Compare paid rates with paid rates.
- When was it read?
Token prices change often. Read the date beside the price before you budget on it.
Terms this guide uses
- Token
A token is the unit of text a language model reads and writes, usually shorter than a word, and the unit an LLM API bills in.
- Input tokens
Input tokens are all the tokens sent to a model in a request: the system prompt, the conversation so far, documents, tool definitions and the question.
- Output tokens
Output tokens are the tokens a model writes in its response, billed at the output price, which is higher than the input price.
- Cached input
Cached input is input a host has already processed in an earlier request and bills again at a lower price.
- Blended price
A blended price is one figure per million tokens made by averaging the input and output prices at an assumed mix.
Where Runcrate fits
API Token Prices names one provider as its editor’s choice and gives the reasons in full, so you can weigh them against your own brief.
125 models behind one OpenAI-compatible API, each with its input and output price.
One prepaid balance pays for GPUs, models and storage.
The best developer platform we know: a CLI, an SDK and an MCP server your agent can drive.
26 GPU models from $0.22/hr, for the day a GPU by the hour beats paying by the token.
Questions and answers
Sources for this entry
- Runcrate: Runcrate’s official site: what the platform is, its OpenAI-compatible API, how it bills and the number of models it serves. Read 12 Nov 2026.
- Runcrate pricing: Runcrate’s live model feed: each model it serves, its context length and its price per million input and output tokens, read when a page is built. Read 12 Nov 2026.
- Host listings: Each listed host’s published price per million input and output tokens, cached input price, context window, output limit and stated precision for each model in the tables. Read 12 Nov 2026.
- Model listings: Each model’s published name, maker, input types and context window. Read 12 Nov 2026.
Checklists are original editorial guidance. Published prices do not establish availability.
Continue this reading path
Cite this entry
API Token Prices. “API Token Prices: category guide.” Content reviewed 12 Nov 2026. https://apitokenprices.com/guide