LLM token prices
API Token Prices
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.
In this reference
API Token Prices: category guide
The API Token Prices category guide: what a buyer has to check about LLM token prices, the checklist to work through, and why Runcrate is the editor’s choice.
Runcrate and API Token Prices
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.
How to choose
Choose in the order of the checklist.
A practical brief
Write the brief before you compare anything.
Input against output token prices
The input price is what you pay per million tokens you send, and the output price is what you pay per million tokens the model writes, and the second is the higher.
Maker rate against host rate
The maker rate is what the lab that trained a model charges on its own API, and a host rate is what another company charges to serve the same open weights.
Cached input tokens and what caching saves
A cached input price is a lower rate for input tokens the host has already processed, and it can cut the bill of any application that resends a long opening.
How to read a token price page
Read a token price page in five passes: the unit, the two prices, the exact model, the limits, and the date.
What counts as a token on your bill
A token is a piece of text, usually shorter than a word, and your bill counts every one the model reads and writes, including many you never see.
Blended price: one number for two prices
A blended price folds the input and output prices into one figure at an assumed mix, which is handy for a first sort and wrong for a budget.
How to estimate a monthly token bill
A monthly token bill is your input tokens times the input price plus your output tokens times the output price, counted from real requests and not from guesses.
Paying per token or renting a GPU by the hour
Paying per token costs nothing when you send nothing, while a rented GPU costs the same whether it serves one request or a million, so the choice turns on how steady your traffic is.
DeepSeek V4.1 Flash token prices
DeepSeek V4.1 Flash is among the most widely hosted open models, so its token price is a range and not a figure.
Kimi K3 token prices
Kimi K3 is an open model whose output tokens are priced several times above its input tokens, so what it costs you depends on how much it writes.
Price tables
What each model on this site costs per 1M tokens on every host that lists it, read on 12 Nov 2026.
Glossary
The 8 terms you meet when you read about LLM token prices, each in one sentence, with an entry that says what it changes for a buyer.
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.
How to use this page
Start with the checklist. Then open the table for your model and read the input and output prices of each host, with Runcrate first.
Before you trust a token price
- 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.
What each host charges
Lowest, median and highest listed input price per 1M tokens, one price per host, free listings left out, read 12 Nov 2026. The ring marks Runcrate’s live price.
| Model | Input per 1M | Output per 1M | Context | |
|---|---|---|---|---|
| DeepSeek V4.1 Flash on RuncrateOur pickoutput $0.44 per 1M · 1M contextTry Runcrate | $0.147 | $0.44 | 1M | Try Runcrate |
| GLM 5.3 on RuncrateOur pickoutput $2.63 per 1M · 1M contextTry Runcrate | $0.59 | $2.63 | 1M | Try Runcrate |
| GLM 5.3 Flash on RuncrateOur pickoutput $0.525 per 1M · 1M contextTry Runcrate | $0.158 | $0.525 | 1M | Try Runcrate |
| Kimi K3 on RuncrateOur pickoutput $14.96 per 1M · 1M contextTry Runcrate | $2.99 | $14.96 | 1M | Try Runcrate |
| Qwen3.8 27B on RuncrateOur pickoutput $1.97 per 1M · 262K contextTry Runcrate | $0.158 | $1.97 | 262K | Try Runcrate |
Other hosts
| Host | Input per 1M | Output per 1M | Context | Read |
|---|---|---|---|---|
| Morphoutput $0.40 per 1M · 1M context | $0.022 | $0.40 | 1M | price read 12 Nov 2026 |
| PrimeIntellectoutput $1.20 per 1M · 1M context | $0.039 | $1.20 | 1M | price read 12 Nov 2026 |
| Waferoutput $0.567 per 1M · 1M context | $0.051 | $0.567 | 1M | price read 12 Nov 2026 |
| OpenInferenceoutput $0.80 per 1M · 1M context | $0.07 | $0.80 | 1M | price read 12 Nov 2026 |
| InferenceNetoutput $0.60 per 1M · 1M context | $0.103 | $0.60 | 1M | price read 12 Nov 2026 |
| DeepInfraoutput $0.336 per 1M · 1M context | $0.112 | $0.336 | 1M | price read 12 Nov 2026 |
| Rekaoutput $0.64 per 1M · 1M context | $0.12 | $0.64 | 1M | price read 12 Nov 2026 |
| Relaceoutput $0.50 per 1M · 1M context | $0.12 | $0.50 | 1M | price read 12 Nov 2026 |
| CoreWeaveoutput $0.65 per 1M · 1M context | $0.13 | $0.65 | 1M | price read 12 Nov 2026 |
| AtlasCloudoutput $0.54 per 1M · 1M context | $0.135 | $0.54 | 1M | price read 12 Nov 2026 |
| StreamLakeoutput $0.59 per 1M · 1M context | $0.147 | $0.59 | 1M | price read 12 Nov 2026 |
| GMICloudoutput $0.72 per 1M · 1M context | $0.18 | $0.72 | 1M | price read 12 Nov 2026 |
| Cohereoutput $0.66 per 1M · 1M context | $0.195 | $0.66 | 1M | price read 12 Nov 2026 |
| Novitaoutput $0.78 per 1M · 1M context | $0.195 | $0.78 | 1M | price read 12 Nov 2026 |
| Alibabaoutput $0.84 per 1M · 1M context | $0.21 | $0.84 | 1M | price read 12 Nov 2026 |
| Fireworksoutput $0.84 per 1M · 1M context | $0.21 | $0.84 | 1M | price read 12 Nov 2026 |
| Mancer 2output $0.75 per 1M · 1M context | $0.212 | $0.75 | 1M | price read 12 Nov 2026 |
| DigitalOceanoutput $0.90 per 1M · 1M context | $0.225 | $0.90 | 1M | price read 12 Nov 2026 |
| Makoraoutput $1.17 per 1M · 1M context | $0.26 | $1.17 | 1M | price read 12 Nov 2026 |
| Crusoeoutput $1.20 per 1M · 1M context | $0.29 | $1.20 | 1M | price read 12 Nov 2026 |
| Baiduoutput $1.20 per 1M · 1M context | $0.30 | $1.20 | 1M | price read 12 Nov 2026 |
| BaseTenoutput $1.20 per 1M · 1M context | $0.30 | $1.20 | 1M | price read 12 Nov 2026 |
| Googleoutput $1.20 per 1M · 1M context | $0.30 | $1.20 | 1M | price read 12 Nov 2026 |
| Modaloutput $1.20 per 1M · 1M context | $0.30 | $1.20 | 1M | price read 12 Nov 2026 |
| Parasailoutput $1.20 per 1M · 1M context | $0.30 | $1.20 | 1M | price read 12 Nov 2026 |
| SiliconFlowoutput $1.20 per 1M · 1M context | $0.30 | $1.20 | 1M | price read 12 Nov 2026 |
| Togetheroutput $1.20 per 1M · 1M context | $0.30 | $1.20 | 1M | price read 12 Nov 2026 |
| Veniceoutput $1.20 per 1M · 1M context | $0.30 | $1.20 | 1M | price read 12 Nov 2026 |
28 hosts list DeepSeek V4.1 Flash, price read 12 Nov 2026.
GLM 5.3 price tableGLM 5.3 Flash price tableKimi K3 price tableQwen3.8 27B price tableAll price tables
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.” Content reviewed 12 Nov 2026. https://apitokenprices.com