What 100 words costs
100 words is about 133 tokens. Priced at list rates across 28 models, that is anything from $0.00001 to $0.00133 for input — the same text, a 100× difference.
Every model at 100 words
| # | Model | Provider | Input | Output | Blended |
|---|---|---|---|---|---|
| 1 | GPT-6 Luna | OpenAI | $0.00001 | $0.00007 | $0.00003 |
| 2 | GPT-5.6 Luna | OpenAI | $0.00003 | $0.00016 | $0.00007 |
| 3 | GPT-5.4 nano | OpenAI | $0.00003 | $0.00017 | $0.00007 |
| 4 | Gemini 3.5 Flash-Lite | Google Gemini | $0.00004 | $0.00033 | $0.00012 |
| 5 | DeepSeek V4.1 Flash | DeepSeek | $0.00004 | $0.00016 | $0.00008 |
| 6 | GPT-5.4 mini | OpenAI | $0.0001 | $0.0006 | $0.00025 |
| 7 | Gemini 3.8 Flash | Google Gemini | $0.0001 | $0.0005 | $0.00022 |
| 8 | Gemini 3.7 Flash | Google Gemini | $0.0001 | $0.0005 | $0.00022 |
| 9 | Claude Haiku 4.5 | Anthropic | $0.00013 | $0.00067 | $0.0003 |
| 10 | Gemini 2.5 Pro | Google Gemini | $0.00017 | $0.00133 | $0.0005 |
| 11 | Grok 4.3 | xAI Grok | $0.00017 | $0.00033 | $0.00025 |
| 12 | DeepSeek V4 Pro | DeepSeek | $0.00018 | $0.00053 | $0.00031 |
| 13 | Gemini 3.5 Flash | Google Gemini | $0.0002 | $0.0012 | $0.0005 |
| 14 | GPT-5.2 | OpenAI | $0.00023 | $0.00186 | $0.0007 |
| 15 | GPT-6.1 Sol | OpenAI | $0.00027 | $0.00133 | $0.0006 |
| 16 | GPT-6 Sol | OpenAI | $0.00027 | $0.00133 | $0.0006 |
| 17 | GPT-5.6 Terra | OpenAI | $0.00027 | $0.0016 | $0.00067 |
| 18 | GPT-4.1 | OpenAI | $0.00027 | $0.00106 | $0.00053 |
| 19 | Claude Sonnet 5 | Anthropic | $0.00027 | $0.00133 | $0.0006 |
| 20 | Gemini 3.1 Pro (Preview) | Google Gemini | $0.00027 | $0.0016 | $0.00067 |
| 21 | Grok 4.6 | xAI Grok | $0.00027 | $0.0008 | $0.00047 |
| 22 | GPT-5.4 | OpenAI | $0.00033 | $0.002 | $0.00083 |
| 23 | Claude Sonnet 4.6 | Anthropic | $0.0004 | $0.002 | $0.0009 |
| 24 | GPT-5.6 Sol | OpenAI | $0.00053 | $0.00266 | $0.0012 |
| 25 | GPT-5.5 | OpenAI | $0.00067 | $0.00399 | $0.00166 |
| 26 | Claude Opus 5 | Anthropic | $0.00067 | $0.00333 | $0.0015 |
| 27 | GPT-6 Astra | OpenAI | $0.00133 | $0.00665 | $0.00299 |
| 28 | Claude Fable 5.1 | Anthropic | $0.00133 | $0.00665 | $0.00299 |
Input = 133 prompt tokens. Output = 133 generated tokens. Blended = input + 25% of output, the same weighting used across this site.
Input vs output
Reading 100 words and writing 100 words are different line items. Output is billed at 5.0× the input rate on GPT-6 Luna and 5.0× on Claude Fable 5.1. A summarisation job pays for 100 words in and a fraction of that out; a generation job pays for the full volume twice.
At scale
| Documents of 100 words | Total tokens | Cheapest input | Priciest input |
|---|---|---|---|
| 100 | 13,300 | $0.00133 | $0.133 |
| 1,000 | 133,000 | $0.0133 | $1.33 |
| 10,000 | 1,330,000 | $0.133 | $13.30 |
| 100,000 | 13,300,000 | $1.33 | $133 |
Prompt caching changes the picture for repeated documents: cache reads bill at $0.006 per 1M on the cheapest cached tier in this dataset, a fraction of the standard input rate.
FAQ
How much does it cost to process 100 words with an LLM?
100 words is about 133 tokens. Input alone costs between $0.00001 on GPT-6 Luna and $0.00133 on Claude Fable 5.1. Generating the same volume as output costs $0.00007 to $0.00665.
What is the cheapest model for 100 words?
GPT-6 Luna at $0.00001 for 133 input tokens. It is 100.0× cheaper than Claude Fable 5.1 for the same volume.
Does that include the prompt overhead?
No. A real request also carries the system prompt and conversation history. A typical system prompt adds 200 to 800 tokens per call, which matters far more than the document size when you make thousands of calls.
Keep going
- Words to tokens converter
- Tokens to dollars
- All models ranked by price
- Recent price changes
- All 28 models ranked by price
- Run your own volumes in the calculator