Token Counter with Price Preview
Count your prompt and compare the cost of one request across AI models. Your text stays in your browser.
Count your text
Counts and prices update as you type.
Token counts
Live results- OpenAI encoding
- 0
- Other models
- ~0
- Words
- 0
- Characters
- 0
Counts vary by model. Use the provider's response for billing-grade usage.
Price per request
02 / Compare modelsCompare your input and expected reply across providers. Rates were checked Nov 5, 2026.
Enter the expected length of one reply.
Prices by provider
Rates in USD per 1 million tokens
OpenAI4 models
GPT-6 Luna
0 input tokens · o200k_base.
Per request
$0.00025
- Input
- $0.10
- Cached
- $0.01
- Output
- $0.50
Over 272,000 input tokens: $0.20 in, $0.75 out.
GPT-6.1 Terra
0 input tokens · o200k_base.
Per request
$0.00250
- Input
- $1.00
- Cached
- $0.05
- Output
- $5.00
Over 272,000 input tokens: $2.00 in, $7.50 out.
GPT-6 Sol
0 input tokens · o200k_base.
Per request
$0.00500
- Input
- $2.00
- Cached
- $0.20
- Output
- $10.00
Over 272,000 input tokens: $4.00 in, $15.00 out.
GPT-6.1 Sol
0 input tokens · o200k_base.
Per request
$0.00500
- Input
- $2.00
- Cached
- $0.10
- Output
- $10.00
Over 272,000 input tokens: $4.00 in, $15.00 out.
USD per 1 million tokens. OpenAI pricing page
Anthropic4 models
Claude Haiku 5.5
0 input tokens · rough estimate.
Per request
$0.00025
- Input
- $0.10
- Cached
- $0.01
- Output
- $0.50
Over 100,000 input tokens: $0.50 in, $2.50 out.
Claude Sonnet 5.5
0 input tokens · rough estimate.
Per request
$0.00500
- Input
- $2.00
- Cached
- $0.10
- Output
- $10.00
Claude Opus 5.5
0 input tokens · rough estimate.
Per request
$0.0100
- Input
- $4.00
- Cached
- $0.20
- Output
- $20.00
Claude Fable 5.1
0 input tokens · rough estimate.
Per request
$0.0250
- Input
- $10.00
- Cached
- $0.25
- Output
- $50.00
USD per 1 million tokens. Anthropic pricing page
Google4 models
Gemini 3.5 Flash Lite
0 input tokens · rough estimate.
Per request
$0.00125
- Input
- $0.30
- Cached
- $0.03
- Output
- $2.50
Gemini 3.6 Flash
0 input tokens · rough estimate.
Per request
$0.00187
- Input
- $0.75
- Cached
- $0.075
- Output
- $3.75
From Jan 1, 2027: $1.50 in, $7.50 out.
Gemini 3.8 Flash
0 input tokens · rough estimate.
Per request
$0.00187
- Input
- $0.75
- Cached
- $0.075
- Output
- $3.75
From Jan 1, 2027: $1.50 in, $7.50 out.
Gemini 4 Argon
0 input tokens · rough estimate.
Per request
$0.00500
- Input
- $2.00
- Cached
- $0.10
- Output
- $10.00
From Dec 1, 2026: $4.00 in, $20.00 out.
USD per 1 million tokens. Google pricing page
xAI4 models
Grok 4.3
0 input tokens · rough estimate.
Per request
$0.00125
- Input
- $1.25
- Cached
- $0.20
- Output
- $2.50
Over 200,000 input tokens: $2.50 in, $5.00 out.
Grok 4.5
0 input tokens · rough estimate.
Per request
$0.00300
- Input
- $2.00
- Cached
- $0.30
- Output
- $6.00
Over 200,000 input tokens: $4.00 in, $12.00 out.
Grok 4.6
0 input tokens · rough estimate.
Per request
$0.00300
- Input
- $2.00
- Cached
- $0.50
- Output
- $6.00
Over 200,000 input tokens: $4.00 in, $12.00 out.
Grok 4.7
0 input tokens · rough estimate.
Per request
$0.00300
- Input
- $2.00
- Cached
- $0.50
- Output
- $6.00
Over 200,000 input tokens: $4.00 in, $12.00 out.
USD per 1 million tokens. xAI pricing page
Mistral4 models
Mistral Small 4
0 input tokens · rough estimate.
Per request
$0.00030
- Input
- $0.15
- Cached
- $0.015
- Output
- $0.60
Ministral 3 14B
0 input tokens · rough estimate.
Per request
$0.00010
- Input
- $0.20
- Cached
- $0.02
- Output
- $0.20
Mistral Large 4
0 input tokens · rough estimate.
Per request
$0.00105
- Input
- $0.70
- Cached
- $0.07
- Output
- $2.10
Mistral Medium 3.5
0 input tokens · rough estimate.
Per request
$0.00375
- Input
- $1.50
- Cached
- $0.15
- Output
- $7.50
USD per 1 million tokens. Mistral pricing page
DeepSeek2 models
DeepSeek V4.1 Flash 1017
0 input tokens · rough estimate. Off-peak request: $0.00030.
Per request
$0.00060
- Input
- $0.30
- Cached
- $0.006
- Output
- $1.20
Peak rate. Off-peak: $0.15 in, $0.003 cached, $0.60 out.
DeepSeek V4 Pro
0 input tokens · rough estimate. Off-peak request: $0.00099.
Per request
$0.00198
- Input
- $1.32
- Cached
- $0.044
- Output
- $3.96
Peak rate. Off-peak: $0.66 in, $0.022 cached, $1.98 out.
USD per 1 million tokens. Peak hours: Mon-Fri 01:00-04:00 and 06:00-10:00 UTC, excluding Chinese public holidays. DeepSeek pricing page
Prices are from models.dev as of Nov 5, 2026, checked against provider pricing pages. For a detailed usage estimate, use the LLM API cost calculator.
How the count works
A token is a piece of a word. For OpenAI models this counter runs OpenAI's o200k_base encoding in your browser. The count is exact for that encoding, but OpenAI does not say which encoding each current model uses, so treat it as a close estimate for OpenAI prices.
Anthropic, Google, xAI, Mistral and DeepSeek do not publish a tokenizer that runs in the browser. For those models the page uses a rule of thumb: about four characters per token for English, and one token for each character outside plain ASCII. That rule can be well off for code and for other languages. For a billing-grade number, use the token count your provider returns with each response.
How the price preview works
The preview prices your text as the input of one request, plus the output tokens you enter, at each model's standard rate. It lists the newest priced models from each provider, grouped by provider, with prices from the open models.dev database. To price a request on one chosen model, use the LLM API cost calculator, or read the cheapest AI API pricing compared.