TokenBudget
Now supporting GPT-5.4, Gemini 3.1, Claude 4.6 & more

Token Counter & Cost Calculator forLLM APIs

Compare token usage and pricing across OpenAI, Anthropic, Google, Mistral, AWS Bedrock, and many more. Estimate project costs before you write a single line of code.

Open Source|Sponsor|50+ models supported

100% Private: All calculations happen in your browser. Your text is never sent to any server or stored anywhere.

Input Prompt

Paste your full prompt including system messages and context to get accurate token counts.

Expected Output500 tokens
tokens per response

Enter the expected average token count for AI responses. Typical responses are 100-2000 tokens.

Usage Projections

Average length of AI response

Input Tokens0
Output Tokens500
Tokens/Request500
Daily Tokens500.00K
Monthly Tokens15.00M
Cheapest Option
Ministral 3B

Mistral | Cost optimized for your usage

Monthly Cost
$0.6000
vs Expensive
100%
Monthly savings vs GPT-5.4 Pro-$2.70K
Cost per request$0.00002000
Daily cost$0.0200

Model Comparison Matrix

Fallback pricing dataUpdated Unknown
Ministral 3B
Mistral128K$0.040$0.040$0.00002000$0.6000
Llama 3.1 8B (Groq)
Groq128K$0.050$0.080$0.00004000$1.20
Ministral 8B
Mistral128K$0.100$0.100$0.00005000$1.50
Nova Micro
AWS Bedrock128K$0.035$0.140$0.00007000$2.10
Titan Text Lite
AWS Bedrock4K$0.150$0.200$0.000100$3.00
Qwen 2.5 32B
Qwen128K$0.150$0.200$0.000100$3.00
Qwen 2.5 Coder 32B
Qwen128K$0.150$0.200$0.000100$3.00
Nova LitePopular
AWS Bedrock300K$0.060$0.240$0.000120$3.60
Mixtral 8x7B (Groq)
Groq32K$0.240$0.240$0.000120$3.60
DeepSeek Coder V2
DeepSeek128K$0.140$0.280$0.000140$4.20
Gemini 3.1 FlashPopular
Google1.0M$0.075$0.300$0.000150$4.50
Gemini 3 FlashPopular
Google1.0M$0.075$0.300$0.000150$4.50
Gemini 2.5 Flash
Google1.0M$0.075$0.300$0.000150$4.50
Llama 4 ScoutPopular
Meta1.0M$0.100$0.300$0.000150$4.50
GPT-5 Nano
OpenAI128K$0.050$0.400$0.000200$6.00
GPT-4.1 Nano
OpenAI1.0M$0.100$0.400$0.000200$6.00
Gemini 2.0 FlashPopular
Google1.0M$0.100$0.400$0.000200$6.00
Qwen 2.5 72BFlagship
Qwen128K$0.350$0.400$0.000200$6.00
Jamba 1.5 Mini
AI21256K$0.200$0.400$0.000200$6.00
GPT-4o MiniPopular
OpenAI128K$0.150$0.600$0.000300$9.00
Mistral SmallPopular
Mistral32K$0.200$0.600$0.000300$9.00
Titan Text ExpressPopular
AWS Bedrock8K$0.200$0.600$0.000300$9.00
QwQ 32B
Qwen32K$0.150$0.600$0.000300$9.00
Llama 4 MaverickFlagship
Meta1.0M$0.200$0.600$0.000300$9.00
Llama 3.3 70B
Meta128K$0.590$0.790$0.000395$11.85
Llama 3.3 70B (Groq)Popular
Groq128K$0.590$0.790$0.000395$11.85
Titan Multimodal
AWS Bedrock8K$0.800$0.800$0.000400$12.00
Codestral
Mistral32K$0.300$0.900$0.000450$13.50
DeepSeek V3Popular
DeepSeek64K$0.270$1.10$0.000550$16.50
Titan Text PremierFlagship
AWS Bedrock32K$0.500$1.50$0.000750$22.50
Command RPopular
Cohere128K$0.500$1.50$0.000750$22.50
GPT-4.1 MiniPopular
OpenAI1.0M$0.400$1.60$0.000800$24.00
GPT-5 MiniPopular
OpenAI128K$0.250$2.00$0.001000$30.00
DeepSeek R1Flagship
DeepSeek64K$0.550$2.19$0.001095$32.85
Nova 2 Lite
AWS Bedrock1.0M$0.300$2.50$0.001250$37.50
Nova ProFlagship
AWS Bedrock300K$0.800$3.20$0.001600$48.00
Claude 3.5 HaikuPopular
Anthropic200K$0.800$4.00$0.002000$60.00
Qwen VL Max
Qwen32K$2.00$4.00$0.002000$60.00
o4-miniPopular
OpenAI200K$1.10$4.40$0.002200$66.00
o3-mini
OpenAI200K$1.10$4.40$0.002200$66.00
o1-mini
OpenAI128K$1.10$4.40$0.002200$66.00
Gemini 3.1 ProFlagship
Google2.0M$1.25$5.00$0.002500$75.00
Gemini 3 ProFlagship
Google2.0M$1.25$5.00$0.002500$75.00
Gemini 2.5 Pro
+1
Google2.0M$1.25$5.00$0.002500$75.00
Codex Mini
OpenAI200K$1.50$6.00$0.003000$90.00
Mistral LargeFlagship
Mistral128K$2.00$6.00$0.003000$90.00
Pixtral Large
Mistral128K$2.00$6.00$0.003000$90.00
Grok 2 Mini
xAI128K$2.00$6.00$0.003000$90.00
GPT-4.1
OpenAI1.0M$2.00$8.00$0.004000$120.00
Jamba 1.5 LargeFlagship
AI21256K$2.00$8.00$0.004000$120.00
GPT-5.1
OpenAI200K$1.25$10.00$0.005000$150.00
GPT-5Flagship
OpenAI200K$1.25$10.00$0.005000$150.00
GPT-4o
OpenAI128K$2.50$10.00$0.005000$150.00
Command R+Flagship
Cohere128K$2.50$10.00$0.005000$150.00
GPT-5.2Flagship
OpenAI200K$1.75$14.00$0.007000$210.00
GPT-5.4Flagship
OpenAI272K$2.50$15.00$0.007500$225.00
Claude 4.6 SonnetPopular
+1
Anthropic200K$3.00$15.00$0.007500$225.00
Claude 4 Sonnet
+1
Anthropic200K$3.00$15.00$0.007500$225.00
Claude 3.7 Sonnet
+2
Anthropic200K$3.00$15.00$0.007500$225.00
Claude 3.5 SonnetPopular
+1
Anthropic200K$3.00$15.00$0.007500$225.00
Grok 2Flagship
xAI128K$5.00$15.00$0.007500$225.00
Nova 2 ProFlagship
AWS Bedrock1.0M$2.19$17.50$0.008750$262.50
o3Flagship
OpenAI200K$10.00$40.00$0.0200$600.00
o1
OpenAI200K$15.00$60.00$0.0300$900.00
Claude 4.6 OpusFlagship
Anthropic200K$15.00$75.00$0.0375$1.13K
Claude 4 OpusFlagship
Anthropic200K$15.00$75.00$0.0375$1.13K
Claude 3 Opus
Anthropic200K$15.00$75.00$0.0375$1.13K
o3 ProFlagship
OpenAI200K$20.00$80.00$0.0400$1.20K
GPT-5.4 ProFlagship
OpenAI272K$30.00$180.00$0.0900$2.70K
Showing 69 of 69 models

How Token Pricing Works

Understanding token-based billing helps you make smarter decisions about which models to use for your applications.

01

Token Counting

LLM providers charge based on the number of tokens processed. Tokens are pieces of text - roughly 4 characters or 0.75 words on average.

02

Input vs Output Tokens

Input tokens are what you send to the model (prompts, context). Output tokens are the generated response. Each has different pricing.

03

Tiered Pricing

Different models have vastly different costs. Flagship models like GPT-4o cost more than efficient alternatives like GPT-4o-mini.

04

Cost Optimization

By comparing costs across providers, you can save 10-90% on your LLM spending without sacrificing quality for your use case.

The Calculation Formula

Total Cost = (Input Tokens * Rate_In) + (Output Tokens * Rate_Out)

Rates are typically expressed per 1 million tokens (1M). Our calculator automatically applies the correct rates for each provider and multiplies by your expected usage volume.

Pro Tip

You can paste both your input prompt AND an example output response to get accurate token counts for both. This gives you the most precise cost estimate for your specific use case.