AI & LLM Multi-Model Pricing Calculator

Compare token pricing, prompt caching savings, and monthly cost across GPT-4o, Claude 3.5 Sonnet, Gemini 2.0, and DeepSeek

Workload Presets

Load typical traffic profiles for common AI use cases

Workload & Token Volume Parameters

Define per-request token usage and daily API volume

Input Tokens (Prompt):

Tokens per request prompt

Output Tokens (Completion):

Tokens per response

Requests per Day:

Volume across users

Prompt Caching Hit Ratio: 50%Anthropic/OpenAI/Gemini cache discount

Multi-Model Pricing & Cost Matrix

Ranked comparison across 9 foundation models

DeepSeek V3

DeepSeek

Context: 64k•Ultra cost-effective general intelligence model

Per 1k calls

$0.190

Monthly

$142.80

-97%

Gemini 2.0 Flash

Google

Context: 1,000k•Ultra-fast multimodal model with 1M context

Per 1k calls

$0.215

Monthly

$161.25

-97%

GPT-4o mini

OpenAI

Context: 128k•Affordable lightweight flagship from OpenAI

Per 1k calls

$0.345

Monthly

$258.75

-95%

DeepSeek R1

DeepSeek

Context: 64k•Open-weight reasoning and chain-of-thought model

Per 1k calls

$1.180

Monthly

$885.38

-84%

Claude 3.5 Haiku

Anthropic

Context: 200k•Rapid coding and lightweight reasoning model

Per 1k calls

$1.928

Monthly

$1,446.00

-73%

o3-mini

OpenAI

Context: 200k•Fast specialized reasoning & math model

Per 1k calls

$2.530

Monthly

$1,897.50

-65%

Gemini 1.5 Pro

Google

Context: 2,000k•Massive 2M token context window model

Per 1k calls

$2.688

Monthly

$2,015.63

-63%

GPT-4o (Omni)

OpenAI

Context: 128k•High intelligence multimodal flagship

Per 1k calls

$5.750

Monthly

$4,312.50

-20%

Claude 3.5 Sonnet

Anthropic

Context: 200k•Industry standard for complex code and architecture

Per 1k calls

$7.230

Monthly

$5,422.50

Baseline