Usage Parameters
Input: $0.1/1M · Output: $0.4/1M
GPT-4o Mini
OpenAIInput: $0.15/1M · Output: $0.6/1M
Gemini 2.5 Flash
GoogleInput: $0.15/1M · Output: $0.6/1M
GPT-4.1 Mini
OpenAIInput: $0.4/1M · Output: $1.6/1M
Claude 3.5 Haiku
AnthropicInput: $0.8/1M · Output: $4/1M
o4 Mini
OpenAIInput: $1.1/1M · Output: $4.4/1M
Gemini 2.5 Pro
GoogleInput: $1.25/1M · Output: $10/1M
GPT-4.1
OpenAIInput: $2/1M · Output: $8/1M
GPT-4o
OpenAIInput: $2.5/1M · Output: $10/1M
Claude 4 Sonnet
AnthropicInput: $3/1M · Output: $15/1M
Official Sources
OpenAI
GPT-4.1, GPT-4o, o-series reasoning models. Tiered pricing with cached input discounts.
Anthropic
Claude 4 Sonnet, Claude 3.7 Sonnet, Claude 3.5 Haiku. Strong coding & analysis.
Google AI
Gemini 2.5 Pro/Flash family. 1M token context windows, competitive pricing.
Updated daily. Verified today. Not affiliated with listed providers.
What is an AI API Pricing Calculator? An AI API pricing calculator compares the cost of using large language model APIs (such as GPT-4o, Claude 4 Sonnet, and Gemini 2.5 Pro) by estimating monthly spend based on your input/output token volume and daily request count. Prices are sourced directly from each provider's official documentation and updated daily.
Frequently Asked Questions
How much does GPT-4o cost per token?▼
GPT-4o costs $2.50 per 1 million input tokens and $10.00 per 1 million output tokens as of April 2026. For 100 requests/day at 10K input + 2K output tokens, that equates to roughly $105/month.
Which AI model is cheapest for API use?▼
Gemini 2.0 Flash is currently the cheapest major AI model at $0.10/1M input and $0.40/1M output tokens, followed by GPT-4o Mini and Gemini 2.5 Flash at $0.15/$0.60.
How do I calculate AI API costs?▼
Multiply your input tokens per request by the model's input price per million, add the output tokens multiplied by the output price per million, then multiply by your daily request volume and 30 for monthly cost.
Is Claude 4 Sonnet more expensive than GPT-4.1?▼
Yes. Claude 4 Sonnet costs $3.00/1M input and $15.00/1M output vs GPT-4.1 at $2.00/$8.00. For the same workload, Claude 4 Sonnet typically costs 50-80% more than GPT-4.1.
What are AI tokens and how are they counted?▼
AI tokens are chunks of text (roughly 4 characters or 0.75 words in English). Both input (your prompt) and output (the response) tokens are counted separately and billed at different rates by each provider.
Stop Wasting API Tokens
Unstructured prompts waste millions of tokens through inefficient wording and hallucinations. Validate your prompts through the STCO Architect to decrease costs by up to 40%.