Text Model Cost Calculator
Total Cost:
$0.00
Select a Model and Enter Tokens
Embedding Models Cost Calculator
Total Cost:
$0.00
Select a Model and Enter Tokens
Fine-tuning Models Cost Calculator
Total Cost:
$0.00
Select a Model and Enter Tokens
Audio & Speech Models Cost Calculator
Total Cost:
$0.00
Select a Model and Enter Input
Image Generation Cost Calculator
Total Cost:
$0.00
Select Model Options
Frequently Asked Questions
1. What are the latest models available in 2025?
The latest models include GPT-4.1 ($2.00/1M input, $8.00/1M output), GPT-4.1 Mini ($0.40/1M input, $1.60/1M output), and GPT-4.1 Nano ($0.10/1M input, $0.40/1M output). There's also o3 ($10.00/1M input, $40.00/1M output) and o4-mini ($1.10/1M input, $4.40/1M output).
2. What's cached input pricing?
Cached input pricing (also known as batch/flex API pricing) offers discounted rates for non-urgent processing. For example, GPT-4.1 costs $2.00/1M tokens for standard input but only $0.50/1M tokens for cached input, representing a 75% discount.
3. How do the embedding model options compare?
There are three main embedding models: text-embedding-3-small ($0.02/1M tokens), text-embedding-3-large ($0.13/1M tokens), and text-embedding-ada-002 ($0.10/1M tokens). The -3 models are newer with improved performance.
4. What are the costs for fine-tuning the latest models?
Fine-tuning GPT-4.1 costs $25.00/1M tokens for training, $3.00/1M for input, and $12.00/1M for output. GPT-4.1 Mini is more economical at $5.00/1M for training, $0.80/1M for input, and $3.20/1M for output.
5. What audio and speech models are available?
Audio models include GPT-4o Transcribe ($0.006/minute), GPT-4o Mini Transcribe ($0.003/minute), and Whisper ($0.006/minute). Text-to-speech options include GPT-4o Mini TTS ($0.015/minute), TTS ($15/million characters), and TTS HD ($30/million characters).
6. How do the o-series models compare to GPT models?
The o-series includes models like o1 ($15/1M input, $60/1M output), o1-pro ($150/1M input, $600/1M output), o3 ($10/1M input, $40/1M output), and o4-mini ($1.10/1M input, $4.40/1M output). These are typically more advanced than corresponding GPT models but at premium pricing.
7. What are the costs for image generation?
DALL·E 3 pricing varies by quality and size: Standard quality costs $0.04 per 1024x1024 image or $0.08 per 1024x1792 image, while HD quality costs $0.08 per 1024x1024 image or $0.12 per 1024x1792 image. DALL·E 2 is more economical at $0.016-$0.02 per image.
8. What's the difference between audio tokens and text tokens?
Audio tokens (used for processing audio input/output) are generally more expensive than text tokens. For example, GPT-4o Audio Preview charges $40/1M tokens for audio input compared to $2.50/1M for text input, reflecting the higher computational demands of audio processing.