AI API Pricing Calculator

Estimate costs across Google Gemini, OpenAI, xAI Grok & Anthropic Claude. Supports text, images, audio & video.

🔷 18 Gemini Models 🟢 7 OpenAI Models ⚡ 3 Grok Models 🟠 3 Claude Models 📷 Image Tokens 🎵 Audio Tokens 🎬 Video Tokens

⚙️ Configure Your Workload

📝 Text Input
📷 Image Input
🎵 Audio Input
⚠ This provider does not natively support audio input via the standard API.
🎬 Video Input
⚠ This provider does not natively support video input via the standard API.
🔁 Request Volume
💡 Cost Optimizations

📊 Cost Estimate

Per Request
$0.00
Daily Cost
$0.00
Monthly Cost
$0.00
Yearly Cost
$0.00
No optimizations applied

🔢 Token Breakdown

Text Input Tokens0
Text Output Tokens0
Image Tokens0
Audio Tokens0
Video Tokens0
Total Input Tokens0
Total Output Tokens0
Grand Total Tokens0

📏 Context Window Usage

0 / 0 tokens (0%)
⚠️ Your input exceeds 200K tokens — long-context pricing applies (2× standard rates) for this model.

All Models Compared (Sorted by Cost)

Provider Model Total Tokens Per Request Daily Monthly + Caching + Batch

Frequently Asked Questions

How much does 1 million tokens cost on different AI APIs?

Costs vary significantly by provider and model. Budget models like Gemini 2.5 Flash-Lite cost $0.10/1M input tokens, while flagship models like GPT-5.5 Pro cost $5.00/1M input tokens. Use our calculator above to compare exact costs for your specific use case.

How many tokens does an image consume when sent to an AI API?

Token consumption varies by provider. Google Gemini uses 258 tokens per image tile (768×768px). OpenAI charges 85 tokens for low-detail images and 765+ tokens for high-detail. Anthropic Claude estimates roughly (width×height)/750 tokens per image.

How are audio and video tokens calculated for AI APIs?

Google Gemini processes audio at 32 tokens per second and video at 263 tokens per second. Most other providers (OpenAI, Claude, Grok) do not natively support audio/video input through their standard text APIs — they use separate endpoints with per-minute pricing.

Which AI API is the cheapest for high-volume text processing?

For high-volume simple tasks, Gemini 2.5 Flash-Lite ($0.10/1M input) and GPT-4.1 Nano ($0.10/1M input) are the cheapest options. Grok 4.1 Fast at $0.20/1M input is also very competitive with a massive 2M token context window.

How can I reduce my AI API costs by 50-90%?

Use Prompt Caching to save up to 90% on repeated input context, and the Batch API (available on most providers) to save 50% on non-urgent workloads. Combining both strategies can reduce costs by up to 95%.

What is the best AI model for coding and complex reasoning?

For coding, GPT-4.1 and Gemini 3.1 Pro offer the best balance of capability and cost. For maximum reasoning, o3-Pro ($20/$80 per 1M tokens) and Claude Opus 4.7 ($5/$25) are top choices, though significantly more expensive.