OpenAI GPT-5.4 Mini
gpt-5.4-mini, detail: high. 32px patches: 16 × 16 = 256; 1.2× model multiplier, rounded up = 308 input tokens.
308 × $0.75 / 1M = $0.000231
Image understanding · API billing
A model's USD-per-million-input-tokens rate does not reveal the price of an image by itself. Each provider converts pixels or a media-resolution choice into tokens differently.
Illustrative standard-rate estimates
These are image-input-only examples, not comparable image-quality benchmarks or complete request prices. The models have different processing rules and capabilities.
gpt-5.4-mini, detail: high. 32px patches: 16 × 16 = 256; 1.2× model multiplier, rounded up = 308 input tokens.
308 × $0.75 / 1M = $0.000231
claude-sonnet-4-6. 28px visual patches: ceil(512/28) = 19 on each axis; 19 × 19 = 361 image tokens, within native limits.
361 × $3 / 1M = $0.001083
gemini-3.5-flash, MEDIA_RESOLUTION_MEDIUM. Standard Gemini 3 image accounting is 560 tokens per image at medium resolution.
560 × $1.50 / 1M = $0.000840
Input rates above are standard non-cached list rates for the named routes, checked Nov 9, 2026. They exclude text prompts, output tokens, system instructions, cache differences, regional premiums, retries, and additional processing. Values are estimates, not invoice guarantees.
Correct comparison method
media_resolution. Low / medium / high / ultra-high correspond to different token budgets; previous Gemini generations behave differently.Image understanding is not image generation and is not equivalent to page-priced OCR. The site's token calculator only estimates correctly after you supply an appropriate total input token count; it does not compute model-specific image tokens automatically.