Compare model

google / Image

GoogleGemini 3 Pro Image 4K

google/gemini-3-pro-image-4k

Gemini 3 Pro Image at 4K resolution (4096 px for 1:1)

Best for: High-resolution 4K images for print and large displays

ShareLinkedInX

Catalog status

Enabled

Research checked

2026-10-06

Benchmark results

No recorded results

Results are source-attributed, not TokenRex measurements. Different tests and thinking variants are not interchangeable.

Published benchmark coverage

Reviewed sources do not include results for this exact version. Provider specifications and API capabilities remain listed separately.

Model specifications

Input token limit

65.54K

Published provider limit

Maximum output

32.77K

Published provider limit

Input and output modalities

Provider-reported formats; API compatibility is detailed below.

Input

Text
Image

Output

Text
Image
Exact model ID
google/gemini-3-pro-image-4k
Model type
Image
Input token limit
65,536 tokens
Maximum output
32,768 tokens

Input token limits describe provider input capacity. Published provider limits are not independently tested TokenRex request limits.

Versions and image configurations

Choose from 3 enabled versions. The exact ID determines the version and its price; benchmark scores do not carry over between variants.

Gemini 3 Pro Image$0.134 per image
Gemini 3 Pro Image 2K$0.134 per image
Gemini 3 Pro Image 4KSelected$0.24 per image

Image quality, resolution, pricing and editing

Every price below is the official provider price converted at ₹96 per US dollar, and you pay exactly that price. OpenAI image models are billed by the tokens the request actually uses, so Low quality costs far less than Max. Gemini image models are billed per image, and each resolution has its own model ID.

ModelQualitySize / resolutionAspect ratioFormatsTransparentEditingPrice
google/gemini-3-pro-image
Fixed1K (default) · 2K · 4K versions10 ratios (image_config.aspect_ratio)PNGNoYes (multiple references)
₹8.04 at 1K/2K · ₹14.4 at 4K per image
Use google/gemini-3-pro-image-2k or -4k for higher resolution.

How to use each control

  • Resolution (Gemini): pick the model ID — google/gemini-3.1-flash-image (1K), -2k or -4k; same for google/gemini-3-pro-image. Tested: 1K returned 1024×1024, 2K returned 2048×2048, 4K returned 4096×4096. Lite and 2.5 Flash are 1K only.
  • Aspect ratio (Gemini 3 Pro / 3.1 Flash): send "image_config": {"aspect_ratio": "16:9"}. Tested: 3.1 Flash 4K at 16:9 returned 5504×3072. Gemini does not accept OpenAI quality, size, format or background fields.
  • Editing: POST /v1/images/edits with one image or several image[] files, in order. OpenAI models also accept a PNG mask. Gemini makes one image per request (n=1).
  • Charges: you only pay for images actually returned. A failed request is refunded. The exact charge is in the x-tokenbaazar-cost-paise response header.

OpenAI pricing · Gemini pricing · OpenAI image controls · Gemini image controls

tokenrex — openai quality
curl https://tokenrex.ai/api/public/v1/images/generations \
  -H "Authorization: Bearer $TOKENBAZAAR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"openai/gpt-image-2.5-sunburst","prompt":"A blue ceramic cup, isolated","quality":"low","size":"1024x1024","background":"transparent","output_format":"png"}'

Features and tool support

TokenRex’s exposed interface, not every feature advertised by the provider. “Available” describes the implemented interface, not a successful test of every input or tool.

Input through TokenRex

Available

Text prompt on POST /v1/images/generations; reference images on edit-capable models. Settings are checked and unsupported ones are rejected.

Output through TokenRex

Available

Generated image (base64) in the chosen size, quality and format supported by this model.

Function tools

Not exposed

Image endpoint only — it creates images and does not run tools.

Sources and verification

Provider specifications describe the upstream model, not a guarantee of every feature through TokenRex. Prices come from the enabled catalog; benchmark results belong to the exact tested model.