Qwen

Image 3.0

The balanced standard tier of Qwen-Image 3.0 for image generation and editing: it supports text-to-image and edits from 1–3 reference images, prompts of up to about 4.5K tokens, up to six outputs, and 2K-class resolution. It fits everyday posters, interfaces, infographics, and repeated creative work; move to Pro when complex layouts and fine text fidelity matter more, and use this tier when speed and cost efficiency are the priority.

Use in Consoleqwen-image-3.0

USD /s

Pricing

GroupTierPrice
defaultimage_input$0.003
defaultsize=1K$0.21
defaultsize=2K$0.21
qwen-0.8image_input$0.0024
qwen-0.8size=1K$0.168
qwen-0.8size=2K$0.168
default
image_input$0.003
size=1K$0.21
size=2K$0.21
qwen-0.8
image_input$0.0024
size=1K$0.168
size=2K$0.168

Public list prices are shown in USD. Final charges may vary by account group and usage tier.

API

Code examples

curl --location --request POST 'https://api.tokenhot.ai/v1/images/generations' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "qwen-image-3.0",
    "input": {
        "messages": [
            {
                "role": "user",
                "content": [
                    {
                        "text": "Draw a cute cat."
                    }
                ]
            }
        ]
    },
    "parameters": {
        "size": "2K",
        "negative_prompt": "",
        "prompt_extend": true,
        "watermark": false
    }
}'

Qwen

Related models

QwenQwenImage 3.0 PRO

A quality-first image generation and editing model: it supports text-to-image and edits from 1–3 reference images, accepts prompts of up to about 4.5K tokens, and is aimed at dense layouts, fine 10px-scale text, 12 languages, and multiple fonts. Choose it over the standard variant when complex composition and detail fidelity matter more than speed or cost; use the standard variant for a faster, more economical workflow.

$0.0024/sGeminiGoogleGemini 3 PRO Image

A reasoning-driven image generation and editing model for professional creative work, including complex graphic design, high-fidelity product mockups, infographics, and visuals that require accurate text rendering. Compared with the faster Flash Image tier, it prioritizes fine control, grounded content, and polished output.

$0.0318/imageGeminiGoogleGemini 2.5 Flash Image

Built for image generation and editing, with stronger multimodal understanding, conversational edits, and rapid visual prototyping than earlier Gemini image capabilities. Compared with GPT Image, Qwen Image, and Seedream, it is useful for combining documents, images, and prompts in one visual workflow.

$0.0585/imageOpenAIOpenAIGPT Image 2 5 Flare Image TO Image

The Flare image-to-image editing route: use a text instruction with a reference image to make focused changes to the subject, background, or style while retaining important source details. It is a strong fit for fast iteration; choose Sunburst when maximum editing precision matters more than speed.

$0.034/s

FAQ

Frequently asked questions

What is Image 3.0 best suited for?

Image 3.0 is suited to the input, output, and capability types listed on this page. Test production workloads before choosing it for a critical system.

How is Image 3.0 priced?

Pricing is shown in the pricing section above. Actual cost depends on usage volume, account group, and the request payload.

How can I call Image 3.0?

Use the model ID shown above with one of the supported API protocols. Code examples are provided when usage data is available.

Get started

Build with Image 3.0

Use in Console
WhatsApp