GPT Image 2.6 API TWD Pricing: flare/sunburst, Same Price as 2.5

Query date: 2026-11-05 (Taipei time). Pricing follows the USD unit prices shown on the BazaarLink models page, and the estimates use 1 USD = NT$ 31.5. This article only covers specifications verified on the site; sizes are currently limited to 1K and 2K.

BazaarLink listed two variants of OpenAI's new image model GPT Image 2.6 today: gpt-image-2.6-flare and gpt-image-2.6-sunburst. The price is exactly the same as GPT Image 2.5, and so is the interface: in existing OpenAI-compatible code, switch the model name to 2.6 and you are done.

Bottom line up front: It supports text and image input with image output, and a 400K-token context, which suits editing while looking at reference images (changing the background of product photos, extending a style, multi-turn retouching). Unit prices match 2.5: input $8 per M, text output $8 per M, image output $30 per M tokens, and cached read $2 per M. Upgrading does not raise the unit price; generation cost still falls mostly on image output tokens.

Want to call GPT Image 2.6 with billing in NT$ and a tax-ID invoice? BazaarLink provides an OpenAI-compatible route. A 10% top-up service fee applies, which addresses the expense-reporting pain point for Taiwan companies. See the complete guide to AI API expense reporting in Taiwan for details.

Specifications at a glance

How do flare and sunburst differ? They are two variants of the same generation, with the same price and the same interface on BazaarLink. If OpenAI publishes an explicit difference in positioning, we will update this article and the model page. Until then, we suggest generating a few images from the same prompts with each and choosing the one that matches your style.

Price comparison (USD ↔ NT$)

Every line matches GPT Image 2.5. For the latest prices, see BazaarLink Models.

How much does one image cost? How to estimate

The cost of an image model is not a "fixed price per image." It is image output tokens × $30 per M. The token count per image varies with size and content, and the actual figure is the usage field in the API response. Estimation method:

• First run 3 to 5 images at 1K size and note the average output token count from the response usage
• Monthly cost ≈ average tokens × images per month × $30 ÷ 1,000,000, then multiply by 31.5 to convert to NT$

Measured (1024x1024, one image each, very small sample): flare produced 1,758 image output tokens, about $0.053 (NT$ 1.66); sunburst produced 2,578, about $0.077 (NT$ 2.44). At that rate, 200 flare images per day is about $10.6 per day (about NT$ 333), and 6,000 images per month is about $317 (about NT$ 9,990), or about NT$ 10,990 with the 10% top-up service fee. Token counts vary with prompt and content; replace these with your own usage measurements.

If you are doing multi-turn retouching (feeding the previous image back in each round), input also accumulates. Put the reference image and fixed instructions in the prefix so that cached reads ($2 per M) absorb the repeated portion.

How to call it

Method 1: /v1/images/generations (simplest)

curl https://api.bazaarlink.ai/v1/images/generations \
  -H "Authorization: Bearer $BAZAARLINK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2.6-flare",
    "prompt": "Hand-drawn poster-style illustration of a Taiwanese night market stall, warm tones",
    "size": "1024x1024",
    "n": 1
  }'

size accepts 1024x1024 (corresponding to 1K) and the 2K level. Put the aspect ratio in aspect_ratio (for example "16:9"), not in size.

Method 2: /v1/chat/completions with a reference image (image-to-image, multi-turn retouching)

curl https://api.bazaarlink.ai/v1/chat/completions \
  -H "Authorization: Bearer $BAZAARLINK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2.6-sunburst",
    "modalities": ["image"],
    "messages": [{
      "role": "user",
      "content": [
        {"type": "text", "text": "Replace the background of this product photo with a pure white studio backdrop, keep the product details"},
        {"type": "image_url", "image_url": {"url": "data:image/png;base64,..."}}
      ]
    }]
  }'

For Python using the OpenAI SDK, you only need to change base_url to https://api.bazaarlink.ai/v1 and model to either ID above. The rest of the code stays the same.

When to choose it

• Editing while looking at a reference image: changing product backgrounds, extending a style, or producing a finished image from a sketch.
• Multi-turn conversational retouching: the 400K context can keep the full retouching history in the same conversation.
• Upgrading from 2.5: the unit price is the same, so just change the model name, compare old and new outputs on the same prompts, then decide whether to switch fully.
• Budget-sensitive, high-volume image generation: measure usage at 1K first, confirm the cost per image, and then scale up.

Using GPT Image 2.6 in Taiwan: invoices and expense reporting

Top-ups through BazaarLink can be invoiced to a company tax ID as an electronic uniform invoice, with NT$ pricing, so companies do not need to handle overseas receipts for expense reporting. See How to fill in a tax ID for OpenAI? A complete guide to buying OpenAI API invoices in Taiwan for details.

Sources and query log

• BazaarLink model catalog /api/v1/models?output_modalities=image (image models only appear with this parameter; query date 2026-11-05): the two model IDs, input and output modalities, context length, and unit prices, compared with GPT Image 2.5
• BazaarLink API documentation: /v1/images/generations and the modalities parameter, and the size / aspect_ratio rules
• BazaarLink production test (2026-11-05): one 1024x1024 generation request was sent to each variant, both produced images successfully; the charge matches image output tokens × $30 per M in usage

TWD billing · Taiwan invoices · leading AI models · OpenAI-compatible API