GPT Image 2.6 Flare vs GPT Image 2.6 Sunburst

vs

Which one, when

Both have the same published rates for prompt, reference-image and output tokens. Try gpt-image-2.6-flare for interactive edits and gpt-image-2.6-sunburst for detailed compositions. Compare cost per accepted image using your own prompts and complexity settings.

Pricing

GPT Image 2.6 Flare GPT Image 2.6 Sunburst Δ
Input / 1M tokens $5 $5 =
Output / 1M tokens $30 $30 =
Reference image input / 1M tokens $8 $8 =
Cache read / 1M tokens $1.25 $1.25 =
Cached reference image input / 1M tokens $2 $2 =

Rates from the live catalogue at build time; each model page carries the current rate card.

Where they sit · output price per 1M tokens across all 15 image-generation models on this billing unit (log scale)

Specs

GPT Image 2.6 Flare GPT Image 2.6 Sunburst
Input modalities text image text image
Output modalities image image
Released 2026-11-04 2026-11-04
Output sizes
  • 1024x1024
  • 1536x1024
  • 1024x1536
  • auto
  • 1024x1024
  • 1536x1024
  • 1024x1536
  • auto
Input modes text-to-image and reference-image editing text-to-image and reference-image editing
Images per request 4 4
Formats png, jpeg, webp, gif, svg png, jpeg, webp, gif, svg
Notes Custom width and height must be multiples of 16, with an aspect ratio from 1:3 to 3:1. On Synthorai, send a reference image as base64 in the image field of a JSON request to /v1/images/generations. Set complexity to low, medium or high independently of quality. Custom width and height must be multiples of 16, with an aspect ratio from 1:3 to 3:1. On Synthorai, send a reference image as base64 in the image field of a JSON request to /v1/images/generations. Set complexity to low, medium or high independently of quality.

Specs are transcribed from each vendor’s documentation; a row a vendor does not publish is left out rather than inferred. Full sources: GPT Image 2.6 Flare · GPT Image 2.6 Sunburst

One prompt, both models, measured through the gateway

PROMPT A weathered enamel diner mug on a steel counter, the words "OPEN 24H" stencilled on the mug in worn paint, low winter sun raking in from the left, shallow depth of field.

GPT Image 2.6 Flare

GPT Image 2.6 Flare: A weathered enamel diner mug on a steel counter, the words "OPEN 24H" stencilled on the mug in worn paint, low winter sun raking in from the left, shallow depth of field.

Model returned 1402×1122 latency 9 s

GPT Image 2.6 Sunburst

GPT Image 2.6 Sunburst: A weathered enamel diner mug on a steel counter, the words "OPEN 24H" stencilled on the mug in worn paint, low winter sun raking in from the left, shallow depth of field.

Model returned 1536×1024 latency 27 s

One prompt, one request per model, no retries and no cherry-picking. This is the first result each model returned. Neither size nor duration was pinned: each model used its own default, because a request shaped to fit all of them would flatter none. Files here are re-encoded for the web, so judge composition and prompt adherence, not compression.

Switch between them with one line

Both ids are in every tab below; the highlighted pair of lines is the only edit. Same endpoint, same key, same request shape.

from openai import OpenAI

client = OpenAI(
    base_url="https://synthorai.io/v1",
    api_key="sk-syn-...",
)

resp = client.images.generate(
    model="gpt-image-2.6-flare",
    # model="gpt-image-2.6-sunburst",  # uncomment this line, comment the one above
    prompt="a watercolor lighthouse at dawn",
    size="1024x1024",
)
print(resp.data[0].b64_json[:80])

Get your API key →

FAQ

Which is cheaper, GPT Image 2.6 Flare or GPT Image 2.6 Sunburst?

Both list $5 for “Input / 1M tokens”. Other rates and the number of units used can still change the total cost.

Can I A/B test GPT Image 2.6 Flare against GPT Image 2.6 Sunburst without two integrations?

Yes. Both are served through the same OpenAI-compatible endpoint with one API key. Switching is a one-line change to the model id, so you can route a fraction of traffic to each and compare bills directly.

Does the price change with image size?

It depends on how the model bills. Per-image models charge the same regardless of prompt or output size; token-billed models scale with the resolution you render, so a 4K image costs a multiple of a small one. The table above shows which applies to each.

Related comparisons

From our measured studies