🎁 New Sign up free, 10 calls on us. Up to $1, no card needed.

GPT Image 1 Mini vs GPT Image 2

vs

Which one, when — curated verdict, not a benchmark table

gpt-image-1-mini is the budget rung at $2 per million input and $8 per million output against $5 and $30 — roughly 2.5x and 3.75x cheaper — on a fixed 1024x1024 / 1536x1024 / 1024x1536 / auto size set. gpt-image-2 buys resolution: arbitrary sizes with edges up to 3840x2160 in multiples of 16. Mask inpainting, png/jpeg/webp output and up to 10 images per request are the same on both, so pick the mini for high-volume 1K work and gpt-image-2 when a frame has to be larger than 1536px.

Pricing

GPT Image 1 Mini GPT Image 2 Δ
Input / 1M tokens $2 $5 0.4×
Output / 1M tokens $8 $30 0.27×

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

Where they sit — output price per 1M tokens across all 8 image-generation models on this billing unit (log scale)

Specs

GPT Image 1 Mini GPT Image 2
Input modalities text image text image
Output modalities image image
Released 2025-10-06 2026-04-21
Output sizes
  • 1024x1024
  • 1536x1024
  • 1024x1536
  • auto
  • 1024x1024
  • 1536x1024
  • 1024x1536
  • 2048x2048
  • 2048x1152
  • 3840x2160
  • 2160x3840
  • auto
  • arbitrary WxH (both divisible by 16, aspect ratio 1:3–3:1)
Input modes text-to-image, image edit with mask inpainting text-to-image, image edit with mask inpainting
Images per request 10 10
Formats png, jpeg, webp png, jpeg, webp
Notes

Cost-efficient version of GPT Image 1

1024x1024 / 1024x1536 / 1536x1024

editing via v1/images/edits

vendor lists indicative per-image costs by quality tier (token-billed on Synthorai; see the live prices above)

Flexible resolutions: edges up to 3840px in multiples of 16, ratio <=3:1, ~0.65-8.3MP total (incl. 4K 3840x2160)

editing with mask inpainting

all image inputs processed at high fidelity

significantly improved text rendering (precise placement can still struggle)

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 1 Mini · GPT Image 2

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 1 Mini

GPT Image 1 Mini: 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 19 s

GPT Image 2

GPT Image 2: 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 18 s

One prompt, one request per model, no retries and no cherry-picking — 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-1-mini",
    # model="gpt-image-2",  # uncomment this line, comment the one above
    prompt="a watercolor lighthouse at dawn",
    size="1024x1024",
)
print(resp.data[0].b64_json[:80])

Get an API key →

FAQ

Which is cheaper, GPT Image 1 Mini or GPT Image 2?

GPT Image 1 Mini is cheaper on input / 1m tokens ($2 vs $5, 2.5× apart). Other rows may point the other way — the table above carries the full card, and real cost depends on your mix.

Can I A/B test GPT Image 1 Mini against GPT Image 2 without two integrations?

Yes. Both are served through the same OpenAI-compatible endpoint with one API key — switching is a one-line model-string change, 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