Enter opens the highlighted result. Esc closes.

GPT-5 Image Mini vs Extract

Updated October 21, 2026. No benchmark has tested both models yet. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

GPT-5 Image MiniOpenAI
Coding
No data
Overall
No data
Output $/M
$2.00
S ExtractScaledown
Coding
No data
Overall
No data
Output $/M
No data
vs 400K vs 1M context window. Extract fits 2.5x more.

Decision reading

Neither model has a coding score yet, so the two cannot be ranked on coding.

Compare them on price, context and the boards below.

No benchmark has tested both yet. GPT-5 Image Mini has results on Design Arena: images, Design Arena: graphic design and Design Arena: logos; Extract has none yet. Compare them on price and context instead.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
GPT-5 Image Mini not benchmarked, Extract not benchmarked.
Widest category
None yet: no category has been tested on both models.
Widest single gap
None yet: no benchmark has tested both models.
Output price
GPT-5 Image Mini $2.00 against Extract Free per million output tokens.
Context window
GPT-5 Image Mini takes 400K tokens, Extract 1M.

Benchmark by benchmark

Every board either model has a result on, a category to a fold; bars are each result on a 0 to 100 scale. Only one model is measured on each, so no row names a leader.

Image generationDirectional onlyPublic boards, shown as published, kept out of the index3 boards measured
Image generation benchmarks for GPT-5 Image Mini and Extract
BenchmarkGPT-5 Image MiniExtractLeader
Design Arena: images1184Not measuredOnly GPT-5 Image Mini measured
Design Arena: graphic design1165Not measuredOnly GPT-5 Image Mini measured
Design Arena: logos1209Not measuredOnly GPT-5 Image Mini measured
Neither model has a result on the other 2 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

GPT-5 Image Mini$0.0035Fits in one request
Extract$0.0000Fits in one request

Extract costs less

Repository review

50K input + 3K output tokens

GPT-5 Image Mini$0.131Fits in one request
Extract$0.0020Fits in one request

Extract costs less

Agent loop

200K input + 10K output tokens

GPT-5 Image Mini$0.520Fits in one request
Extract$0.0080Fits in one request

Extract costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of GPT-5 Image Mini and Extract
SpecificationOpenAI GPT-5 Image MiniScaleDown Extract
MakerOpenAIScaledown
WeightsNo public weights listedNo public weights listed
ReleasedOctober 16, 2025October 13, 2026
Context window400K1M
Input $/Mtok$2.50$0.04
Output $/Mtok$2.00Free
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5 Image Mini better than Extract for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Compare them on price, context and the boards below.

Which is cheaper, GPT-5 Image Mini or Extract?

GPT-5 Image Mini costs $2.50 per million input tokens and $2.00 per million output tokens; Extract costs $0.04 and Free. Cost per solved task is known for neither of them.

Which has the bigger context window, GPT-5 Image Mini or Extract?

Extract, with 1M tokens against 400K.

Has any benchmark tested both GPT-5 Image Mini and Extract?

No benchmark has tested both yet. GPT-5 Image Mini has results on Design Arena: images, Design Arena: graphic design and Design Arena: logos; Extract has none yet. Compare them on price and context instead. Data as of October 21, 2026.

Compare next