OpenAI·openai/gpt-5-image
GPT-5 Image has a published context limit of 400K tokens in the ModelCap catalogue as of 22 Sept 2026, 02:49 UTC.
GPT-5 Image has 1 published OpenRouter serving endpoint, from OpenRouter as of 22 Sept 2026, 02:49 UTC.
GPT-5 Image weight access is api only, from ModelCap classification of published repository metadata as of 22 Sept 2026, 02:49 UTC.
Snapshot facts · download the public dataset · methodology
Superseded by GPT-5.4 Image 2. It no longer holds a current-board position.
This category board uses only published catalogue and deployment facts. It does not infer media-generation quality or compare incompatible media-unit prices.
This is a discovery ordering, not a capability benchmark. Category-compatible public evaluation evidence must be added before ModelCap can publish a media-quality rank.
Missing: artifactReproducibility.revision-sha, artifactReproducibility.architecture-and-model-type, artifactReproducibility.parameter-count, artifactReproducibility.serialized-weight-format, artifactReproducibility.base-lineage, accessLegalClarity.declared-license, accessLegalClarity.resolvable-license-terms, evaluationProvenance.admitted-evaluation-observations, evaluationProvenance.capability-family-breadth, evaluationProvenance.evaluation-source-diversity, evaluationProvenance.identity-and-source-confidence, evaluationProvenance.evaluation-dataset-revisions.
A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.
Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.
OpenRouter weekly popularity across the full model catalogue.
Independent providers versus the model's open or closed cohort, weighted by uptime.
Hugging Face 30-day downloads for open models; neutral for closed models.
Time since first public availability, on a six-month half-life.
GPT-5 Image has a published context window of 400K tokens (400,000) and a maximum output of 128K tokens. Individual providers can serve less than the published maximum; the providers table lists each endpoint's own limit.
API only. No downloadable model weights are linked in the current source data; access is through a hosted API or product.
GPT-5 Image first appeared in the catalogue on 14 Oct 2025. It has since been superseded by GPT-5.4 Image 2. Rank and price movements since then are recorded on the site's changes feed.