openai
OpenAI: GPT-5 (batch)
openai/gpt-5:batch
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
According to OpenRouter's catalog, openai/gpt-5:batch is the batch variant of OpenAI's GPT-5, mapped to the canonical snapshot openai/gpt-5-2025-08-07. The catalog lists text, image, and file inputs with text-only output, a context window of 400,000 tokens, and a knowledge cutoff of September 30, 2024. Reasoning is mandatory, with effort adjustable from minimal to high and medium as default. Supported parameters include structured outputs, tool use, seed, and verbosity. OpenRouter also reports design-arena and coding-index results; these are catalog-reported figures, not independently verified.[1]
Strengths
- The catalog lists a 400,000-token context window and accepts text, image, and file inputs, suiting long or mixed-media prompts.[1]
- Reasoning effort is configurable across four levels (minimal, low, medium, high), and parameters such as structured outputs, tool calling, seed, and verbosity are supported.[1]
- OpenRouter reports design-arena placements across categories such as SVG, data visualization, and game development, plus a coding index; treat these as catalog-reported measurements.[1]
Limitations
- All evidence here comes from a single OpenRouter catalog entry; no independent model card was available in this source pack, so validate against your own workloads.[1]
- Reasoning cannot be disabled, only adjusted in effort, and output is text-only despite the multimodal inputs.[1]
- The catalog lists a knowledge cutoff of September 30, 2024 and an expiration date of December 11, 2026, but does not explain what the batch designation implies for latency or throughput.[1]
Where to use it
- A plausible candidate for long-context document analysis or mixed image/file review, pending evaluation on your data.[1]
- May suit asynchronous bulk workloads implied by the batch variant, such as offline summarization or dataset processing, though batch behavior is not documented in this source.[1]
- Worth testing for tasks that benefit from tunable reasoning effort combined with structured outputs or tool calling, such as data extraction or code drafting.[1]
Sources
- [1] OpenRouter catalog · OpenAI: GPT-5 (batch)Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...
Specifications
- Model ID
- openai/gpt-5:batch
- Canonical ID
- openai/gpt-5-2025-08-07
- Creator
- openai
- Added to OpenRouter
- 07.08.2025
- Context length
- 400,000
- Modality
- text+image+file->text
- Input modalities
- text, image, file
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.625 / out $5
- Knowledge cutoff
- 30.09.2024
- Expiration date
- 11.12.2026
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | reasoning: mandatory · default medium · efforts: high, medium, low, minimal · parameters: include_reasoning, reasoning, reasoning_effort |
| Coding | CC — below the B band | — |
| Agents | No measurement | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: mandatory · default medium · efforts: high, medium, low, minimal · parameters: include_reasoning, reasoning, reasoning_effort |
| Document analysis | No measurement | input: file |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Coding index | 37.8 | CC — below the B band | 13.11.2026 |
| Design Arena | models · 3dwin rate 41.3% · rank 113 | 1,038Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · asciiartwin rate 49% · rank 51 | 1,136Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · codecategorieswin rate 54.5% · rank 82 | 1,158Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · datavizwin rate 60.5% · rank 52 | 1,219Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · gamedevwin rate 59.3% · rank 66 | 1,176Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · svgwin rate 64.1% · rank 38 | 1,180Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · uicomponentwin rate 57.4% · rank 72 | 1,172Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · websitewin rate 53.7% · rank 79 | 1,177Elo | BB — next 30% of the cohort | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| OpenAI | 400,000 | $0.625 | $5 | — | — | — |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.