openai
OpenAI: GPT-5 Mini
openai/gpt-5-mini
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-mini is a compact GPT-5 variant intended for lighter reasoning tasks, with text, image, and file inputs and text output. The listing reports a large context window, mandatory reasoning with selectable effort, tool and structured-output support, and reduced latency and cost relative to GPT-5. Its supplied benchmark entries cover selected design, coding, and agentic categories but do not establish broad real-world performance. An independent model card was not available in this source pack, so capabilities and suitability should be validated on target workloads.[1]
Strengths
- The catalog positions it as a smaller GPT-5 option for lighter reasoning, with lower latency and cost than GPT-5.[1]
- It accepts text, image, and file inputs, returns text, and lists a very large context window.[1]
- Reasoning effort is configurable, and tool use, structured outputs, seed, response format, and verbosity controls are listed.[1]
Limitations
- Evidence is limited to OpenRouter's catalog; no independent model card was supplied, so target-workload validation is needed.[1]
- The supplied benchmark data covers only selected design, coding, and agentic categories, and a general intelligence index is unpopulated.[1]
- Reasoning is mandatory even though effort can be adjusted; the catalog also lists an expiration date, so operational fit and availability should be confirmed.[1]
Where to use it
- Potential fit for assistants that need configurable reasoning over long, multimodal inputs while returning text.[1]
- Worth evaluating for tool-using or structured-output workflows such as data extraction and application backends.[1]
- May suit teams seeking a lower-latency, lower-cost GPT-5-family option, subject to workload testing.[1]
Sources
- [1] OpenRouter catalog · OpenAI: GPT-5 MiniSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....
Specifications
- Model ID
- openai/gpt-5-mini
- Canonical ID
- openai/gpt-5-mini-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 $0.250 / out $2
- Knowledge cutoff
- 31.05.2024
- 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 | CC — below the B band | 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 | 15.6 | CC — below the B band | 13.11.2026 |
| Artificial Analysis | Agentic index | 6.8 | CC — below the B band | 13.11.2026 |
| Design Arena | models · 3dwin rate 36.9% · rank 116 | 1,020Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · asciiartwin rate 44.8% · rank 57 | 1,120Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · codecategorieswin rate 43.5% · rank 106 | 1,105Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · datavizwin rate 43.7% · rank 92 | 1,129Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · gamedevwin rate 46.5% · rank 93 | 1,120Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · svgwin rate 45.8% · rank 71 | 1,083Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · uicomponentwin rate 41.9% · rank 99 | 1,097Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · websitewin rate 44.3% · rank 105 | 1,118Elo | CC — below the B band | 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 | $0.125 | $1 | — | — | 100% |
| Azure | 400,000 | $0.250 | $2 | — | — | 100% |
| OpenAI | 400,000 | $0.250 | $2 | — | — | 100% |
| Azure | 400,000 | $0.275 | $2.2 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.