openai
OpenAI: GPT-4.1 Mini
openai/gpt-4.1-mini
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
OpenRouter's catalog lists openai/gpt-4.1-mini (canonical variant openai/gpt-4.1-mini-2025-04-14) as a mid-sized OpenAI model that it describes as competitive with GPT-4o at lower latency and cost; that positioning is catalog copy, not an independent measurement. The entry reports text, image and file inputs with text output, an about-one-million-token context window, a June 2024 knowledge cutoff, and support for tools plus structured output parameters. No independent model card was available in this source pack.[1]
Strengths
- Catalog-reported multimodal inputs cover text, images and files, while output is text only.[1]
- The listed context window is around one million tokens, which may suit long-document or many-turn workloads if validated.[1]
- Supported parameters include tools, tool choice, structured outputs, response format, seed and common decoding controls.[1]
Limitations
- Evidence is catalog-only: no independent model card or first-party technical report was included, so workload validation is needed.[1]
- The catalog lists text as the sole output modality and a June 2024 knowledge cutoff.[1]
- Claims of lower latency and cost versus GPT-4o are description text, while arena and index data are contextual signals rather than proof for a specific task.[1]
Where to use it
- A reasonable candidate to evaluate for high-volume assistants that need long context and can accept text-only answers.[1]
- Worth testing for document, image or file understanding pipelines that must return structured text.[1]
- Plausible fit for tool-using application backends where JSON-mode style outputs and function calling matter.[1]
Sources
- [1] OpenRouter catalog · OpenAI: GPT-4.1 MiniSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...
Specifications
- Model ID
- openai/gpt-4.1-mini
- Canonical ID
- openai/gpt-4.1-mini-2025-04-14
- Creator
- openai
- Added to OpenRouter
- 14.04.2025
- Context length
- 1,047,576
- Modality
- text+image+file->text
- Input modalities
- image, text, file
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.400 / out $1.6
- Knowledge cutoff
- 30.06.2024
- Expiration date
- —
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 | — |
| Coding | CC — below the B band | — |
| Agents | No measurement | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | — |
| 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 | 20.2 | CC — below the B band | 13.11.2026 |
| Design Arena | models · 3dwin rate 30.5% · rank 135 | 820Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · codecategorieswin rate 47.5% · rank 133 | 984Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · datavizwin rate 49.2% · rank 114 | 1,034Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · gamedevwin rate 58.5% · rank 113 | 1,061Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · uicomponentwin rate 45.4% · rank 127 | 952Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · websitewin rate 47.8% · rank 135 | 990Elo | 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) |
|---|---|---|---|---|---|---|
| Azure | 1,047,576 | $0.400 | $1.6 | — | — | 100% |
| OpenAI | 1,047,576 | $0.400 | $1.6 | — | — | 100% |
| Azure | 1,047,576 | $0.440 | $1.76 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.