openai
OpenAI: GPT-4.1
openai/gpt-4.1
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
OpenAI’s openai/gpt-4.1 is listed in the OpenRouter catalog as a flagship text-output model accepting text, image, and file inputs. The catalog reports a context window of about one million tokens and describes the model as optimized for instruction following, real-world software engineering, and long-context reasoning. It also reports support for tool calls and structured outputs. Arena measurements supplied by the catalog show mixed outcomes across the supplied categories. Because this source pack contains only catalog data and no independent model card, teams should validate quality, cost, and fit on their own workloads.[1]
Strengths
Limitations
- Evidence is catalog-only; the source pack did not include an independent model card, so capabilities and fit require workload validation.[1]
- The catalog reports text as the sole output modality and leaves the reasoning field unspecified.[1]
- A June 2024 knowledge cutoff and mixed supplied arena results mean recency and measured performance should be checked for the intended use.[1]
Where to use it
- Consider evaluating it for long-context summarization, question answering, or analysis across text, image, and file inputs.[1]
- It may be worth testing for instruction-following and software-engineering assistance, the areas the catalog describes as optimization targets.[1]
- Consider it for integrations needing tool calls, structured outputs, or controlled generation, subject to task-specific validation.[1]
Sources
- [1] OpenRouter catalog · OpenAI: GPT-4.1Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...
Specifications
- Model ID
- openai/gpt-4.1
- Canonical ID
- openai/gpt-4.1-2025-04-14
- 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 $2 / out $8
- 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 | No measurement | — |
| 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 |
|---|---|---|---|---|
| Design Arena | models · 3dwin rate 30.9% · rank 134 | 833Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · codecategorieswin rate 50.9% · rank 127 | 1,016Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · datavizwin rate 59.5% · rank 99 | 1,104Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · gamedevwin rate 59.1% · rank 109 | 1,070Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · uicomponentwin rate 49.7% · rank 123 | 991Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · websitewin rate 52.3% · rank 128 | 1,031Elo | 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 | $2 | $8 | — | — | 100% |
| OpenAI | 1,047,576 | $2 | $8 | — | — | 100% |
| Azure | 1,047,576 | $2.2 | $8.8 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.