GPT-4.1
GPT-4.1 is a deprecated non-reasoning model for instructions, tools and long inputs. It has a large context without a separate reasoning stage.
Deprecated API; check access details
A million-token model with a smaller output limit
The precise published window is 1,047,576 tokens, with a maximum output of 32,768 tokens. The dated snapshot is from April 2025. Its non-reasoning design differs from later models that expose effort settings.GPT-4.1 official model documentation
Review an existing integration
Practical guidance. For a long-document workflow, compare retrieval of details from different positions in the input. Confirm the output can fit the required answer. A large input window does not prove complete use of all supplied evidence.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Status | Deprecated API; check access details |
| Access | API |
| Model identifiers | gpt-4.1gpt-4.1-2025-04-14 |
| Context window | 1,047,576 tokens Published context for this deprecated release GPT-4.1 official model documentation |
| Maximum output | 32,768 tokens Published maximum output, bounded by the remaining context GPT-4.1 official model documentation |
| Provider status | Deprecated in the current OpenAI model catalog; confirm remaining account access.GPT-4.1 official model documentation |