← Models

GPT-4.1

OpenAI · GPT-4.1

Long-context multimodal model retained as a legacy reference after retirement from ChatGPT defaults.

Part of GPT family · Other versions: GPT-5.5 Pro , GPT-5.5 , GPT-Rosalind , GPT-5.4 mini , GPT-5.4 nano , GPT-5.4-Pro , GPT-5.4 , GPT-5.3 , GPT-5.3-Codex , GPT-5.2-Codex , GPT-5.2-Pro , GPT-5.2 , GPT-5-Codex , GPT-5 mini , GPT-5 , GPT-5 nano , GPT-4o mini Transcribe , GPT-4o mini TTS , GPT-4o Transcribe , GPT-4o mini , GPT-4o
Type
multimodal
Context
1M tokens
Max Output
33K tokens
Status
legacy
Input
$2/1M tok
Output
$8/1M tok
API Access
Yes
License
proprietary
multimodal long-context general-purpose tool-use enterprise
Released April 2025 · Updated March 27, 2026

Overview

Freshness note: Model capabilities, limits, and pricing can change quickly. This profile is a point-in-time snapshot last verified on March 27, 2026.

GPT-4.1 is a versatile long-context model for mixed tasks across analysis, generation, and workflow automation. OpenAI’s current API docs still list it as the smartest non-reasoning model in the older generation, but ChatGPT retired GPT-4.1 on February 13, 2026 while leaving API availability unchanged. That makes it more useful as a compatibility route than as a new default.

Capabilities

The model handles long-document synthesis, instruction-following, and mixed business or engineering tasks well. It is effective for structured outputs and assistant behaviors where consistency is more important than the heavier reasoning style of GPT-5 or o-series models.

Technical Details

OpenAI’s model card still lists GPT-4.1 with a 1,047,576-token context window and 32,768 max output tokens, which keeps it relevant for long-document and multi-file compatibility cases. It remains useful in enterprise document-heavy pipelines that were built before the GPT-5 generation.

Pricing & Access

OpenAI’s pricing docs still list GPT-4.1 at 2.00per1Minputtokens,2.00 per 1M input tokens, 0.50 cached input, and $8.00 per 1M output tokens. It remains available in the API even though it is no longer part of the current ChatGPT default lineup.

Best Use Cases

Best for enterprise copilots, long-context compatibility work, and API systems that still rely on GPT-4.1 behavior. For new default deployments, OpenAI’s GPT-5 family is the more current path.

Comparisons

Compared with GPT-5.2, GPT-4.1 is the older general-purpose route in OpenAI’s lineup. Compared with GPT-5.4, it is less aligned with OpenAI’s current premium path. Compared with Gemini 2.5 Pro, choice depends on multimodal needs, cost targets, and integration context.