ModelRefs / GPT-4.1 - AI model implementation reference

GPT-4.1 - AI model implementation reference

GPT-4.1 is a deprecated OpenAI API model, designed for instruction-following, coding, tool use, and long-input applications. OpenAI's deprecations page gives the gpt-4.1-2025-04-14 snapshot a shutdown date of 14 January 2027, with gpt-6-luna as the recommended replacement. Its non-reasoning behavior, latency, and long-context handling should be compared against a current OpenAI family before any new integration.

Overview

GPT-4.1 is attributed to OpenAI in ModelRefs' canonical registry. Tracked modalities: Text input and output, Image input. Primary use cases considered on ModelRefs: Repository and document analysis; Tool calling, structured extraction, and instruction-heavy workflows.

This ModelRefs profile is decision-support material, not a final or universal ranking. Confirm current behavior, access, pricing, limits, licensing, and lifecycle in OpenAI's own documentation, and evaluate GPT-4.1 on representative workloads before implementation.

Lifecycle

Deprecated. Still served, but the provider has scheduled its retirement.

Stops serving
14 January 2027
Provider's replacement
gpt-6-luna

Provider-documented snapshots

  • gpt-4.1-2025-04-14

Source: developers.openai.com, checked 2026-10-16.

Benchmark & Evaluation

ModelRefs currently has partial, narrow benchmark coverage for GPT-4.1. Treat the available benchmark evidence as one input to the decision, not a guarantee that GPT-4.1 is the strongest option for your workload, and evaluate it on representative workloads before selecting it.

  • Provider-reported benchmark results should be interpreted with methodology, dataset, prompting, tool, sampling, and recency limitations in mind.
  • G.18 registers OpenAI's source-scoped simple-evals GPQA result for gpt-4.1-2025-04-14. It supports Partial eligibility only; broader benchmark coverage and independent reproduction remain incomplete.

Implementation considerations

  • Use a dated model snapshot when behavior stability matters.
  • Evaluate long-context retrieval and instruction adherence on representative inputs rather than assuming full-window reliability.
  • Hosted through eligible OpenAI API endpoints.
  • Deprecated with a scheduled shutdown of 14 January 2027 for gpt-4.1-2025-04-14; endpoint features, quotas, and retention controls must still be checked for the exact account and model snapshot.

Risks and limitations

  • Outputs can be incorrect or unsuitable for the intended task; use task-specific evaluation, grounding, and human review where consequences are material.
  • API availability, model aliases, rate limits, data controls, regions, and prices are mutable and differ by product channel.

Source coverage

ModelRefs reviewed OpenAI's published material on 2026-06-29. Model behavior, access, pricing, limits, and lifecycle can change, so verify the linked provider documentation before implementation. What remains open is recorded on this page: Provider-reported evaluations lack independent reproduction and a registered canonical evaluation date. Fit and comparison signals remain provisional until tested on your own workload.

Connected ModelRefs evidence

Sources

Continue your research

Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to GPT-4.1 - AI model implementation reference.