All times Eastern (ET)Provider pages checked daily at

Migrating from gpt-4.5-preview to gpt-4.1

What changes when you move from gpt-4.5-preview to gpt-4.1: context window 128,000 → 1,047,576 tokens.

Status
Retired
Shutdown
Jul 14, 2025
Time left
—
Status
Active
Shutdown
none announced
Time left
—

Prices

USD per 1M tokens, standard tier
Typegpt-4.5-previewgpt-4.1Change
InputNot published$2.00first seen October 1, 2026 · source—
Cached inputNot published$0.50first seen October 1, 2026 · source—
OutputNot published$8.00first seen October 1, 2026 · source—

Other tiers, prompt-size bands and modalities are on each model's page.

Limits

Tokens
Limitgpt-4.5-previewgpt-4.1Change
Context window128,000 tokensin place when tracking began (October 6, 2026) · source1,047,576 tokensin place when tracking began (October 6, 2026) · source+718.4%
Max output tokens16,384 tokensin place when tracking began (October 6, 2026) · source32,768 tokensin place when tracking began (October 6, 2026) · source+100%

Benchmarks

Same benchmark, source and setting on both sides
Benchmarkgpt-4.5-previewgpt-4.1Change
Arena TextArena. Ranges don't overlap.1445 ±61415 ±4−30
Arena Text: CodingArena.1458 ±131456 ±7−2
within range
Arena VisionArena.1225 ±121214 ±7−11
within range
GPQA DiamondEpoch AI.68.7%66.9%−1.8 pts
MATH Level 5Epoch AI.78.6%83.0%+4.4 pts
OTIS Mock AIME 2024-2025Epoch AI.37.8%38.3%+0.5 pts

A score from one source is never compared with another source's, and company-reported scores are compared only within the same company; settings named where they differ. Data: Arena (arena.ai), CC BY 4.0; Epoch AI, Capabilities & benchmarking (epoch.ai/benchmarks), CC BY.

Features and parameters

Compare models
  • Fine-tuning: not supported on gpt-4.5-preview, supported on gpt-4.1.gpt-4.5-preview: in place when tracking began (October 6, 2026) · source · gpt-4.1: in place when tracking began (October 6, 2026) · source

Same on both

  • Structured outputs: supported on both.gpt-4.5-preview: in place when tracking began (October 6, 2026) · source · gpt-4.1: in place when tracking began (October 6, 2026) · source
  • Function calling: supported on both.gpt-4.5-preview: in place when tracking began (October 6, 2026) · source · gpt-4.1: in place when tracking began (October 6, 2026) · source
  • Prompt caching: supported on both.gpt-4.5-preview: in place when tracking began (October 6, 2026) · source · gpt-4.1: in place when tracking began (October 6, 2026) · source
  • Batch API: supported on both.gpt-4.5-preview: in place when tracking began (October 6, 2026) · source · gpt-4.1: in place when tracking began (October 6, 2026) · source
  • Image input: supported on both.gpt-4.5-preview: in place when tracking began (October 6, 2026) · source · gpt-4.1: in place when tracking began (October 6, 2026) · source

Not published for gpt-4.5-preview: PDF input, Reasoning / thinking, Built-in web search, temperature parameter, top_p parameter, logprobs.

Not published for gpt-4.1: PDF input, Reasoning / thinking, temperature parameter, top_p parameter, logprobs.

No aliases point at either model.

On cloud platforms

All platform dates
ModelPlatformPlatform IDShutdownTime left
gpt-4.1Microsoft Foundryversion 2025-04-14gpt-4.1Apr 14, 2027Deprecated181 days

Read daily from each platform's own pages. The status above uses each company's own date. Time left counts to 00:00 UTC on the shutdown date, which is the evening before in ET.

Checklist

  1. Change the model string from gpt-4.5-preview to gpt-4.1.

Compared from AIWire's published data when this page loaded. Each fact links to the page it came from. Model pages: gpt-4.5-preview, gpt-4.1.