All times Eastern (ET)Provider pages checked daily at
ProSign inRSS

Migrating from gpt-4.1-mini to gpt-5-mini

What changes when you move from gpt-4.1-mini to gpt-5-mini: input price −37.5%, output price +25%, context window 1,047,576 → 400,000 tokens.

Status
Active
Shutdown
none announced
Time left
—
Status
Active
Shutdown
none announced
Time left
—

Prices

USD per 1M tokens, standard tier
Typegpt-4.1-minigpt-5-miniChange
Input$0.40first seen October 1, 2026 · source$0.25first seen October 1, 2026 · source−37.5%
Cached input$0.10first seen October 1, 2026 · source$0.025first seen October 1, 2026 · source−75%
Output$1.60first seen October 1, 2026 · source$2.00first seen October 1, 2026 · source+25%

At 1M input and 250K output tokens a month: $0.80 on gpt-4.1-mini, $0.75 on gpt-5-mini (−6.3%).

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

Limits

Tokens
Limitgpt-4.1-minigpt-5-miniChange
Context window1,047,576 tokensin place when tracking began (October 6, 2026) · source400,000 tokensin place when tracking began (October 6, 2026) · source−61.8%
Max output tokens32,768 tokensin place when tracking began (October 6, 2026) · source128,000 tokensin place when tracking began (October 6, 2026) · source+290.6%

Benchmarks

Same benchmark and source on both sides; settings named where they differ
Benchmarkgpt-4.1-minigpt-5-miniChange
Arena TextArena, high effort (vs no setting).1383 ±41390 ±5+7
within range
Arena Text: CodingArena, high effort (vs no setting).1433 ±81432 ±8−1
within range
Arena VisionArena, high effort (vs no setting). Ranges don't overlap.1201 ±81183 ±8−18

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.

Features and parameters

Compare models
  • Fine-tuning: supported on gpt-4.1-mini, not supported on gpt-5-mini.gpt-4.1-mini: in place when tracking began (October 6, 2026) · source · gpt-5-mini: in place when tracking began (October 6, 2026) · source

Same on both

  • Structured outputs: supported on both.gpt-4.1-mini: in place when tracking began (October 6, 2026) · source · gpt-5-mini: in place when tracking began (October 6, 2026) · source
  • Function calling: supported on both.gpt-4.1-mini: in place when tracking began (October 6, 2026) · source · gpt-5-mini: in place when tracking began (October 6, 2026) · source
  • Batch API: supported on both.gpt-4.1-mini: in place when tracking began (October 6, 2026) · source · gpt-5-mini: in place when tracking began (October 6, 2026) · source
  • Image input: supported on both.gpt-4.1-mini: in place when tracking began (October 6, 2026) · source · gpt-5-mini: in place when tracking began (October 6, 2026) · source
  • Built-in web search: supported on both.gpt-4.1-mini: in place when tracking began (October 6, 2026) · source · gpt-5-mini: in place when tracking began (October 6, 2026) · source

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

Not published for gpt-5-mini: Prompt caching, PDF input, temperature parameter, top_p parameter, logprobs.

Aliases

All aliases

No aliases point at either model.

On cloud platforms

All platform dates
ModelPlatformPlatform IDShutdownTime left
gpt-4.1-miniMicrosoft Foundryversion 2025-04-14gpt-4.1-miniApr 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-4.1-mini to gpt-5-mini.
  2. Check prompt sizes: gpt-5-mini's context window is 400,000 tokens, gpt-4.1-mini's 1,047,576 tokens.
  3. Re-check costs: gpt-5-mini costs more than gpt-4.1-mini (output +25%).

Compared from AIWire's published data when this page loaded. Each fact links to the page it came from. Model pages: gpt-4.1-mini, gpt-5-mini.