Migrating from gpt-4o-mini to gpt-4.1-mini
What changes when you move from gpt-4o-mini to gpt-4.1-mini: input price +166.7%, output price +166.7%, context window 128,000 → 1,047,576 tokens.
- From
- gpt-4o-mini
- Status
- Active
- Shutdown
- none announced
- Time left
- —
- Status
- Active
- Shutdown
- none announced
- Time left
- —
Prices
USD per 1M tokens, standard tier| Type | gpt-4o-mini | gpt-4.1-mini | Change |
|---|---|---|---|
| Input | $0.15first seen October 1, 2026 · source | $0.40first seen October 1, 2026 · source | +166.7% |
| Cached input | $0.075first seen October 1, 2026 · source | $0.10first seen October 1, 2026 · source | +33.3% |
| Output | $0.60first seen October 1, 2026 · source | $1.60first seen October 1, 2026 · source | +166.7% |
At 1M input and 250K output tokens a month: $0.30 on gpt-4o-mini, $0.80 on gpt-4.1-mini (+166.7%).
Other tiers, prompt-size bands and modalities are on each model's page.
Limits
Tokens| Limit | gpt-4o-mini | gpt-4.1-mini | Change |
|---|---|---|---|
| Context window | 128,000 tokensin place when tracking began (October 6, 2026) · source | 1,047,576 tokensin place when tracking began (October 6, 2026) · source | +718.4% |
| Max output tokens | 16,384 tokensin place when tracking began (October 6, 2026) · source | 32,768 tokensin place when tracking began (October 6, 2026) · source | +100% |
Benchmarks
Same benchmark, source and setting on both sides| Benchmark | gpt-4o-mini | gpt-4.1-mini | Change |
|---|---|---|---|
| Arena TextArena. Ranges don't overlap. | 1318 ±4 | 1383 ±4 | +65 |
| Arena Text: CodingArena. Ranges don't overlap. | 1348 ±7 | 1433 ±8 | +85 |
| Arena VisionArena. Ranges don't overlap. | 1097 ±8 | 1201 ±8 | +104 |
| FrontierMath Tiers 1-3Epoch AI. | 0.7% | 6.7% | +6.0 pts |
| GPQA DiamondEpoch AI. | 37.7% | 65.8% | +28.1 pts |
| MATH Level 5Epoch AI. | 52.6% | 87.3% | +34.7 pts |
| OTIS Mock AIME 2024-2025Epoch AI. | 6.9% | 44.7% | +37.8 pts |
| SimpleQA VerifiedEpoch AI. | 8.3% | 12.7% | +4.4 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 modelsSame on both
- Structured outputs: supported on both.gpt-4o-mini: in place when tracking began (October 6, 2026) · source · gpt-4.1-mini: in place when tracking began (October 6, 2026) · source
- Function calling: supported on both.gpt-4o-mini: in place when tracking began (October 6, 2026) · source · gpt-4.1-mini: in place when tracking began (October 6, 2026) · source
- Batch API: supported on both.gpt-4o-mini: in place when tracking began (October 6, 2026) · source · gpt-4.1-mini: in place when tracking began (October 6, 2026) · source
- Image input: supported on both.gpt-4o-mini: in place when tracking began (October 6, 2026) · source · gpt-4.1-mini: in place when tracking began (October 6, 2026) · source
- Fine-tuning: supported on both.gpt-4o-mini: in place when tracking began (October 6, 2026) · source · gpt-4.1-mini: in place when tracking began (October 6, 2026) · source
- Built-in web search: supported on both.gpt-4o-mini: in place when tracking began (October 6, 2026) · source · gpt-4.1-mini: in place when tracking began (October 6, 2026) · source
Not published for gpt-4o-mini: Prompt caching, PDF input, Reasoning / thinking, temperature parameter, top_p parameter, logprobs.
Not published for gpt-4.1-mini: Prompt caching, PDF input, Reasoning / thinking, temperature parameter, top_p parameter, logprobs.
Aliases
All aliasesNo aliases point at either model.
On cloud platforms
All platform dates| Model | Platform | Platform ID | Shutdown | Time left |
|---|---|---|---|---|
| gpt-4o-mini | Microsoft Foundryversion 2024-07-18 | gpt-4o-mini | Apr 14, 2027Deprecated | 181 days |
| gpt-4.1-mini | Microsoft Foundryversion 2025-04-14 | gpt-4.1-mini | Apr 14, 2027Deprecated | 181 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
- Change the model string from
gpt-4o-minitogpt-4.1-mini. - Re-check costs: gpt-4.1-mini costs more than gpt-4o-mini (input +166.7%, output +166.7%).
Compared from AIWire's published data when this page loaded. Each fact links to the page it came from. Model pages: gpt-4o-mini, gpt-4.1-mini.