Migrating from gpt-4-0613 to gpt-4.1
What changes when you move from gpt-4-0613 to gpt-4.1: input price −93.3%, output price −86.7%, context window 8,192 → 1,047,576 tokens.
- From
- gpt-4-0613
- Status
- Deprecated
- Shutdown
- Oct 23, 2026
- Time left
- 8 days
- To
- gpt-4.1
- Status
- Active
- Shutdown
- none announced
- Time left
- —
Prices
USD per 1M tokens, standard tier| Type | gpt-4-0613 | gpt-4.1 | Change |
|---|---|---|---|
| Input | $30.00first seen October 1, 2026 · source | $2.00first seen October 1, 2026 · source | −93.3% |
| Cached input | Not published | $0.50first seen October 1, 2026 · source | — |
| Output | $60.00first seen October 1, 2026 · source | $8.00first seen October 1, 2026 · source | −86.7% |
At 1M input and 250K output tokens a month: $45.00 on gpt-4-0613, $4.00 on gpt-4.1 (−91.1%).
Other tiers, prompt-size bands and modalities are on each model's page.
Limits
Tokens| Limit | gpt-4-0613 | gpt-4.1 | Change |
|---|---|---|---|
| Context window | 8,192 tokensin place when tracking began (October 6, 2026) · source | 1,047,576 tokensin place when tracking began (October 6, 2026) · source | +12687.8% |
| Max output tokens | 8,192 tokensin place when tracking began (October 6, 2026) · source | 32,768 tokensin place when tracking began (October 6, 2026) · source | +300% |
Benchmarks
Same benchmark, source and setting on both sides| Benchmark | gpt-4-0613 | gpt-4.1 | Change |
|---|---|---|---|
| Arena TextArena. Ranges don't overlap. | 1276 ±4 | 1415 ±4 | +139 |
| Arena Text: CodingArena. Ranges don't overlap. | 1315 ±8 | 1456 ±7 | +141 |
| GPQA DiamondEpoch AI. | 30.7% | 66.9% | +36.2 pts |
| MATH Level 5Epoch AI. | 23.0% | 83.0% | +60.0 pts |
| OTIS Mock AIME 2024-2025Epoch AI. | 1.1% | 38.3% | +37.2 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
- Batch API: supported on both.gpt-4-0613: in place when tracking began (October 6, 2026) · source · gpt-4.1: in place when tracking began (October 6, 2026) · source
- Fine-tuning: supported on both.gpt-4-0613: 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-4-0613: Structured outputs, Function calling, Prompt caching, Image input, 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.
Aliases
All aliasesAliases pointing at gpt-4-0613: gpt-4 (in place when tracking began (October 7, 2026) · source)
No aliases point at gpt-4.1.
On cloud platforms
All platform dates| Model | Platform | Platform ID | Shutdown | Time left |
|---|---|---|---|---|
| gpt-4.1 | Microsoft Foundryversion 2025-04-14 | gpt-4.1 | 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-4-0613togpt-4.1.
Counting to 8:00 pm ET on October 22, 2026, which is 00:00 UTC on October 23, 2026.
Compared from AIWire's published data when this page loaded. Each fact links to the page it came from. Model pages: gpt-4-0613, gpt-4.1.