Migrating from gpt-4.1-nano to gpt-5-nano
What changes when you move from gpt-4.1-nano to gpt-5-nano: input price −50%, output price 0%, context window 1,047,576 → 400,000 tokens.
- From
- gpt-4.1-nano
- Status
- Deprecated
- Shutdown
- Oct 23, 2026
- Time left
- 8 days
- Status
- Active
- Shutdown
- none announced
- Time left
- —
Prices
USD per 1M tokens, standard tier| Type | gpt-4.1-nano | gpt-5-nano | Change |
|---|---|---|---|
| Input | $0.10first seen October 1, 2026 · source | $0.05first seen October 1, 2026 · source | −50% |
| Cached input | $0.025first seen October 1, 2026 · source | $0.005first seen October 1, 2026 · source | −80% |
| Output | $0.40first seen October 1, 2026 · source | $0.40first seen October 1, 2026 · source | 0% |
At 1M input and 250K output tokens a month: $0.20 on gpt-4.1-nano, $0.15 on gpt-5-nano (−25%).
Other tiers, prompt-size bands and modalities are on each model's page.
Limits
Tokens| Limit | gpt-4.1-nano | gpt-5-nano | Change |
|---|---|---|---|
| Context window | 1,047,576 tokensin place when tracking began (October 6, 2026) · source | 400,000 tokensin place when tracking began (October 6, 2026) · source | −61.8% |
| Max output tokens | 32,768 tokensin place when tracking began (October 6, 2026) · source | 128,000 tokensin place when tracking began (October 6, 2026) · source | +290.6% |
Benchmarks
Same benchmark and source on both sides; settings named where they differ| Benchmark | gpt-4.1-nano | gpt-5-nano | Change |
|---|---|---|---|
| Arena TextArena, high effort (vs no setting). Ranges don't overlap. | 1322 ±8 | 1338 ±7 | +16 |
| Arena Text: CodingArena, high effort (vs no setting). | 1373 ±19 | 1385 ±15 | +12 within range |
| Arena VisionArena, high effort (vs no setting). Ranges don't overlap. | 1089 ±18 | 1146 ±11 | +57 |
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-nano, not supported on gpt-5-nano.gpt-4.1-nano: in place when tracking began (October 6, 2026) · source · gpt-5-nano: in place when tracking began (October 6, 2026) · source
Same on both
- Structured outputs: supported on both.gpt-4.1-nano: in place when tracking began (October 6, 2026) · source · gpt-5-nano: in place when tracking began (October 6, 2026) · source
- Function calling: supported on both.gpt-4.1-nano: in place when tracking began (October 6, 2026) · source · gpt-5-nano: in place when tracking began (October 6, 2026) · source
- Prompt caching: supported on both.gpt-4.1-nano: in place when tracking began (October 6, 2026) · source · gpt-5-nano: in place when tracking began (October 6, 2026) · source
- Batch API: supported on both.gpt-4.1-nano: in place when tracking began (October 6, 2026) · source · gpt-5-nano: in place when tracking began (October 6, 2026) · source
- Image input: supported on both.gpt-4.1-nano: in place when tracking began (October 6, 2026) · source · gpt-5-nano: in place when tracking began (October 6, 2026) · source
Not published for gpt-4.1-nano: PDF input, Reasoning / thinking, Built-in web search, temperature parameter, top_p parameter, logprobs.
Not published for gpt-5-nano: PDF input, Built-in web search, temperature parameter, top_p parameter, logprobs.
Free tier
gpt-4.1-nano: Free for shared data, 10M tokens a day for Launch and Grow (2.5M for Build), in place when tracking began (October 12, 2026) (source) · All free models
gpt-5-nano: no free tier listed
Free access is lost: gpt-5-nano has no free tier listed.
Aliases
All aliasesAliases pointing at gpt-4.1-nano: gpt-4.1-nano (in place when tracking began (October 7, 2026) · source)
No aliases point at gpt-5-nano.
On cloud platforms
All platform dates| Model | Platform | Platform ID | Shutdown | Time left |
|---|---|---|---|---|
| gpt-4.1-nano | Microsoft Foundryversion 2025-04-14 | gpt-4.1-nano | 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-4.1-nanotogpt-5-nano. - Check prompt sizes: gpt-5-nano's context window is 400,000 tokens, gpt-4.1-nano's 1,047,576 tokens.
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-4.1-nano, gpt-5-nano.