Migrating from gpt-4.1-nano to gpt-5.6-luna
What changes when you move from gpt-4.1-nano to gpt-5.6-luna: input price +100%, output price +200%, context window 1,047,576 → 1,050,000 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-5.6-luna | Change |
|---|---|---|---|
| Input | $0.10first seen October 1, 2026 · source | $0.20first seen October 1, 2026 · source | +100% |
| Cached input | $0.025first seen October 1, 2026 · source | $0.02first seen October 1, 2026 · source | −20% |
| Output | $0.40first seen October 1, 2026 · source | $1.20first seen October 1, 2026 · source | +200% |
At 1M input and 250K output tokens a month: $0.20 on gpt-4.1-nano, $0.50 on gpt-5.6-luna (+150%).
Other tiers, prompt-size bands and modalities are on each model's page.
Limits
Tokens| Limit | gpt-4.1-nano | gpt-5.6-luna | Change |
|---|---|---|---|
| Context window | 1,047,576 tokensin place when tracking began (October 6, 2026) · source | 1,050,000 tokensin place when tracking began (October 7, 2026) · source | +0.2% |
| Max output tokens | 32,768 tokensin place when tracking began (October 6, 2026) · source | 128,000 tokensin place when tracking began (October 7, 2026) · source | +290.6% |
Benchmarks
Same benchmark and source on both sides; settings named where they differ| Benchmark | gpt-4.1-nano | gpt-5.6-luna | Change |
|---|---|---|---|
| Arena TextArena, xhigh effort (vs no setting). Ranges don't overlap. | 1322 ±8 | 1453 ±4 | +131 |
| Arena Text: CodingArena, xhigh effort (vs no setting). Ranges don't overlap. | 1373 ±19 | 1501 ±7 | +128 |
| Arena VisionArena, xhigh effort (vs no setting). Ranges don't overlap. | 1089 ±18 | 1258 ±7 | +169 |
GPQA DiamondEpoch AI, max effort (vs no setting).Other settings
| 48.9% | 91.6% | +42.7 pts |
OTIS Mock AIME 2024-2025Epoch AI, max effort (vs no setting).Other settings
| 28.9% | 98.3% | +69.4 pts |
| SimpleQA VerifiedEpoch AI, max effort (vs no setting). | 6.0% | 41.0% | +35.0 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: supported on gpt-4.1-nano, not supported on gpt-5.6-luna.gpt-4.1-nano: in place when tracking began (October 6, 2026) · source · gpt-5.6-luna: in place when tracking began (October 7, 2026) · source
Same on both
- Structured outputs: supported on both.gpt-4.1-nano: in place when tracking began (October 6, 2026) · source · gpt-5.6-luna: in place when tracking began (October 7, 2026) · source
- Function calling: supported on both.gpt-4.1-nano: in place when tracking began (October 6, 2026) · source · gpt-5.6-luna: in place when tracking began (October 7, 2026) · source
- Prompt caching: supported on both.gpt-4.1-nano: in place when tracking began (October 6, 2026) · source · gpt-5.6-luna: in place when tracking began (October 7, 2026) · source
- Batch API: supported on both.gpt-4.1-nano: in place when tracking began (October 6, 2026) · source · gpt-5.6-luna: in place when tracking began (October 7, 2026) · source
- Image input: supported on both.gpt-4.1-nano: in place when tracking began (October 6, 2026) · source · gpt-5.6-luna: in place when tracking began (October 7, 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-5.6-luna: PDF input, 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)
gpt-5.6-luna: 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
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-5.6-luna.
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 |
| gpt-5.6-luna | Amazon Bedrock | openai.gpt-5.6-luna | not before Jul 13, 2027Active | |
| gpt-5.6-luna | Microsoft Foundryversion 2026-07-09 | gpt-5.6-luna | Jan 11, 2028Active | 453 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-5.6-luna. - Re-check costs: gpt-5.6-luna costs more than gpt-4.1-nano (input +100%, output +200%).
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-5.6-luna.