Migrating from gpt-4.5-preview to gpt-5
What changes when you move from gpt-4.5-preview to gpt-5: context window 128,000 → 400,000 tokens.
- From
- gpt-4.5-preview
- Status
- Retired
- Shutdown
- Jul 14, 2025
- Time left
- —
- To
- gpt-5
- Status
- Active
- Shutdown
- none announced
- Time left
- —
Prices
USD per 1M tokens, standard tier| Type | gpt-4.5-preview | gpt-5 | Change |
|---|---|---|---|
| Input | Not published | $1.25first seen October 1, 2026 · source | — |
| Cached input | Not published | $0.125first seen October 1, 2026 · source | — |
| Output | Not published | $10.00first seen October 1, 2026 · source | — |
Other tiers, prompt-size bands and modalities are on each model's page.
Limits
Tokens| Limit | gpt-4.5-preview | gpt-5 | Change |
|---|---|---|---|
| Context window | 128,000 tokensin place when tracking began (October 6, 2026) · source | 400,000 tokensin place when tracking began (October 7, 2026) · source | +212.5% |
| Max output tokens | 16,384 tokensin place when tracking began (October 6, 2026) · source | 128,000 tokensin place when tracking began (October 7, 2026) · source | +681.3% |
Benchmarks
Same benchmark and source on both sides; settings named where they differ| Benchmark | gpt-4.5-preview | gpt-5 | Change |
|---|---|---|---|
| Arena TextArena, high effort (vs no setting). | 1445 ±6 | 1435 ±5 | −10 within range |
| Arena Text: CodingArena, high effort (vs no setting). | 1458 ±13 | 1471 ±8 | +13 within range |
| Arena VisionArena, high effort (vs no setting). | 1225 ±12 | 1210 ±7 | −15 within range |
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 modelsSame on both
- Structured outputs: supported on both.gpt-4.5-preview: in place when tracking began (October 6, 2026) · source · gpt-5: in place when tracking began (October 7, 2026) · source
- Function calling: supported on both.gpt-4.5-preview: in place when tracking began (October 6, 2026) · source · gpt-5: in place when tracking began (October 7, 2026) · source
- Prompt caching: supported on both.gpt-4.5-preview: in place when tracking began (October 6, 2026) · source · gpt-5: in place when tracking began (October 7, 2026) · source
- Batch API: supported on both.gpt-4.5-preview: in place when tracking began (October 6, 2026) · source · gpt-5: in place when tracking began (October 7, 2026) · source
- Image input: supported on both.gpt-4.5-preview: in place when tracking began (October 6, 2026) · source · gpt-5: in place when tracking began (October 7, 2026) · source
- Fine-tuning: not supported on both.gpt-4.5-preview: in place when tracking began (October 6, 2026) · source · gpt-5: in place when tracking began (October 7, 2026) · source
Not published for gpt-4.5-preview: PDF input, Reasoning / thinking, Built-in web search, temperature parameter, top_p parameter, logprobs.
Not published for gpt-5: PDF input, temperature parameter, top_p parameter, logprobs.
Aliases
All aliasesNo aliases point at either model.
Checklist
- Change the model string from
gpt-4.5-previewtogpt-5.
Compared from AIWire's published data when this page loaded. Each fact links to the page it came from. Model pages: gpt-4.5-preview, gpt-5.