Migrating from gpt-3.5-turbo-0125 to gpt-4-turbo
What changes when you move from gpt-3.5-turbo-0125 to gpt-4-turbo: input price +1900%, output price +1900%, context window 16,385 → 128,000 tokens.
- Status
- Deprecated
- Shutdown
- Oct 23, 2026
- Time left
- 8 days
- Status
- Deprecated
- Shutdown
- Oct 23, 2026
- Time left
- 8 days
gpt-4-turbo is itself deprecated, shutting down Oct 23, 2026. Its replacement is gpt-5.6-sol.
Prices
USD per 1M tokens, standard tier| Type | gpt-3.5-turbo-0125 | gpt-4-turbo | Change |
|---|---|---|---|
| Input | $0.50first seen October 1, 2026 · source | $10.00first seen October 1, 2026 · source | +1900% |
| Output | $1.50first seen October 1, 2026 · source | $30.00first seen October 1, 2026 · source | +1900% |
At 1M input and 250K output tokens a month: $0.875 on gpt-3.5-turbo-0125, $17.50 on gpt-4-turbo (+1900%).
Other tiers, prompt-size bands and modalities are on each model's page.
Limits
Tokens| Limit | gpt-3.5-turbo-0125 | gpt-4-turbo | Change |
|---|---|---|---|
| Context window | 16,385 tokensin place when tracking began (October 6, 2026) · source | 128,000 tokensin place when tracking began (October 6, 2026) · source | +681.2% |
| Max output tokens | 4,096 tokensin place when tracking began (October 6, 2026) · source | 4,096 tokensin place when tracking began (October 6, 2026) · source | 0% |
Benchmarks
Same benchmark, source and setting on both sides| Benchmark | gpt-3.5-turbo-0125 | gpt-4-turbo | Change |
|---|---|---|---|
| Arena TextArena. Ranges don't overlap. | 1226 ±5 | 1325 ±4 | +99 |
| Arena Text: CodingArena. Ranges don't overlap. | 1275 ±8 | 1347 ±7 | +72 |
| FrontierMath Tiers 1-3Epoch AI. | 0.0% | 0.7% | +0.7 pts |
| GPQA DiamondEpoch AI. | 27.2% | 46.6% | +19.4 pts |
| MATH Level 5Epoch AI. | 11.6% | 46.7% | +35.1 pts |
| OTIS Mock AIME 2024-2025Epoch AI. | 2.2% | 6.7% | +4.5 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-3.5-turbo-0125, not supported on gpt-4-turbo.gpt-3.5-turbo-0125: in place when tracking began (October 6, 2026) · source · gpt-4-turbo: in place when tracking began (October 6, 2026) · source
Same on both
- Batch API: supported on both.gpt-3.5-turbo-0125: in place when tracking began (October 6, 2026) · source · gpt-4-turbo: in place when tracking began (October 6, 2026) · source
Not published for gpt-3.5-turbo-0125: 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-turbo: Structured outputs, Prompt caching, PDF input, Reasoning / thinking, Built-in web search, temperature parameter, top_p parameter, logprobs.
Aliases
All aliasesAliases pointing at gpt-3.5-turbo-0125: gpt-3.5-turbo (in place when tracking began (October 7, 2026) · source)
Aliases pointing at gpt-4-turbo: gpt-4-turbo (in place when tracking began (October 7, 2026) · source)
Checklist
- Change the model string from
gpt-3.5-turbo-0125togpt-4-turbo. - Re-check costs: gpt-4-turbo costs more than gpt-3.5-turbo-0125 (input +1900%, output +1900%).
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-3.5-turbo-0125, gpt-4-turbo.