GPT-3.5 Turbo (0125)
API ID gpt-3.5-turbo-0125
gpt-3.5-turbo-0125 is an OpenAI model. It has a 16,385-token context window and up to 4,096 output tokens. Standard price: from $0.50 input and from $1.50 output per 1M tokens.
- Status
- Deprecated
- Released
- —
- Shutdown
- Oct 23, 2026
- Replacement
- GPT-5.6 Terragpt-5.6-terra
It stops serving on October 23, 2026. Recommended replacement: gpt-5.6-terra.
How to migrate to GPT-5.6 Terra
Benchmarks
Scores as each source published themComparing with GPT-3.5 Turbo 16K (0613), the previous model in this line. A score is compared only with the same benchmark from the same source, at the same setting where both have it. Full comparison: prices, limits, features
Arena
| Arena | GPT-3.5 Turbo (0125) | GPT-3.5 Turbo 16K (0613) | Change | Rank | Date | Source |
|---|---|---|---|---|---|---|
TextBy category
| 1226 ±5 | not rated | 334 of 415 66,207 votes | Oct 13, 2026 | source | |
| Text: Coding | 1275 ±8 | not rated | 324 of 410 11,130 votes | Oct 13, 2026 | source |
Rated as gpt-3.5-turbo-0125. Ratings come from people voting between two anonymous answers; Text is style-controlled, as on arena.ai. Data: Arena (arena.ai), CC BY 4.0.
Epoch AI
| Benchmark | GPT-3.5 Turbo (0125) | GPT-3.5 Turbo 16K (0613) | Change | Setting | Run | Source |
|---|---|---|---|---|---|---|
| FrontierMath Tiers 1-3 | 0.0% | not run | Aug 27, 2026 | source | ||
| GPQA Diamond | 27.2% | not run | Jan 27, 2025 | source | ||
| MATH Level 5 | 11.6% | not run | Jan 27, 2025 | source | ||
| OTIS Mock AIME 2024-2025 | 2.2% | not run | Aug 7, 2026 | source |
Run independently by Epoch AI. Data: Epoch AI, Capabilities & benchmarking (epoch.ai/benchmarks), CC BY.
Aliases pointing here: gpt-3.5-turbo (in place when tracking began (October 7, 2026))
Features
Compare models| Feature | Value | Since | Source |
|---|---|---|---|
| Batch APISend many requests as one job that runs in the background, usually finished within 24 hours, at a lower price than live requests. | Supported | in place when tracking began (October 6, 2026) | source |
| Fine-tuningYou can train your own version of the model on your examples through the company's API, then call it like any other model. | Supported | in place when tracking began (October 6, 2026) | source |
| Context windowThe most the model can work with in one request, in tokens: your prompt, conversation history and files. A token is about three-quarters of an English word. | 16,385 tokens | in place when tracking began (October 6, 2026) | source |
| Max output tokensThe longest reply the model can write in one response, in tokens. A token is about three-quarters of an English word. | 4,096 tokens | in place when tracking began (October 6, 2026) | source |
Not published by OpenAI: Structured outputs, Function calling, Prompt caching, Image input, PDF input, Reasoning / thinking, Built-in web search, temperature parameter, top_p parameter, logprobs.
Price history
USD per 1M tokens, standard tierWe started recording this model's prices on Oct 1, 2026. The history grows with each daily check.
Show as a table
| From | Type | Price |
|---|---|---|
| Oct 1, 2026 | Input | $0.50 |
| Oct 1, 2026 | Output | $1.50 |
Prices
USD per 1M tokens, every type and band, by tier| Type | Band | Price $/1M | In effect |
|---|---|---|---|
| Standard | |||
| input | short context | $0.50 | |
| output | short context | $1.50 | |
| Batch | |||
| input | short context | $0.25 | |
| output | short context | $0.75 | |
Changelog
Changes we detected on OpenAI's pagesNo changes recorded yet.
Counting to 8:00 pm ET on October 22, 2026, which is 00:00 UTC on October 23, 2026.
Email alerts
Get an email before gpt-3.5-turbo-0125 shuts down
We'll email you 30, 7 and 1 days before it shuts down, and the same morning if the shutdown date moves or the price changes.
No password: one email to confirm, and you can unsubscribe any time. Privacy
Last checked · Sources: OpenAI deprecations, OpenAI pricing, OpenAI models