All times Eastern (ET)Provider pages checked daily at
ProSign inRSS

GPT-4 0125 Preview

API ID gpt-4-0125-preview

gpt-4-0125-preview was a preview OpenAI model. It had a 128,000-token context window and up to 4,096 output tokens.

Status
Retired
Released
—
Shutdown
Mar 26, 2026
Replacement
GPT-5gpt-5

gpt-4-0125-preview stopped serving on March 26, 2026. Recommended replacement: gpt-5.

How to migrate to GPT-5

Benchmarks

Scores as each source published them
or

Comparing with GPT-4 1106 Preview, 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

ArenaGPT-4 0125 PreviewGPT-4 1106 PreviewChangeRankDateSource
Text
By category
  • Math 1299 rank 250 vs 1303 (−4, within range)
  • Creative writing 1280 rank 264 vs 1286 (−6, within range)
  • Instruction following 1290 rank 276 vs 1296 (−6, within range)
  • Hard prompts 1307 rank 284 vs 1313 (−6, within range)
  • Long prompts 1309 rank 276 vs 1303 (+6, within range)
  • Multi-turn 1292 rank 277 vs 1299 (−7, within range)
  • Expert 1281 rank 279 vs 1290 (−9, within range)
1313 ±41313 ±40
within range		271 of 415
93,439 votes		Oct 13, 2026source
Text: Coding1332 ±81340 ±7−8
within range		286 of 410
15,289 votes		Oct 13, 2026source

Rated as gpt-4-0125-preview; GPT-4 1106 Preview as gpt-4-1106-preview. 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

BenchmarkGPT-4 0125 PreviewGPT-4 1106 PreviewChangeSettingRunSource
GPQA Diamond42.3%42.4%−0.1 ptsJan 27, 2025source
MATH Level 535.4%40.0%−4.6 ptsJan 27, 2025source

Run independently by Epoch AI. Data: Epoch AI, Capabilities & benchmarking (epoch.ai/benchmarks), CC BY.

Aliases pointing here: gpt-4-turbo-preview (in place when tracking began (October 7, 2026))

Features

Compare models
FeatureValueSinceSource
Batch APISend many requests as one job that runs in the background, usually finished within 24 hours, at a lower price than live requests.Not supportedin 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.Not supportedin 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.128,000 tokensin 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 tokensin 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 tier

No price history yet.

Prices

USD per 1M tokens, every type and band, by tier

No published prices.

Changelog

Changes we detected on OpenAI's pages

No changes recorded yet.

Last checked · Sources: OpenAI deprecations, OpenAI pricing, OpenAI models