All times Eastern (ET)Provider pages checked daily at

GPT-4 (0613)

API ID gpt-4-0613

gpt-4-0613 is an OpenAI model. It has a 8,192-token context window and up to 8,192 output tokens. Standard price: from $30.00 input and from $60.00 output per 1M tokens.

Status
Deprecated
Released
—
Shutdown
Oct 23, 2026

It stops serving on October 23, 2026. Recommended replacement: gpt-5.6-sol.

How to migrate to GPT-5.6 Sol

Benchmarks

Scores as each source published them
or

Comparing with GPT-4 (0314), 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 (0613)GPT-4 (0314)ChangeRankDateSource
Text
By category
  • Math 1277 rank 274 vs 1284 (−7, within range)
  • Creative writing 1267 rank 279 vs 1255 (+12, within range)
  • Instruction following 1277 rank 290 vs 1285 (−8, within range)
  • Hard prompts 1290 rank 295 vs 1306 (−16)
  • Long prompts 1281 rank 302 vs 1280 (+1, within range)
  • Multi-turn 1262 rank 303 vs 1274 (−12, within range)
  • Expert 1254 rank 299 vs 1265 (−11, within range)
1276 ±41288 ±5−12306 of 415
88,723 votes
Oct 13, 2026source
Text: Coding1315 ±81330 ±9−15
within range
296 of 410
13,719 votes
Oct 13, 2026source

Rated as gpt-4-0613; GPT-4 (0314) as gpt-4-0314. 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 (0613)GPT-4 (0314)ChangeSettingRunSource
GPQA Diamond30.7%35.7%−5.0 ptsJan 27, 2025source
MATH Level 523.0%not runJan 27, 2025source
OTIS Mock AIME 2024-20251.1%0.6%+0.5 ptsOct 23, 2025source

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

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

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.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.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.8,192 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.8,192 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
$0.00$20.00$40.00$60.00$80.00Oct 2026In $30.00Out $60.00Oct 1, 2026 to Oct 15, 2026: Input $30.00, Output $60.00
$0.00$20.00$40.00$60.00$80.00Oct 2026In $30.00Out $60.00Oct 1, 2026 to Oct 15, 2026: Input $30.00, Output $60.00

We started recording this model's prices on Oct 1, 2026. The history grows with each daily check.

Show as a table
FromTypePrice
Oct 1, 2026Input$30.00
Oct 1, 2026Output$60.00

Prices

USD per 1M tokens, every type and band, by tier
TypeBandPrice $/1MIn effect
Standard
inputshort context$30.00
outputshort context$60.00
Batch
inputshort context$15.00
outputshort context$30.00

Changelog

Changes we detected on OpenAI's pages

No changes recorded yet.

Time until shutdown
7days
11hours
26min
02sec

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-4-0613 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