AI Model Watch
Models / OpenAI

GPT-4

Retired

gpt-4-0613, including the gpt-4 alias and the gpt-4-0613-completions and gpt-4-completions aliases, was shut down on 2026-10-23 and OpenAI names gpt-5.6-sol as the replacement. Until 2026-10-24 the row was held at deprecated on OpenAI's own deprecations page, section '2026-04-22: Legacy GPT model snapshots', which stated the shutdown date and the recommended replacement as columns of a table; the date passing on 2026-10-23 was not treated as evidence on its own. Rates read the same day from developers.openai.com/api/docs/pricing (Standard tier), which priced deprecated models; on the 2026-10-24 read the pricing page's own data payload still carries these same rates, so they are kept as the last published ones. Standard-tier rates: input $30.00, output $60.00 per 1M, with no cached-input rate published. Specs are from developers.openai.com/api/docs/models/gpt-4: 8,192 context window, 8,192 max output tokens, knowledge cutoff Dec 01, 2023, text only in and out. released is null on purpose: the snapshot id encodes 06-13 with no year, and OpenAI publishes no release date for it on either surface, so dating it would mean supplying the year ourselves. A fine-tuned variant, ft-gpt-4, carries the same shutdown date and is not covered by this row. THE DELAY IS OURS, NOT A PROVIDER EVENT: the announcement, the date and the replacement are all OpenAI's, published 2026-04-22; this catalog simply never carried the row. It was added 2026-09-21, 32 days before the shutdown. CONFIRMED RETIRED 2026-10-24. Signal (first-party, past tense): the same section of developers.openai.com/api/docs/deprecations now states "Access to these models was shut down on October 23, 2026." and lists gpt-4-0613 | gpt-4, gpt-4-0613-completions, gpt-4-completions in its table with substitute gpt-5.6-sol - an executed shutdown, not a scheduled one. The substitute is unchanged.

GPT-4 by OpenAI costs $30 per 1M input tokens and $60 per 1M output tokens ($37.50/1M blended), with a 8K (8192-token) context window. It has been retired (shut down 23 Oct 2026); the recommended migration is GPT-5.6 Sol.

Last verified: 24 Oct 2026 · sourced from official provider documentation

Retired on 23 Oct 2026 · deprecated since 22 Apr 2026

Lifecycle warning

This model has been retired. Recommended migration: GPT-5.6 Sol.

Read the GPT-4 migration guide → replacement & cheapest alternatives

Provider
OpenAI
Status
Retired
Input price
$30 / 1M tokens
Output price
$60 / 1M tokens
Cached input
—
Blended price
$37.50 / 1M tokens
Context window
8192 tokens (8K)
Max output
8192 tokens
Modality
text
Open weights
No — API only
Knowledge cutoff
2023-12-01
Released
—
API string
gpt-4-0613

Source: OpenAI official documentation ↗

See also

Explore more

All OpenAI models→

Prices, context windows and lifecycle status for every OpenAI model we track.

Compare models head-to-head→

Side-by-side price, context and status for the models developers weigh against each other.

FAQ

GPT-4 — questions & answers

How much does GPT-4 cost?

GPT-4 is priced at $30 per 1M input tokens and $60 per 1M output tokens ($37.50/1M blended at a 3:1 input-to-output ratio).

What is the context window of GPT-4?

GPT-4 has a 8192-token context window (8K), with up to 8192 output tokens per request.

Is GPT-4 still available?

GPT-4 has been retired and is no longer available. Its scheduled shutdown date is 23 Oct 2026. The recommended migration is GPT-5.6 Sol.

Does GPT-4 support image or vision input?

Our catalog lists GPT-4's modalities as text; image/vision input is not among them.

Can I self-host GPT-4?

No — GPT-4 is proprietary. Its weights are not publicly released, so it is available only through OpenAI's API (or hosted partners), not for self-hosting.

What is the API model string for GPT-4?

The API model identifier for GPT-4 is "gpt-4-0613" when calling OpenAI's API.

What is GPT-4's knowledge cutoff?

GPT-4's training knowledge cutoff is 1 Dec 2023.