AI Model Watch
Models / OpenAI

GPT-4.1 nano

Deprecated

The gpt-4.1-nano alias and its gpt-4.1-nano-2025-04-14 snapshot shut down 2026-10-23, and OpenAI names gpt-5.6-luna as the replacement. Signal used: OpenAI's own deprecations page, section '2026-04-22: Legacy GPT model snapshots', which states the shutdown date and the recommended replacement as columns of a table. Rates read the same day from developers.openai.com/api/docs/pricing (Standard tier), which still prices deprecated models. Standard-tier rates: input $0.10, cached input $0.025, output $0.40 per 1M. Its stated replacement gpt-5.6-luna carries twice this input rate and three times this output rate on the same table, so the migration OpenAI recommends is not a like-for-like price; the figures are on gpt-5.6-luna's own row in this catalog. Specs are from developers.openai.com/api/docs/models/gpt-4.1-nano: 1,047,576 context window, 32,768 max output tokens, knowledge cutoff Jun 01, 2024, text and image in, text out. OpenAI lists a fine-tuned variant, ft-gpt-4.1-nano-2025-04-14, under the same shutdown date; this row does not cover it. The sibling rows gpt-4.1 and gpt-4.1-mini are priced by OpenAI but appear in no deprecation table and are not carried yet. 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.

GPT-4.1 nano by OpenAI costs $0.1 per 1M input tokens and $0.4 per 1M output tokens ($0.175/1M blended), with a 1.0M (1.047.576-token) context window. It is deprecated, shutting down 23 Oct 2026; the recommended replacement is GPT-5.6 Luna.

Last verified: 26 Sep 2026 · sourced from official provider documentation

Retires on 23 Oct 2026 · deprecated since 22 Apr 2026

Lifecycle warning

This model is deprecated. Recommended migration: GPT-5.6 Luna.

Read the GPT-4.1 nano migration guide → replacement & cheapest alternatives

Provider
OpenAI
Status
Deprecated
Input price
$0.1 / 1M tokens
Output price
$0.4 / 1M tokens
Cached input
$0.025 / 1M tokens
Blended price
$0.175 / 1M tokens
Context window
1.047.576 tokens (1.0M)
Max output
32.768 tokens
Modality
text, image
Open weights
No — API only
Knowledge cutoff
2024-06-01
Released
14 Apr 2025
API string
gpt-4.1-nano-2025-04-14

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-4.1 nano — questions & answers

How much does GPT-4.1 nano cost?

GPT-4.1 nano is priced at $0.1 per 1M input tokens and $0.4 per 1M output tokens ($0.175/1M blended at a 3:1 input-to-output ratio), with cached input at $0.025 per 1M tokens.

What is the context window of GPT-4.1 nano?

GPT-4.1 nano has a 1.047.576-token context window (1.0M), with up to 32.768 output tokens per request.

Is GPT-4.1 nano being deprecated or retired?

GPT-4.1 nano is deprecated. Its scheduled shutdown date is 23 Oct 2026. The recommended migration is GPT-5.6 Luna.

Does GPT-4.1 nano support image or vision input?

Yes — GPT-4.1 nano accepts image input. Listed modalities: text, image.

Can I self-host GPT-4.1 nano?

No — GPT-4.1 nano 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-4.1 nano?

The API model identifier for GPT-4.1 nano is "gpt-4.1-nano-2025-04-14" when calling OpenAI's API.

What is GPT-4.1 nano's knowledge cutoff?

GPT-4.1 nano's training knowledge cutoff is 1 Jun 2024.