GPT-5.4 nano

Q: What is the API model name for GPT-5.4 nano?

Use gpt-5.4-nano in API calls to OpenAI. The context window is 400K tokens, and a response can run to 128,000 output tokens.

GPT-5.4 nano API pricing is $0.20 per million input tokens and $1.25 per million output tokens.

Provider: OpenAI
API model name: gpt-5.4-nano
Status: Deprecated
Input, $ per 1M tokens: $0.20
Cached input, $ per 1M tokens: $0.02
Output, $ per 1M tokens: $1.25
Sample request (10K in, 2K out), $: $0.0045
Context window, tokens: 400K
Price checked on: October 27, 2026
Official pricing page: developers.openai.com

These are standard rates on OpenAI’s own API. Cached input is billed at $0.02 per million tokens. A request with 10,000 input tokens and 2,000 output tokens costs about $0.0045 before caching or batch discounts. The API model name is gpt-5.4-nano, and the context window is 400K tokens. OpenAI’s current GPT-6 Luna runs the same request for about $0.002.

Max output, tokens: 128K
Input types: Text, image, file
Open weights: No
Pricing notes: OpenAI deprecated gpt-5.4-nano on October 1, 2026 and will remove it from the API on April 1, 2027. The recommended replacement is gpt-6-luna.
Sources: Page URL Checked
OpenAI API pricing https://developers.openai.com/api/docs/pricing 2026-10-21
OpenAI GPT-5.4 nano model page (prices) https://developers.openai.com/api/docs/models/gpt-5.4-nano 2026-10-02
OpenAI deprecations https://developers.openai.com/api/docs/deprecations 2026-10-02
OpenRouter model listing (context and output limits) https://openrouter.ai/models 2026-09-29

Page	URL	Checked
OpenAI API pricing	https://developers.openai.com/api/docs/pricing	2026-10-21
OpenAI GPT-5.4 nano model page (prices)	https://developers.openai.com/api/docs/models/gpt-5.4-nano	2026-10-02
OpenAI deprecations	https://developers.openai.com/api/docs/deprecations	2026-10-02
OpenRouter model listing (context and output limits)	https://openrouter.ai/models	2026-09-29

Price changes for this model

Effective	Change	Was	Now	Official source
October 1, 2026	Deprecation	Available: $0.20 input, $0.02 cached input, $1.25 output per 1M tokens	Deprecated; gpt-5.4-nano shuts down April 1, 2027 (replacement: gpt-6-luna at $0.10 input, $0.50 output per 1M tokens)	developers.openai.com

Questions

How much does the GPT-5.4 nano API cost?

GPT-5.4 nano costs $0.20 per million input tokens and $1.25 per million output tokens on OpenAI’s own API. Cached input costs $0.02 per million tokens.

What is the API model name for GPT-5.4 nano?

Use gpt-5.4-nano in API calls to OpenAI. The context window is 400K tokens, and a response can run to 128,000 output tokens.

What does one GPT-5.4 nano request cost?

A request with 10,000 input tokens and 2,000 output tokens costs about $0.0045 at standard rates, before caching or batch discounts.

Is GPT-5.4 nano still available?

OpenAI deprecated gpt-5.4-nano on October 1, 2026 and will remove it from the API on April 1, 2027. The recommended replacement is gpt-6-luna.

Sources

Prices are read from each provider’s official pricing page: OpenAI, Anthropic, Google Gemini API, xAI, DeepSeek and Mistral AI. Context and output limits that a provider does not publish come from OpenRouter’s model listing. Each model’s Sources field lists the pages used and the date each was checked. How we check prices · Price change log