GPT-5.4 nano
openai The API that serves this model and sets the prices shown here. gpt-5.4-nano The model identifier to send in API requests. LLM Generates text from a prompt, so it can be compared with other LLMs on price and capability. Small The fast, low-latency tier of a model family, suited to high-volume or simple tasks. Retiring Apr 01, 2027 This model is scheduled to retire on this date.Provider: openai
Knowledge cutoff: August 2025
Deprecated on 2026-10-01. Scheduled for shutdown April 1, 2027. Replacement: gpt-6-luna.
Sticker prices & cost-per-token
List rates as published by openai, before any volume or enterprise discounts.
$0.20
$1.25
400,000 tokens
128,000
tokens per response (includes reasoning tokens)
Closed weights
$0.02
Get this data free
Want to stay updated on price changes on this model? Pull this data free (no API key required) here:
curl "https://coolhandlabs.com/api/v2/inference_apis?q%5Bmodel_eq%5D=gpt-5.4-nano&q%5Bsource_api_eq%5D=openai"Pricing History
| Effective | Price |
|---|---|
| Aug 16, 2026 – present | Input cost: $0.20 / 1M, Output cost: $1.25 / 1M, Cached input cost: $0.02 / 1M, Cache creation cost: $0.00 / 1M, 5-minute cache write cost: $0.00 / 1M, 1-hour cache write cost: $0.00 / 1M, Reasoning output cost: $0.00 / 1M, Cache storage cost: $0.00 / 1M/hr |
History
Last change detected October 12, 2026 (14 days ago) by an automated scan.
| Date | Changed by | What changed |
|---|---|---|
| Aug 16, 2026 | Unknown | Initial record created |
Source
https://models.dev/api.json (models.dev provider 'openai', bulk import 2026-08-13)Comparable models
No comparable models identified yet.
Reliability
No reliability incidents recorded in the last 90 days.
Frequently asked questions
GPT-5.4 nano (openai) costs $0.20 per 1M input tokens and $1.25 per 1M output tokens, as last published by openai.
GPT-5.4 nano has a context window of 400,000 tokens (the maximum combined input and output it can handle in a single request).
GPT-5.4 nano sits in the small size tier. Size tiers run from micro (small enough to run on a device) through small, medium and large to extra large (frontier flagships), and are assigned from the model's family, naming and limits rather than its price.
GPT-5.4 nano can generate up to 128,000 tokens in a single response. Reasoning (thinking) tokens count toward this limit.
GPT-5.4 nano's training data runs through August 2025, so it may not know about later events. Coolhand records the cutoff at month precision, since providers often publish only the month.
GPT-5.4 nano accepts image and text as input and produces text as output, as recorded in the Coolhand catalog.
No — the weights of GPT-5.4 nano have not been released, so it is only available through hosted APIs.
Not yet — openai has announced GPT-5.4 nano will be deprecated on April 1, 2027. Deprecated on 2026-10-01. Scheduled for shutdown April 1, 2027. Replacement: gpt-6-luna.
openai is retiring GPT-5.4 nano on April 1, 2027.
Since GPT-5.4 nano is deprecated, openai customers are moving to GPT-4, GPT-Image-2, and o1 Mini.
Call GET https://coolhandlabs.com/api/v2/inference_apis?q[source_api_eq]=openai&q[model_eq]=gpt-5.4-nano — free, no API key required, and scoped to just this model since source_api and model together are unique. See https://coolhandlabs.com/docs for the full REST API reference.
Coolhand also tracks GPT-4, GPT-3.5 Turbo 0125, GPT-3.5 Turbo 1106, GPT-3.5 Turbo Instruct, GPT-4 Turbo Vision, and GPT-4 from openai. Some may already be deprecated, so check each model's status alongside its current pricing.
| Model | Input cost | Output cost | Context window | Max output tokens | Status |
|---|---|---|---|---|---|
| GPT-4 | $30.00/1M $0.0000300000 | $60.00/1M $0.0000600000 | 8,192 | 8,192 |
Deprecated Oct 23, 2026
|
| GPT-3.5 Turbo 0125 via Azure | $0.50/1M $0.0000005000 | $1.50/1M $0.0000015000 | 16,384 | 16,384 |
Deprecated Aug 13, 2026
|
| GPT-3.5 Turbo 1106 via Azure | $1.00/1M $0.0000010000 | $2.00/1M $0.0000020000 | 16,384 | 16,384 |
Deprecated Aug 13, 2026
|
| GPT-3.5 Turbo Instruct via Azure | $1.50/1M $0.0000015000 | $2.00/1M $0.0000020000 | 4,096 | 4,096 |
Deprecated Aug 13, 2026
|
| GPT-4 Turbo Vision via Azure | $10.00/1M $0.0000100000 | $30.00/1M $0.0000300000 | 128,000 | 4,096 |
Deprecated Aug 13, 2026
|
| GPT-4 via Azure | $30.00/1M $0.0000300000 | $60.00/1M $0.0000600000 | — | — | Active |
Track LLM pricing and deprecations automatically.
Start free