# GPT-5.4 nano

GPT-5.4 nano is a text generation model from OpenAI, available through the Impossibl API. Its published context window is 400,000 tokens. The advertised input rate is $0.20 per million input tokens. The advertised output rate is $1.25 per million output tokens.

- Model identifier: ` openai/gpt-5.4-nano `
- Creator: OpenAI
- Model type: Text generation
- Canonical model page: [GPT-5.4 nano](<https://impossibl.com/openai/gpt-5.4-nano>)
- API availability: Listed as serving through Impossibl.
- Creator release date: 2026-03-17

## Capabilities and limits

- Context window: 400,000 tokens
- Maximum output tokens: Not published in the public catalog; this is separate from the context window.
- Inputs: text, image
- Outputs: text
- Tool calling: Not published

## API access

Use ` openai/gpt-5.4-nano ` as the model identifier through the Impossibl API.

Published API endpoints:

- ` /v1/chat/completions `

[API quickstart](<https://impossibl.com/docs/agent-quickstart>) · [Models and billing documentation](<https://impossibl.com/docs/models>)

## Published API prices

All rates are in USD. An unpublished rate is unknown, not zero. Workspace-specific pricing, taxes, balance-purchase fees, billing adjustments, and tool charges can affect the amount paid.

| Usage | Published base rate | Billing unit |
| --- | --- | --- |
| Input | $0.20 | per million input tokens |
| Output | $1.25 | per million output tokens |
| Cache read | $0.02 | per million cached input tokens |
| Cache write (default retention) | Not published | per million tokens |
| Cache write (one-hour retention) | Not published | per million tokens |
| Audio input | Not published | per million audio input tokens |

## Independent benchmarks

Source: [Artificial Analysis](<https://artificialanalysis.ai/>). Last checked: 2026-09-10T09:58:54.927Z.
Configurations are evaluated separately. API scores retain their original units. Unmeasured scores are omitted.

### GPT-5.4 nano (xhigh)

Source: [Evaluation source](<https://artificialanalysis.ai/models/gpt-5-4-nano>)

| Benchmark | Score |
| --- | --- |
| Intelligence Index | 21.24 |
| Omniscience Index | -29.47 |
| GPQA | 81.72% |
| Humanity’s Last Exam | 28.27% |
| SciCode | 47.22% |
| CritPt | 9.25% |
| Terminal-Bench v2.1 | 60.67% |
| Terminal-Bench v4.0 | 0.51% |
| Terminal-Bench Hard | 42.42% |
| AA-LCR | 76.67% |
| Multilingual LCR | 5.00% |
| Harvey LAB | 52.24% |
| GDPval Elo | 1035.42 |
| GDP.pdf All-pass | 7.80% |
| AutomationBench Partial | 5.96% |
| MMMU-Pro | 65.38% |
| IFBench | 75.92% |
| Tau2 | 76.02% |
| Tau Banking | 27.42% |
| APEX-Agents | 24.93% |
| ITBench | 24.39% |
| coding index (API) | 56.1 |
| agentic index (API) | 17.7 |
| intelligence index (API) | 21.2 |

### GPT-5.4 nano (medium)

Source: [Evaluation source](<https://artificialanalysis.ai/models/gpt-5-4-nano-medium>)

| Benchmark | Score |
| --- | --- |
| Intelligence Index | 20.01 |
| Omniscience Index | -18.03 |
| GPQA | 76.06% |
| Humanity’s Last Exam | 15.94% |
| CritPt | 5.14% |
| Terminal-Bench Hard | 33.33% |
| AA-LCR | 67.33% |
| MMMU-Pro | 59.54% |
| IFBench | 64.42% |
| Tau2 | 52.63% |
| intelligence index (API) | 20 |

### GPT-5.4 nano (Non-Reasoning)

Source: [Evaluation source](<https://artificialanalysis.ai/models/gpt-5-4-nano-non-reasoning>)

| Benchmark | Score |
| --- | --- |
| Intelligence Index | 11.69 |
| Omniscience Index | -37.48 |
| GPQA | 55.76% |
| Humanity’s Last Exam | 4.08% |
| CritPt | 0.00% |
| Terminal-Bench Hard | 24.24% |
| AA-LCR | 29.67% |
| GDPval Elo | 680.74 |
| MMMU-Pro | 43.76% |
| IFBench | 32.72% |
| Tau2 | 34.80% |
| ITBench | 12.91% |
| intelligence index (API) | 11.7 |

Full benchmark data and breakdowns: [Complete benchmark snapshot](<https://api.impossibl.com/v1/models/openai/gpt-5.4-nano/benchmarks>).


## Availability and retirement

The model is listed as serving. No retirement is announced in the current public catalog.

## Frequently asked questions

### What is GPT-5.4 nano?

GPT-5.4 nano is a text-generation model from OpenAI, available through the Impossibl API.

### How much does GPT-5.4 nano cost?

GPT-5.4 nano costs $0.20 per million input tokens and $1.25 per million output tokens through the Impossibl API. Cache reads cost $0.02 per million tokens. All rates are in USD.

### What is the context length of GPT-5.4 nano?

GPT-5.4 nano has a 400,000-token context window through the Impossibl API.

### What inputs and outputs does GPT-5.4 nano support?

GPT-5.4 nano accepts text and image as input. GPT-5.4 nano returns text.

### How do I use GPT-5.4 nano through an API?

GPT-5.4 nano is available through the Impossibl API. Use openai/gpt-5.4-nano as the model identifier with /v1/chat/completions. The quickstart explains how to create an API key and send your first request.

### When was GPT-5.4 nano released?

OpenAI released GPT-5.4 nano on March 17, 2026.

Sources: [Creator release announcement](<https://openai.com/index/introducing-gpt-5-4-mini-and-nano/>)

## Sources and related links

Prices, limits, capabilities, endpoints, and availability come from the public Impossibl catalog. Creator documentation supplies descriptions and release dates where available; it does not override the published API offering.

- [Public Impossibl model catalog](<https://api.impossibl.com/v1/models>)
- [Full model directory as JSON](<https://impossibl.com/models.json>)
- [GPT-5.4 nano: model details and pricing](<https://impossibl.com/openai/gpt-5.4-nano>)
- [Model directory](<https://impossibl.com/models>)