---
title: "GPT-5.4"
description: "GPT-5.4 by OpenAI: 1.05M context. Compare provider prices and applicable pricing conditions on the model page. Pay as you go."
canonical: https://pirouter.ai/models/openai/gpt-5.4
last-updated: 2026-10-15
---

# GPT-5.4

> GPT-5.4 by OpenAI: 1.05M context. Compare provider prices and applicable pricing conditions on the model page. Pay as you go.

GPT-5.4 is the flagship of OpenAI's GPT-5.4 family, aimed at complex coding and professional work one step below GPT-5.5. It accepts text and image input with a 1.05M-token context, 128K output, and reasoning effort from none to xhigh.

## At a glance

- Model ID: `openai/gpt-5.4`
- Also accepted as: `gpt-5.4`
- Vendor: OpenAI
- Category: text
- Openness: Proprietary
- Model page: https://developers.openai.com/api/docs/models/gpt-5.4
- Context: 1,050,000 tokens
- Max output: 128,000 tokens
- Added to pirouter: 2026-03-05
- Knowledge cutoff: 2025-08-31
- Status: Available

## Pricing (USD per 1M tokens)

|  | Input | Output | Cache read | Cache write | Reasoning |
|---|---|---|---|---|---|
| < 272,000 | $1.75 ~~$2.5~~ | $10.5 ~~$15~~ | $0.175 ~~$0.25~~ | $2.1875 ~~$3.125~~ | $10.5 ~~$15~~ |
| ≥ 272,000 | $3.5 ~~$5~~ | $15.75 ~~$22.5~~ | $0.35 ~~$0.5~~ | $4.375 ~~$6.25~~ | $15.75 ~~$22.5~~ |

30% off for a limited time · Ends 2026-10-31 23:59 HKT · Same price on every provider · this is what you are billed.

## Capabilities

- Function calling
- Tool choice
- Parallel tool calls
- Structured outputs
- Response schema
- Reasoning
- Prompt caching
- System messages
- Streaming
- Vision
- PDF input

## Reasoning effort

- xhigh, high, medium, low, minimal, none (default: none)

## How to call it

One pirouter API key works with every API format below; create it in the console. Use one of these formats; formats not listed are not available for this model.

- API key: https://app.pirouter.ai/sign-in

### OpenAI Responses

- Endpoint: `POST /v1/responses` on https://api.pirouter.ai
- Auth: `Authorization: Bearer <key>`
- SDK base URL: https://api.pirouter.ai/v1
- Reference: https://pirouter.ai/docs/api/responses

```bash
curl https://api.pirouter.ai/v1/responses \
  -H "Authorization: Bearer $PIROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-5.4",
    "input": "Hello!"
  }'
```

### OpenAI Chat

- Endpoint: `POST /v1/chat/completions` on https://api.pirouter.ai
- Auth: `Authorization: Bearer <key>`
- SDK base URL: https://api.pirouter.ai/v1
- Reference: https://pirouter.ai/docs/api/chat-completions

```bash
curl https://api.pirouter.ai/v1/chat/completions \
  -H "Authorization: Bearer $PIROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-5.4",
    "messages": [{ "role": "user", "content": "Hello!" }]
  }'
```

## Providers

One row per provider; pirouter sends each request to a healthy one.

| Provider | API format | Context | Max output | Input /M | Output /M | Trains on your data | Data retention |
|---|---|---|---|---|---|---|---|
| azure | openai | 1,050,000 | 128,000 | $1.75 ~~$2.5~~ | $10.5 ~~$15~~ | No | Limited |

## Rankings

Where this model ranks on each blind-vote leaderboard, listing the boards where it makes the top 100. Open a board for the full ranking.

| Board | Rank | Score |
|---|---|---|
| [Overall](https://pirouter.ai/rankings/overall) | #28 / 385 | 1475 |
| [Coding](https://pirouter.ai/rankings/coding) | #30 / 380 | 1521 |
| [Math](https://pirouter.ai/rankings/math) | #21 / 371 | 1491 |
| [Creative writing](https://pirouter.ai/rankings/creative) | #46 / 383 | 1442 |
| [Instruction following](https://pirouter.ai/rankings/instruct) | #29 / 385 | 1471 |
| [Multi-turn](https://pirouter.ai/rankings/multiturn) | #16 / 383 | 1493 |
| [Long prompts](https://pirouter.ai/rankings/longctx) | #36 / 363 | 1481 |
| [Chinese](https://pirouter.ai/rankings/chinese) | #40 / 362 | 1507 |
| [Web dev](https://pirouter.ai/rankings/webdev) | #55 / 121 | 1465 |
| [Agents](https://pirouter.ai/rankings/agent) | #25 / 44 | +0.9 pp |
| [Vision](https://pirouter.ai/rankings/vision) | #18 / 144 | 1284 |
| [Documents](https://pirouter.ai/rankings/document) | #14 / 38 | 1470 |

Data: [LMArena leaderboard dataset](https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset), used under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) · Updated 2026-10-01

## Supported parameters

`tools`, `tool_choice`, `parallel_tool_calls`, `response_format`, `structured_outputs`, `max_tokens`, `max_completion_tokens`, `seed`, `reasoning`, `include_reasoning`, `stream`, `n`, `verbosity`

## Links

- HTML: https://pirouter.ai/models/openai/gpt-5.4
- JSON: https://pirouter.ai/api/models/openai/gpt-5.4
- Providers JSON: https://api.pirouter.ai/v1/models/openai/gpt-5.4/endpoints
- Leaderboard ranks (JSON): https://pirouter.ai/api/models/openai/gpt-5.4/rankings
- Catalog: https://pirouter.ai/models
- Quickstart: https://pirouter.ai/docs/quickstart
- How routing works: https://pirouter.ai/docs/routing
- llms.txt: https://pirouter.ai/llms.txt

---

HTML version: https://pirouter.ai/models/openai/gpt-5.4 · Machine-readable index: https://pirouter.ai/llms.txt