GPT-5.4

Name: GPT-5.4
Brand: OpenAI
SKU: gpt-5-4
Price: 3 USD
Availability: InStock

MultimodalNewAvailable

by OpenAIgpt-5-4

OpenAI's unified flagship combining GPT and o-series reasoning into one model. 1M context, multimodal, top SWE-Bench Pro and OSWorld scores.

Try it Get API key Compare

Price · 1M in / out: $3.00 / $18.00
Context: 1,050,000 tokens
Max. output: 128,000 tokens
Input → output: Text + Image → Text
Developer: OpenAI
Updated: September 23, 2026

Playground

Try GPT-5.4

Chat

$3.00/1M in

Send a message. The answer arrives in full once the model is done (no streaming).

System prompt

Max. answer length (tokens)

TemperatureModel default

⌘/Ctrl + Enter

This run

at most $0.0185 · 1.85 credits reserved

Billed by the tokens actually used; the unused part of the reservation is refunded.

New here?

10 free credits ($0.10) when you sign up with Google

Usable 24 hours after sign-up, up to 5 runs per day and at most 2 credits per run. Other sign-in methods start without credits. Enough for 5 runs of this model.

About GPT-5.4

TL;DRAs of September 23, 2026

GPT-5.4 is a model by OpenAI in the Multimodal category. On Railwail, GPT-5.4 costs $3.00 per 1M input tokens and $18.00 per 1M output tokens. The context window holds 1,050,000 tokens, and one response can be up to 128,000 tokens long.

GPT-5.4 is OpenAI's frontier model as of 2026, merging the previously separate GPT and o-series reasoning lines into a single unified architecture. Native multimodal input (text + images), 1.05M-token experimental context window (272K standard), 128K max output, integrated 'Thinking' tier for reasoning on demand. Best for: high-context coding, agentic engineering, multimodal analysis, complex tool-use workflows. The Codex line has been absorbed into this model.

Background

About OpenAI

Founded 2015 · San Francisco, USA

OpenAI was founded in December 2015 by Sam Altman, Elon Musk, Greg Brockman, Ilya Sutskever, Wojciech Zaremba and John Schulman as a non-profit AI research organisation; it transitioned to a 'capped-profit' structure in 2019. OpenAI authored the GPT lineage starting with GPT-1 (2018), GPT-2 (2019), GPT-3 (2020), the ChatGPT launch with GPT-3.5 (November 2022), GPT-4 (March 2023), GPT-4o (May 2024), the o-series reasoning models o1 (December 2024) and o3 (early 2025), then GPT-5 (mid-2025). The GPT-5.x series unified the reasoning o-series with the general-purpose GPT line: GPT-5.2 shipped December 2025, GPT-5.3-Codex February 2026, GPT-5.4 in March 2026 and the GPT-5.5 family later in 2026. OpenAI's investors include Microsoft (~$13B+), Khosla Ventures, Andreessen Horowitz, Thrive Capital and Sequoia, with total funding exceeding $60 billion and a 2026 valuation above $300 billion.

Visit OpenAI

Architecture

Unified Transformer with integrated reasoning ('Thinking') tier

GPT-5.4 is OpenAI's frontier model as of March 2026 and marks the full convergence of the previously separate o-series reasoning models and general-purpose GPT line into a single unified architecture. The o1, o3, o3-pro and o4-mini reasoning models were retired from ChatGPT on February 13, 2026; their capabilities are now folded into GPT-5.x as a 'Thinking' tier that activates on demand. GPT-5.4 also absorbs the Codex line for agentic coding. Pretraining used a multi-trillion-token mixture of web text, code repositories, scientific papers, books and licensed datasets on OpenAI's most recent supercomputer cluster. Post-training combined supervised fine-tuning, RLHF and large-scale reinforcement learning against verifiable rewards on coding, math and tool-use trajectories. The model supports native text + image input and a 1.05M-token experimental context window (272K standard), 128K max output, integrated tool-use, function calling, structured outputs, and built-in 'Tool Search' for delegating to subagents. Safety training followed OpenAI's Preparedness Framework with red-teaming, capability evaluations and external assessments.

Parameters: Undisclosed (estimated multi-hundred billion parameters, likely sparse MoE)
Context: 1,050,000 tokens

Capabilities

Unified GPT and o-series: integrated 'Thinking' tier activates on demand
1.05M-token experimental context window (272K standard, 128K max output)
Native multimodal input: text and images in a single pass
Top scores on SWE-Bench Pro and OSWorld-Verified at launch
Native tool use, function calling, parallel tool calls and structured outputs
Integrated 'Tool Search' for delegating to subagent models
Absorbed Codex agentic coding capabilities
Strong multilingual performance and instruction following
Available via OpenAI API, Azure OpenAI, ChatGPT and Codex CLI
Regional processing (data residency) endpoints available with 10% uplift
Best for: high-context coding, agentic engineering, multimodal analysis, complex tool-use workflows.

Training & license

Pretrained on a multi-trillion-token mixture of web text, code, scientific papers, books and licensed datasets. Post-training combines supervised fine-tuning, RLHF and large-scale reinforcement learning against verifiable rewards on coding, math and tool-use tasks. Knowledge cutoff approximately late 2025.

License: Proprietary commercial license via OpenAI API and Azure OpenAI. Commercial use permitted under OpenAI's Usage Policies.

Safety testing: Evaluated under OpenAI's Preparedness Framework with internal and external red-teaming, capability evaluations and a public Bug Bounty programme.

Known limitations

1M context is experimental and must be enabled explicitly (default is 272K)
Prompts above 272K input tokens are billed at 2x input / 1.5x output for the full session
No native audio or video input in this variant
Higher latency and cost than mini/nano tiers, especially with Thinking enabled
Knowledge cutoff in late 2025

Research papers

Pricing

Prices in US dollars. Usage is charged from prepaid credits.

Input	$3.00 / 1M tokens
Output	$18.00 / 1M tokens
Input (prompts over 272,000 tokens)	$6.00 / 1M tokens
Output (prompts over 272,000 tokens)	$27.00 / 1M tokens

Billed by the tokens each request actually uses.
1 credit = $0.01

Cost calculator

Price calculator

Input tokens

/ req.

Output tokens

/ req.

Requests

Total

$1.20

120 credits

Per request

$0.012 · 1.2 credits

Each request is rounded up to 0.01 credits.

API

Call GPT-5.4 with your Railwail API key. Use this model ID in the request:

gpt-5-4API documentation Get an API key

curl https://railwail.com/api/v1/chat/completions \
  -H "Authorization: Bearer $RAILWAIL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5-4",
    "messages": [
      {
        "role": "user",
        "content": "Explain what a vector database is in two sentences."
      }
    ],
    "max_tokens": 1024
  }'

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["RAILWAIL_API_KEY"],
    base_url="https://railwail.com/api/v1",
)

completion = client.chat.completions.create(
    model="gpt-5-4",
    messages=[
        {
            "role": "user",
            "content": "Explain what a vector database is in two sentences.",
        },
    ],
    max_tokens=1024,
)

print(completion.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.RAILWAIL_API_KEY,
  baseURL: "https://railwail.com/api/v1",
});

const completion = await client.chat.completions.create({
  model: "gpt-5-4",
  messages: [
    {
      role: "user",
      content: "Explain what a vector database is in two sentences."
    }
  ],
  max_tokens: 1024
});

console.log(completion.choices[0].message.content);

// npm install railwail
import railwail from "railwail";

const rw = railwail(process.env.RAILWAIL_API_KEY);

const res = await rw.chat("gpt-5-4", [
  { role: "user", content: "Explain what a vector database is in two sentences." },
], { max_tokens: 1024 });

console.log(res.choices[0].message.content);

Set your key as RAILWAIL_API_KEYCreate API key

Specifications

Model ID: gpt-5-4
Developer: OpenAI
Category: Multimodal
Input: Text, Image
Output: Text
Context window: 1,050,000 tokens
Max. output: 128,000 tokens
Billing: By usage (tokens or GPU time)
Model size: Undisclosed (estimated multi-hundred billion parameters, likely sparse MoE)
License: Proprietary commercial license via OpenAI API and Azure OpenAI. Commercial use permitted under OpenAI's Usage Policies.
Catalog entry updated: September 23, 2026

Input parameters

Inputs and settings from the model's input schema. The example in the API section shows which of them the API accepts.

ParameterTypeDefaultAllowed values

promptrequired
User message
Type: Text
Default: –
Allowed values: up to 32,000 characters
top_p
Type: Number
Default: 1
Allowed values: 0 to 1
stream
Type: Yes/no
Default: false
Allowed values: –
image_url
Optional image URL to analyze
Type: Text
Default: –
Allowed values: –
max_tokens
Type: Integer
Default: 4096
Allowed values: 1 to 32,000
temperature
Type: Number
Default: 1
Allowed values: 0 to 2
system_prompt
Optional system instruction
Type: Text
Default: –
Allowed values: up to 8,000 characters

Use cases

What it is used for

Frontier coding agents and IDE copilots
Long-context document and codebase analysis
Agentic engineering with Tool Search and subagents
Scientific and quantitative reasoning
Multimodal analysis of diagrams and screenshots
Enterprise copilots and customer-facing assistants

All models in Multimodal

Frequently asked questions

What is GPT-5.4?

GPT-5.4 is a model by OpenAI in the Multimodal category. On Railwail you can call it with an API key through the Railwail API.

How much does GPT-5.4 cost on Railwail?

On Railwail, GPT-5.4 costs $3.00 per 1M input tokens and $18.00 per 1M output tokens. You are charged for what each request actually uses. Usage is paid from prepaid credits; 1 credit equals $0.01.

What is the context window of GPT-5.4?

The context window of GPT-5.4 holds 1,050,000 tokens. One response can be up to 128,000 tokens long.

How fast is GPT-5.4?

There are not enough measured runs of GPT-5.4 on Railwail yet to state a run time. It depends on the input, the settings and the load at the provider.

Is GPT-5.4 better than BLIP?

That depends on the task. GPT-5.4 (OpenAI) and BLIP (Salesforce) are both models in the Multimodal category. The comparison page shows their prices and specifications side by side.

Compare GPT-5.4 and BLIP

Can GPT-5.4 process images?

Yes. GPT-5.4 accepts images as input in addition to text.

How do I use GPT-5.4 through the API?

Create a Railwail API key and send your request with the model ID gpt-5-4. Code examples for curl, Python and JavaScript are in the API section of this page.

Comparable models

All in this category

Claude Opus 4.7Anthropic
Anthropic's April 2026 flagship. 87.6% on SWE-bench Verified, 3x higher image resolution, output self-verification, vision + reasoning.
$6.00/1M in
100 % more expensive per unit
Compare GPT-5.4 vs. Claude Opus 4.7
Claude Sonnet 4.6Anthropic
Anthropic's balanced mid-tier model from February 2026. Best price/performance for production workloads: 5x cheaper than Opus, near-flagship quality.
$3.60/1M in
20 % more expensive per unit
Compare GPT-5.4 vs. Claude Sonnet 4.6
Gemini 3 FlashGoogle DeepMind
Google's April 2026 fast multimodal model. Combines Gemini 3 Pro's reasoning with Flash-tier latency and price. Default model in the Gemini app.
$0.60/1M in
80 % cheaper per unit
Compare GPT-5.4 vs. Gemini 3 Flash

Use GPT-5.4 via the API

One API key for every model on Railwail. Usage is charged from prepaid credits, 1 credit = $0.01.

Get API key Browse all models