OpenAI · Model guide

GPT-5.4

Q: What is GPT-5.4?

GPT-5.4 is available on CrossModel as openai/gpt-5.4. It has a 1M-token context window and can return up to 128K tokens per request.

Q: How much does GPT-5.4 cost?

Currently $ 2.50 per 1M input tokens and $ 15.00 per 1M output tokens. Cached input is billed at $ 0.25 per 1M.

Q: Does GPT-5.4 support tool calling and structured output?

Tool calling: Supported · Structured output (JSON): Supported · Image input: Supported · Streaming: Supported · Thinking mode: Supported

Q: Which endpoint do I call?

For text models, OpenAI Chat Completions (/v1/chat/completions), OpenAI Responses (/v1/responses) and Anthropic Messages (/v1/messages) all work — pick whichever your SDK already speaks.

Q: Can I try it without writing code?

Yes. Sign in and open the Playground on this page to chat with the model directly — no API key needed. Usage is billed from your wallet at the normal rate.

Compare

openai/gpt-5.4

The main GPT-5.4 model combines strong coding, professional knowledge work, visual understanding and native computer use. Its 1.05M-token context is useful for long-running agents and large document or repository workloads.

Modalities

Context

Max output

128K

Price / 1M tokens

$ 2.50in$ 15.00out

StreamingTool callingJSON outputImage inputThinking mode

What this model is good at

What the vendor positions it for, and which of our models to reach for instead.

VendorA frontier model for complex professional work, coding and computer-using agents.source

Best for

Agentic coding · Combines the coding strengths of GPT-5.3-Codex with lower-latency general reasoning.(vendor claim)source
Professional knowledge work · Strong on documents, spreadsheets, presentations and long-horizon deliverables.(vendor claim)source

Neighbouring models

openai/gpt-5.5successor —Use GPT-5.5 for a stronger model at the same generation style.
openai/gpt-5.4-minicheaper —Use Mini for high-volume workloads with lower latency and price.

Compare them side by side →

Pricing and billing

Tiered pricing: the rate changes once the input passes the threshold.

Price / 1M tokens by input size	Input < 272.0K	Input ≥ 272.0K
Input	$ 2.50	$ 5.00
Output	$ 15.00	$ 22.50
Cache read	$ 0.25	$ 0.50
Cache write	$ 2.50	$ 5.00

Estimate a request

Input tokens10,000

Output tokens2,000

Cache hit rate0%

At this input size you are on the Input < 272.0K tier.

$ 0.0550

Estimated cost per request

10.0K × $ 2.50
+ 2.0K × $ 15.00

≈ $ 55.00 per 1,000 requests

Capabilities and limits

What CrossModel guarantees across every route this model can take right now.

Context window: 1.1M tokens
Max output: 128.0K tokens
Input / output modalities: Text + Image → Text
Streaming: Supported
Tool calling: Supported
Structured output (JSON): Supported
Image input: Supported
Thinking mode: Supported· always on
Reasoning effort: none · low · medium · high · xhigh
Available endpoints: /v1/chat/completions · /v1/responses · /v1/messages

First-party sources:Specsdevelopers.openai.comCapabilitiesdevelopers.openai.com 1 openai.com 2

Published benchmarks

Scores the vendor reported, with the evaluation setup each one came from.

Agentic coding

Terminal-Bench 2.0
pass_rate·OpenAI · 2026-03-05effort xhighsetup not fully disclosed
75.1%

Agentic search

BrowseComp (with tools)
accuracy·OpenAI · 2026-03-05effort xhighsetup not fully disclosed
82.7%

Coding

SWE-Bench Pro (Public)
pass_rate·OpenAI · 2026-03-05effort xhighsetup not fully disclosed
57.7%

Computer use

OSWorld-Verified
success_rate·OpenAI · 2026-03-05effort xhighsetup not fully disclosed
75%

Multimodal reasoning

MMMU Pro (no tools)
accuracy·OpenAI · 2026-03-05effort xhighsetup not fully disclosed
81.2%

Reasoning

Humanity's Last Exam Full (with tools)
accuracy·OpenAI · 2026-03-05effort xhighsetup not fully disclosed
52.1%

Scientific reasoning

GPQA Diamond
accuracy·OpenAI · 2026-03-05effort xhighsetup not fully disclosed
92.8%

Tool use

Toolathlon
score·OpenAI · 2026-03-05effort xhighsetup not fully disclosed
54.6%

Vendor-reported numbers, not CrossModel measurements. Scores are only comparable when the benchmark version, metric and evaluation setup match, so nothing here is averaged or ranked.

Use it in your tools

Point the base URL at CrossModel and paste this model ID — every tool below has a setup guide.

Claude Code

Anthropic's official command-line coding assistant

Cursor

AI-first code editor

Cline

Open-source AI coding agent for VS Code

Codex

OpenAI's coding agent for ChatGPT desktop and the terminal

OpenCode

Open-source terminal coding assistant

Zed

High-performance, AI-native code editor

Open WebUI

Open-source, self-hosted AI chat interface

Continue

Open-source AI coding assistant for VS Code & JetBrains

See all integration guides →

Frequently asked questions

What is GPT-5.4?

GPT-5.4 is available on CrossModel as openai/gpt-5.4. It has a 1M-token context window and can return up to 128K tokens per request.

How much does GPT-5.4 cost?

Currently $ 2.50 per 1M input tokens and $ 15.00 per 1M output tokens. Cached input is billed at $ 0.25 per 1M.

Does GPT-5.4 support tool calling and structured output?

Tool calling: Supported · Structured output (JSON): Supported · Image input: Supported · Streaming: Supported · Thinking mode: Supported

Which endpoint do I call?

For text models, OpenAI Chat Completions (/v1/chat/completions), OpenAI Responses (/v1/responses) and Anthropic Messages (/v1/messages) all work — pick whichever your SDK already speaks.

Can I try it without writing code?