Textby OpenAI

GPT-5.4

GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...

  • By price it is among the most expensive of the 345 text models GenMagic runs (311th cheapest).
  • Among the models GenMagic runs, it places in the top 10 on 9 of its 52 benchmarks: 1st of 14 on CL-bench, 2nd of 43 on FrontierMath, 2nd of 39 on Terminal-Bench, and more below.
  • It was listed on Mar 5, 2026.

Data last changed Nov 13, 2026 · tracked since Oct 29, 2026 · Every model change

Try GPT-5.4

Generate with GPT-5.4 right here. Verify your email to start with free credits.

~$0.026
Try

Specifications

Context window

1.1M tokens

Max output

128K tokens

Input price

$3.75 / 1M tokens

Output price

$22.50 / 1M tokens

Cached input

$0.38 / 1M tokens

Benchmarks

How GPT-5.4 scores on public benchmarks. Each card links to the benchmark explainer and to the original source.

71.1

source date 2026-11-11
Source: openrouter
AIMEMathematics

95.6%± 3.1

mediumsource date 2026-07-15
Source: epoch
APEX-AgentsAgentic & Tool Use

52.4%

unknown
Source: epoch
ARC-AGI-1Reasoning & Knowledge

93.7%

xhigh
Source: epoch
ARC-AGI-2Reasoning & Knowledge

74%

xhigh
Source: epoch
Chess PuzzlesReasoning & Knowledge

48%± 5.0

xhighsource date 2026-10-13
Source: epoch
CL-benchLong Context

27.9%

xhigh
Source: epoch
CL-bench LifeLong Context

21.7%

xhigh
Source: epoch
Design Arena: 3DDesign & Generation

1084 Elo

Source: designarena
Design Arena: CodeDesign & Generation

1203 Elo

Source: designarena
Design Arena: SVGDesign & Generation

1185 Elo

Source: designarena
DeepSWECoding

51.8%

xhigh; Reasoning effort: xhigh; Harness: mini-swe-agent
Source: epoch
DTBenchReasoning & Knowledge

94.4%

xhigh
Source: epoch

25.4

xhighsource date 2026-06-25
Source: epoch
FrontierMathMathematics

47.6%± 2.9

xhighsource date 2026-03-06
Source: epoch

27.1%± 6.4

xhighsource date 2026-03-06
Source: epoch

49%± 8.0

xhighsource date 2026-06-11
Source: epoch

78.6%± 2.4

xhighsource date 2026-06-11
Source: epoch
GPQA DiamondReasoning & Knowledge

90.2%± 0.0

source date 2026-10-01
Source: openrouter
GSO OPT@1Coding

31.4%

xhigh; Scaffold: OpenHands
Source: epoch
Humanity's Last ExamReasoning & Knowledge

36.2%± 1.9

xhigh
Source: epoch
LMArena (Coding)Instruction & Preference

1497 Elo

highsource date 2026-11-11
Source: lmarena
LMArena: Creative WritingInstruction & Preference

1437 Elo

highsource date 2026-11-11
Source: lmarena
LMArena: Hard PromptsInstruction & Preference

1485 Elo

highsource date 2026-11-11
Source: lmarena

1473 Elo

highsource date 2026-11-11
Source: lmarena
LMArena: MathMathematics

1496 Elo

highsource date 2026-11-11
Source: lmarena
LMArena: Multi-TurnInstruction & Preference

1482 Elo

highsource date 2026-11-11
Source: lmarena
LMArena (Overall)Instruction & Preference

1469 Elo

highsource date 2026-11-11
Source: lmarena
LMCAReasoning & Knowledge

52

xhigh
Source: epoch
METR: Average Task SuccessAgentic & Tool Use

74.3%

xhigh
Source: epoch

23.3

xhighsource date 2026-10-29
Source: epoch
Mystery Game PuzzlesReasoning & Knowledge

16%± 3.7

nonesource date 2026-08-30
Source: epoch
PostTrainBenchAgentic & Tool Use

17.8

high; Scaffold: Codex CLI
Source: epoch
ProofBenchMathematics

56%± 5.0

xhigh; Reasoning effort: xhigh
Source: epoch
SciCodeCoding

56.6%

xhigh
Source: epoch
SimpleQA VerifiedReasoning & Knowledge

45.1%± 1.6

xhighsource date 2026-08-27
Source: epoch

76.9%± 1.9

highsource date 2026-03-06
Source: epoch
tau-bench (Airline)Agentic & Tool Use

75%± 0.3

source date 2026-10-01
Source: openrouter

81.8%± 2.0

unknown
Source: epoch
WebDev ArenaAgentic & Tool Use

1463 Elo

high
Source: epoch
WeirdMLCoding

77.7%± 0.0

xhigh
Source: epoch

Compare against every model in the full benchmark matrix.

Capabilities

Reasoning

Works through multi-step problems before answering, for harder tasks.

Vision input

Accepts images alongside text, so you can prompt with pictures and screenshots.

Tool use

Can call functions and tools, enabling agentic and structured workflows.

Structured output

Returns validated JSON that conforms to a schema you define.

Use GPT-5.4 through the API

The model id is openai/gpt-5.4. Requests bill your GenMagic balance at the price above, and each response reports what it cost.

curl
curl https://genmagic.co/api/v1/chat/completions \
  -H "Authorization: Bearer $GENMAGIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-5.4",
    "messages": [{ "role": "user", "content": "Explain vector databases in two sentences." }]
  }'
Python (openai SDK)
from openai import OpenAI

client = OpenAI(base_url="https://genmagic.co/api/v1", api_key="YOUR_GENMAGIC_API_KEY")

resp = client.chat.completions.create(
    model="openai/gpt-5.4",
    messages=[{"role": "user", "content": "Explain vector databases in two sentences."}],
)
print(resp.choices[0].message.content)

From an AI agent, call generate_text with "model": "openai/gpt-5.4" on the GenMagic MCP server. Keys, limits and every endpoint are in the API documentation.

Use GPT-5.4 in n8n

  1. In n8n, open the nodes panel, search for GenMagic and install it (a verified community node), then add it to your workflow.
  2. Set Resource to Text and Operation to Generate.
  3. In Model Name or ID, pick OpenAI: GPT-5.4, or enter openai/gpt-5.4 as an expression.
  4. Connect your GenMagic API key (get one free). Each run is billed at the price above, and the node returns what it cost.

Ready-to-import workflows that already use the node are on GenMagic for n8n.

Similar-priced text models from other providers

Other text models GenMagic runs at a comparable price, on the same balance and API key.

ModelProviderPriceContext
OpenAI: GPT-5.4 (this model)OpenAI$3.75 in / $22.50 out per 1M tokens1.1M
Fireworks: Ember-1Fireworks$4.50 in / $22.50 out per 1M tokens1M
Anthropic: Claude Sonnet 4.6Anthropic$4.50 in / $22.50 out per 1M tokens1M
Perplexity: Sonar Pro SearchPerplexity$4.50 in / $22.50 out per 1M tokens200K
MoonshotAI: Kimi K3Moonshot AI$0.29 in / $24.00 out per 1M tokens1M
Qwen: Qwen3.8 Max PrimeQwen$6.00 in / $18.00 out per 1M tokens1M

More from OpenAI

All 70 OpenAI models

Price and listing history

Every change GenMagic has recorded for GPT-5.4 since it began tracking the model on Oct 29, 2026. Prices are GenMagic's, the same the studio and the API charge.

DateChangeBeforeAfter
Nov 1, 2026Price up 36%$2.75 in / $16.50 out per 1M tokens$3.75 in / $22.50 out per 1M tokens

Where these figures come from

  • Price: GenMagic's own price, what the studio and the API charge, recomputed from the provider's price list every few minutes and recorded daily. How pricing works.
  • Specs and description: as OpenAI publishes them, checked daily.
  • Benchmarks: 52 scores from Artificial Analysis and OpenRouter, Epoch AI, Design Arena, LMArena, re-read daily. Each score above links to its source.
  • Changes: the data on this page last changed on Nov 13, 2026, tracked since Oct 29, 2026. Every model's new listings, price changes and retirements are in the model changes log, and how every figure on GenMagic is sourced is on our sources page.

Generate with GPT-5.4 today

One GenMagic plan unlocks GPT-5.4 and every other model across text, image, audio, and video.