GPT text model pricing has been updated. All GPT text models are now billed at 10% of OpenAI's official API prices, including the latest official price reductions for GPT-5.6 Terra and Luna.View latest pricing
OpenAI

GPT-5.4

Official

openai/gpt-5.4

The prior-generation GPT-5.4. Strong reasoning and coding at roughly half the token price of 5.5, with a 1M-token context window. A solid default when 5.5 is overkill.

1000K contextVisionReasoningTool callingCodingPrompt cache

Pricing

Source: openai_x0.10 · Verified 2026-08-02

InputOfficial $2.5 / M tokens
$0.25/ M tokensSave 90%
OutputOfficial $15 / M tokens
$1.5/ M tokensSave 90%

Fast $0.5 / $3 /M

Cache read $0.025/M · Cache write —/M

TierInputCache readCache writeOutput
Standard ≤272K$0.25$2.5 −90%$0.025$0.25 −90%—$1.5$15 −90%
Standard >272K$0.5$5 −90%$0.05$0.5 −90%—$2.25$22.5 −90%
Priority$0.5$5 −90%$0.05$0.5 −90%—$3$30 −90%

Estimate cost

Estimated cost$0.004

Protocols

  • OpenAI Chat CompletionsStatus: Available: Streaminghttps://api.routemux.com/v1
  • OpenAI ResponsesStatus: Available: Streaminghttps://api.routemux.com/v1
  • Anthropic MessagesStatus: Available: Streaminghttps://api.routemux.com/anthropic
  • Google Vertex AIStatus: Not supported—
  • OpenAI ImagesStatus: Not supported—
  • OpenAI SoraStatus: Not supported—

Call IDs

Use either ID to call this model via the API.

RouteMux nameopenai/gpt-5.4

Try it

Replace the ROUTEMUX_KEY placeholder with your API key. Create one →

from openai import OpenAI

client = OpenAI(
    base_url="https://api.routemux.com/v1",
    api_key="<ROUTEMUX_KEY>",
)

completion = client.chat.completions.create(
    model="openai/gpt-5.4",
    messages=[{"role": "user", "content": "What is the meaning of life?"}],
)
print(completion.choices[0].message.content)
base_url: https://api.routemux.com/v1

Other variants in this family

OpenAIGPT-5.6 Sol

OpenAI's flagship GPT-5.6 for the hardest reasoning, coding, and agentic work.

$0.5/M↓ · $3/M↑

OpenAIGPT-5.6 Terra

Balanced GPT-5.6 quality and cost for production workloads.

$0.2/M↓ · $1.2/M↑

OpenAIGPT-5.6 Luna

The most efficient GPT-5.6 for high-volume and latency-sensitive work.

$0.02/M↓ · $0.12/M↑

OpenAIGPT-5.4 mini

OpenAI GPT-5.4 mini — fast, cheapest GPT-5 text route.

$0.075/M↓ · $0.45/M↑

OpenAIGPT-5.5

OpenAI GPT-5.5 — flagship, 1M context, top reasoning & agentic coding.

$0.5/M↓ · $3/M↑

Frequently asked questions

›What is GPT-5.4?

OpenAI GPT-5.4 — strong general model, 1M context, lower cost than 5.5.

›How large is the context window of GPT-5.4?

GPT-5.4 supports a context window of up to 1M tokens, with up to 128K output tokens per request.

›How much does the GPT-5.4 API cost?

Through RouteMux, GPT-5.4 costs $0.25 for input and $1.5 for output (USD per 1M tokens), below the official list price.

›How do I call GPT-5.4 via API?

GPT-5.4 is OpenAI-compatible: point your base URL at RouteMux and set the model field to openai/gpt-5.4 — no code changes needed.

›Which input and output modalities does GPT-5.4 support?

GPT-5.4 accepts text, image as input and produces text as output.