anoman
Sign InGet API Key

OpenAI

GPT-5.4

modelgpt-5.4
MidStableVisionStreamingVisionToolsBatchLong contextUnited States

Context

1.1M

Input / 1M tokens

$2.50

Output / 1M tokens

$15.00

Cached input / 1M tokens

$0.5875

Cache write / 1M tokens

β€” (bills at input price)

About this model

GPT-5.4

GPT-5.4 is OpenAI's mid-tier flagship β€” near-GPT-5.5 quality at half the price. The default workhorse choice when you want strong reasoning without paying premium rates.

Key facts

Maker
OpenAI
Context window
1.1M tokens
Max output
128K tokens
Lane
Guarded: the provider has confirmed it does not train on your data
Modality
Text and image input
Input price
$2.50 per 1M tokens
Output price
$15.00 per 1M tokens
Processing region(s)
us
Route
Via OpenAI's API
Cheapest plan
Available from the Pro plan
Price comparison
Priced below 22 of 235 pro-band guarded models on Anoman (blended price: 1 part input to 3 parts output).

More models by OpenAI

Released

2026-01

Training cutoff

2024-11

Parameters

Not disclosed

Ways to call

Ways to call GPT-5.4

Each model ID below is callable through the Anoman AI API. Price and processing region depend on the route.

Model IDRouteInput / output per 1M tokensRegion(s)LaneContext
gpt-5.4Via OpenAI's API$2.50 / $15.00usGuarded1.1M
gpt-5-4-openrouterVia OpenRouter$2.50 / $15.00globalGuarded1.1M

Best for

Use cases

  • Production AI assistants
  • Multi-step reasoning at scale
  • Document analysis + extraction
  • Tool-using agents

Strengths

What it does well

  • Near-5.5 quality at significantly lower cost
  • 1M-token context window
  • Strong tool calling + structured output
  • Reliable at high throughput

Limitations

Know the trade-offs

  • Trails 5.5 on the very hardest reasoning
  • Output tokens $15/Mtok β€” set max_tokens carefully

Code example

Chat completion with GPT-5.4

from openai import OpenAI

client = OpenAI(
    base_url="https://api.anoman.io/v1",
    api_key="anm-sk-..."
)

response = client.chat.completions.create(
    model="gpt-5.4",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

Alternatives

Similar models in our catalog

Same maker first, then the closest price to GPT-5.4 in the Anoman catalog.

Use GPT-5.4 through Anoman.