anoman

OpenAI

GPT-5.4 Mini

modelgpt-5.4-mini
MidStableVisionStreamingVisionToolsBatchLong contextUnited States

Context

272K

Input / 1M tokens

$0.7500

Output / 1M tokens

$4.50

About this model

GPT-5.4 Mini

GPT-5.4 Mini — OpenAI's cost-optimized 5.x tier. Strong reasoning per dollar; the right pick for high-volume agentic workloads where 5.4 is overkill.

Released

2026-01

Training cutoff

2024-11

Parameters

Not disclosed

Best for

Use cases

  • High-volume agentic workloads
  • Routing + classification
  • Cost-sensitive production chat

Strengths

What it does well

  • Sub-second TTFT typical
  • Same tool calling reliability as full 5.4
  • 400K context window

Limitations

Know the trade-offs

  • !Reasoning depth trails 5.4 on hard math
  • !Not a Mini replacement for Opus-class tasks

Code example

Chat completion with GPT-5.4 Mini

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-mini",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

Alternatives

Similar models in our catalog

Workloads that fit GPT-5.4 Mini often fit these too. Compare benchmarks and pricing before locking in a default.

Use GPT-5.4 Mini through Anoman.