Conduix.ai
All models

GPT-5.4 mini

Mid
OpenAIChatgpt-5.4-mini

Cheap and capable — default for high-volume routine tasks.

Capabilities

Tool callingVisionJSON modePrompt cache

Recommended for

  • high-volume routine tasks
  • summarisation
  • extraction

Using this model through Conduix

Call it by its id, or let a routing alias pick it as part of a governed, cross-provider chain with automatic failover.

Direct model idgpt-5.4-mini

Reached by these routing aliases:

  • frontier-budgetprimary pick · GPT-5.4 mini → Claude Haiku 4.5 → Gemini 3.1 Flash-Lite → DeepSeek V4 Flash
  • code-fastprimary pick · GPT-5.4 mini → Codestral → Claude Haiku 4.5
  • reasoning-budgetfallback #2 · DeepSeek V4 Pro → DeepSeek V4 Flash → GPT-5.4 mini
  • vision-fastfallback #1 · Gemini 3.5 Flash → GPT-5.4 mini → Gemma 4 31B (Together)

Routing relationships are operational — chains adapt to provider availability and your org's policy — not a contractual guarantee that a specific model serves a given request.

Get started

Conduix is OpenAI-API-compatible — point any OpenAI SDK at https://api.conduix.ai/v1 and pass gpt-5.4-mini as the model.

from conduix import Conduix

client = Conduix(api_key="cx_live_YOUR_KEY")  # base URL is built in

response = client.chat.completions.create(
    model="gpt-5.4-mini",
    messages=[{"role": "user", "content": "Hello, Conduix!"}],
)
print(response.choices[0].message.content)
  • Tool calling: Pass a tools array and the model calls your functions.
  • Vision: Accepts image inputs — add image_url parts to a message.
  • JSON mode: Set response_format for guaranteed-valid JSON output.
  • Prompt cache: Repeated prompt context is billed at a reduced rate.

The response's x-conduix-model-served header tells you exactly which model answered. See the quickstart for keys, headers, and usage.