GPT-5.4 Mini

openai/gpt-5.4-mini

GPT-5.4 mini is the smaller, faster tier of OpenAI's GPT-5.4 family, released in March 2026 with text and image input and text output. OpenAI describes it as its strongest mini model at release for coding, computer use and subagents, bringing much of GPT-5.4's capability to high-volume workloads at more than twice the speed of GPT-5 mini. Pick it over full GPT-5.4 for responsive coding assistants and agent fleets, and over nano when tasks need computer use.

Input price
$0.75USD / 1M tokens
Output price
$4.50USD / 1M tokens
Cache read
$0.08USD / 1M tokens
Context window
400K
Max output
128K

Specifications

CapabilitiesChatVisionReasoningStructured outputFunction calling
Input
Text, image
Output
Text
Available

Questions

FAQ

How do I call OpenAI GPT-5.4 Mini through SandBase?

Create a SandBase API key, then send requests with the model ID "openai/gpt-5.4-mini" to Responses API (/v1/responses) or Chat Completions API (/v1/chat/completions) at https://api.sandbase.ai. The request examples on this page show the exact payload.

How much does OpenAI GPT-5.4 Mini cost?

$0.75 per 1M input tokens and $4.50 per 1M output tokens, billed per request from your SandBase balance. Discounts, when available, are shown in the pricing on this page.

What is the context window of OpenAI GPT-5.4 Mini?

400K tokens of context, with up to 128K output tokens per response.

Which features does OpenAI GPT-5.4 Mini support?

OpenAI GPT-5.4 Mini supports vision (image input), reasoning, function calling, structured output. See Specifications above for the full list.

Do I need a separate OpenAI account?

No. One SandBase API key and balance gives you access to OpenAI GPT-5.4 Mini and the other models in the catalog; you do not need to sign up with OpenAI separately.