GPT-5.4 mini

Lightweight tier of the GPT-5.4 family for cost-sensitive, high-volume workloads.

GPT-5.4 mini strengths

• Very low cost
• Fast latency
• Good general capability for its size
• Solid tool calling

Pricing & context

Cost guide: a typical call of about 10K input + 2K output tokens costs roughly $0.017 at list prices. Worth modelling against cheaper tiers before committing high-volume traffic.

When to choose GPT-5.4 mini

GPT-5.4 mini is best for high-volume tasks like classification, extraction, and chat where cost and speed matter most. If your workload is more cost-sensitive, weigh it against gpt-oss-120b (≈$0.03 input /1M) first.

GPT-5.4 mini FAQ

How much does GPT-5.4 mini cost?

GPT-5.4 mini is priced at $0.75 per 1M input tokens and $4.50 per 1M output tokens (public API list price), with a ~400K tokens context window. A typical call of about 10K input and 2K output tokens costs roughly $0.017.

What is GPT-5.4 mini best for?

GPT-5.4 mini by OpenAI is best for high-volume tasks like classification, extraction, and chat where cost and speed matter most.

How does GPT-5.4 mini pricing compare to Claude Haiku 4.5?

GPT-5.4 mini input costs $0.75 per 1M tokens versus $1.00 for Claude Haiku 4.5, roughly 1.3x less expensive on input. Output is $4.50 vs $5.00.

Is GPT-5.4 mini multimodal?

GPT-5.4 mini supports text, image.