GPT 5.4 Mini
by OpenAI
GPT 5.4 Mini pricing, context window and specs
GPT 5.4 Mini is OpenAI’s small, fast model in the GPT 5.4 family. It costs $0.75 per million input tokens and $4.50 per million output tokens, reads up to 400,000 tokens in one request, and supports images, tool calling and structured output.
GPT 5.4 Mini specs
Provider
OpenAI
Model ID
gpt-5.4-mini
Input price
$0.75 per 1M tokens
Cached input price
$0.075 per 1M tokens
Output price
$4.50 per 1M tokens
Context window
400,000 tokens
Modalities
Text and images in, text out
Tool calling
✓ Supported
Structured output
✓ Supported
Reasoning
✓ Supported
Vision
✓ Supported
Prices checked on
When to use GPT 5.4 Mini
Pick GPT 5.4 Mini when the job is clearly defined and you run it a lot. Dozens of agent templates in the Fetch Hive library run on it for that reason.
High volume steps. Classifying, tagging, routing and pulling fields out of text, where the cost of each call matters more than depth.
Agents that use tools. It supports tool calling and structured output, so it can search, read a page and hand back clean JSON.
Summaries and first drafts. The 400,000 token context window fits long documents, transcripts and email threads in one request.
Reading images. It accepts screenshots, scans and photos alongside text.
Pick a larger model for long chains of reasoning, hard code changes, or writing where the tone has to be exactly right. GPT 5.4 is the usual step up, at $2.50 per million input tokens and $15 per million output tokens.
Cost calculator
What GPT 5.4 Mini costs at your volume
Pick a workload or move the sliders. The estimate uses the prices in the table above.
One flat rate at any prompt length. Input that OpenAI serves from its prompt cache is billed at $0.075 per million tokens.
Templates
Templates that run on GPT 5.4 Mini
Each one is a finished workflow or agent built on this model. Run it as it is, or copy it and change the steps.
Build with it
Use GPT 5.4 Mini in Fetch Hive
Fetch Hive is an AI agent builder. Pick this model in any prompt, workflow or agent step, or call it from your own code with one API request.
Call GPT 5.4 Mini through the AI Gateway
1
Create a prompt and pick the model
Write your prompt in Fetch Hive and choose this model from the model library. Add a fallback model if you want a backup.
2
Deploy the prompt
Deploying gives the prompt a deployment name and a variant that your code can call.
3
Send one POST request
Call the invoke endpoint with your API key. Usage is charged to your AI wallet at the provider list price, and each call uses one task.
Compare
Compare GPT 5.4 Mini with similar models
List prices per 1M tokens and context window, next to the models people most often weigh it against.
GPT 5.4 Nano
GPT 5.4
Claude Haiku 4.5
FAQ





