OpenAI: GPT-4o mini

Small omni GPT for cheap multimodal assistance and production-scale traffic

gpt-4o-mini

AvailableOpenAIChatCached input 50% less

Input / Output-30%: $0.15 / $0.60$0.105 / $0.42
Context: 128K
Max output: 16K
Modalities: VisionChat
Capabilities: Tool usePrompt Cache

About GPT-4o mini

GPT-4o mini is OpenAI's fast, affordable small model for focused tasks. It takes text and image input and returns text, with function calling, structured outputs, and streaming. OpenAI positions it as a good target for fine-tuning and for distilling outputs from the larger GPT-4o. It is a long-running choice for high-volume features; GPT-4.1 mini is the newer small option with a longer context.

Where it works well

Small and quick, so it handles high-volume traffic for chat features, tagging, and short replies.
Accepts images with text, so simple vision jobs such as reading a receipt do not need a larger model.
OpenAI recommends distilling GPT-4o outputs into it, a path to a cheaper specialist model.
Supports function calling, structured outputs, streaming, and tools such as code interpreter and file search.

When to choose another model

Context is much shorter than GPT-4.1 mini's, so long inputs need chunking.
Knowledge ends in October 2023, older than the GPT-4.1 line.
On hard reasoning or intricate instructions it falls behind larger models.

Getting started

Create API key
Create a key in Console, then use it with every model on the platform.
02
Send your first request
Copy the example for your language and run it against the endpoint.
Text to textResponses API
POST/v1/responses
API format:
curl https://api.tokenlab.sh/v1/responses \ -H "Content-Type: application/json" \ -H "Authorization: Bearer sk-xxx" \ -d '{ "model": "gpt-4o-mini", "input": "Hello!" }'

Pricing

The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.

Default spec

per 1M tokens

Official price: Input $0.15 / Output $0.60 / Cache read $0.075
Verified price: Input $0.105 / Output $0.42 / Cache read $0.0525
Discount: -30%

Prompt cache pricing

Cache read

Official price: $0.075
Verified price: $0.0525
Discount: -30%

Tool fees

Charged per call, only when the model uses the tool.

Web search

Official price: $0.01/search
Verified price: $0.007/search
Discount: -30%

	Official priceper 1M tokens	Verified priceper 1M tokens	Discount
Default spec	Input $0.15 / Output $0.60 / Cache read $0.075	Input $0.105 / Output $0.42 / Cache read $0.0525	-30%
Prompt cache pricing
Cache read	$0.075	$0.0525	-30%
Tool feesCharged per call, only when the model uses the tool.
Web search	$0.01/search	$0.007/search	-30%

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours

Requests
Success rate
P95 latency
Total tokens

Model performance

Last updated Oct 13, 2026, 6:17 AM UTC

30-day success rate: 100.0%
7-day median latency: 4.8sn=261
7-day P95 latency: 16.5sn=261
30-day requests: 2K+
Last active: 5 hours ago

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open GPT-4o mini in Console with a prompt ready to edit or send.

Help me try gpt-4o-mini with a short message at /v1/responses. Show the reply, latency, and cost.

Use cases

Best for

Vision

High-volume chat features
Back a support widget or in-app helper that answers short questions quickly for many users.
Distilled specialist
Fine-tune it on answers from GPT-4o to keep quality on a narrow task at a smaller footprint.
Ticket triage
Label and summarise incoming tickets so agents see priority and topic at a glance.
Simple image reading
Pull text and fields from receipts, labels, and screenshots where layouts are simple.

Prompt examples

Summarise this support ticket in one sentence and give it a priority of low, medium, or high.

Read the label in this photo and list the ingredients as a JSON array.

Rewrite this product description in a friendly tone, under 40 words.

This model has conditional pricing. Monthly token totals alone cannot produce a reliable estimate; use the detailed pricing for the request specification, cache, and applicable time window.

FAQ

What is GPT-4o mini?

OpenAI's small model in the GPT-4o line. It reads text and images, answers in text, and is built for fast, affordable, focused tasks. It also supports fine-tuning and distillation from the larger GPT-4o.

GPT-4o mini or GPT-4.1 mini?

GPT-4.1 mini has a far longer context and a later knowledge cutoff. GPT-4o mini fits where you already tuned prompts to it or distilled GPT-4o into it. For new builds with long inputs, try GPT-4.1 mini.

Can I fine-tune it?

Yes. OpenAI describes it as ideal for fine-tuning, including using outputs from GPT-4o as training data, so the small model imitates the larger one on your task.

Does it understand images?

Yes, it accepts image input with text. It suits simple jobs such as reading labels, receipts, and screenshots; complex diagrams may need a larger model.

Does it support function calling and structured outputs?

Yes. It can call functions you define and return output that follows a JSON schema, which suits classification, tagging, and extraction features that run at high volume.

How much does GPT-4o mini cost?

On TokenLab, GPT-4o mini costs Input $0.105 / Output $0.42 per 1M tokens. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

What are the context window and output limit of GPT-4o mini?

GPT-4o mini accepts up to 128,000 tokens of context and returns up to 16,384 tokens in one response.

Which endpoint should GPT-4o mini use?

Use https://api.tokenlab.sh/v1/responses for GPT-4o mini. The request example below shows the matching code shape.

Which operations does GPT-4o mini support?

GPT-4o mini supports Text to text. Select an operation above to see its endpoint and request example.