GPT Mini Latest overview
GPT Mini Latest by OpenAI
GPT Mini Latest API runs through a chat completions endpoint and always redirects to the newest model in the GPT Mini family, so requests stay current without a code change. 400,000-token context, 128,000-token output limit, function calling, structured outputs.
GPT Mini Latest specs
- Model ID
openai/gpt-mini-latest- Developer
- OpenAI
- Context window
- 400,000 tokens
- Max output
- 128,000 tokens
- Input
- Image, Text
- Output
- Text
- API
- OpenAI-compatible, base URL
https://api.aimlapi.com/v1
Basic Information
Model Type: Rolling alias (chat)
Overview:
GPT Mini Latest is not a fixed model, it is an alias that always resolves to OpenAI's newest Mini-tier model. As OpenAI ships a new Mini generation, requests to this endpoint automatically route to it, without any change to your code or model string.
Key Features:
Automatic upgrades to the newest Mini-tier model as OpenAI releases them
Function calling and structured outputs
Up to 128,000 output tokens per response
Intended Use:
Suited for cost-sensitive, high-volume workloads, classification, extraction, drafting, lightweight chat, where staying on the latest Mini-tier model matters more than pinning to a specific dated snapshot.
Usage
Because this is a rolling alias, behavior and pricing can change when OpenAI updates which model it points to. For workloads that require a fixed, reproducible model version, use a dated snapshot instead of this alias.
Use cases
Customer support chatbots, high-volume text summaries, and code generation assistants are all documented use cases for this model.
It is also described as suitable for knowledge base search, especially when the workload needs quick retrieval-style assistance.
For lightweight operational tasks, it is documented for usage cost optimization and log and alert monitoring.
Capabilities
- File input
- Reasoning
- Streaming
- Vision
- Web search
GPT Mini Latest API pricing
| Usage | Price | Unit |
|---|---|---|
| Input | $0.7935 | 1M tokens |
| Output | $4.76 | 1M tokens |
| Cached input | $0.0794 | 1M tokens |
Prices from the AI/ML API price list, checked on Nov 4, 2026.
GPT Mini Latest vs other models: token prices
AI/ML API input and output rates for 5 models, per million tokens.
| Model | Input | Output |
|---|---|---|
 GPT Mini Latest | $0.7935 | $4.76 |
| GPT-6 Luna | $0.1 | $0.5 |
| GPT-6.1 Terra | $1 | $5 |
| GPT-6.1 Sol | $2 | $10 |
| GPT-6.1 Terra Pro | $2.12 | $10.58 |
How to use the GPT Mini Latest API
View docs
Build with your agent
Give your agent the model details, code and documentation.
1Get your API key
Create API keyexport AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"2Make your first request
curl 'https://api.aimlapi.com/v1/chat/completions' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "openai/gpt-mini-latest",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "openai/gpt-mini-latest",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}
response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "openai/gpt-mini-latest",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());Models similar to GPT Mini Latest
GPT Mini Latest FAQ
What is the context window of GPT Mini Latest?
GPT Mini Latest has a 400,000 tokens context window and can return up to 128,000 tokens.
What inputs and outputs does GPT Mini Latest support?
GPT Mini Latest takes image, text as input and returns text.
What is the model ID for GPT Mini Latest?
Use openai/gpt-mini-latest as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
When was GPT Mini Latest released?
GPT Mini Latest became available on April 27, 2026.
How much does GPT Mini Latest cost?
GPT Mini Latest costs $0.7935 input and $4.76 output per 1M tokens on AI/ML API, billed as you go with no subscription.
Does GPT Mini Latest support streaming?
Yes, GPT Mini Latest can stream responses as they are generated.
Can GPT Mini Latest read images?
Yes, GPT Mini Latest accepts image input alongside text.
Who created GPT Mini Latest?
GPT Mini Latest was built by OpenAI.
Does GPT Mini Latest support tool calling or external integrations?
Yes, it supports tool use, parallel tool calls, and web search.