OpenAIFastStandard

GPT-4.1 Nano

OpenAI's fastest and cheapest model. Optimized for classification, autocompletion, and low-latency tasks. Ultra-affordable at $0.10/1M input tokens.

1 credits

per 1K tokens (avg)

1M token context window

32K max output tokens

Ultra-low latency

Lowest cost in GPT-4.1 family

Native vision (text + image)

Function calling & JSON mode

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

llms.txt

Model Specifications

Context Window

1.0M

tokens

Max Output

33K

tokens

Training Cutoff

2024-05

Compatible SDK

OpenAI

Capabilities

Vision

Function Calling

Streaming

JSON Mode

System Prompt

Token Pricing (per 1M tokens)

Token Type	Credits	USD Equivalent
Input Tokens	100	$0.10
Output Tokens	400	$0.40
Cached Tokens	25	$0.03

* 1 credit ≈ $0.001 (actual charges may vary based on usage)

Quick Start

curl -X POST "https://api.core.today/llm/openai/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "model": "gpt-4.1-nano",
  "messages": [
    {
      "role": "system",
      "content": "Classify the sentiment as positive, negative, or neutral. Respond with JSON: {\"sentiment\": \"...\", \"confidence\": 0.0}"
    },
    {
      "role": "user",
      "content": "The new update is amazing! Everything runs so much smoother now."
    }
  ],
  "response_format": {
    "type": "json_object"
  },
  "max_tokens": 50
}'

Parameters

Parameter	Type	Required	Default	Description
`messages`	array	Yes	-	Array of message objects with role and content
`model`	string	Yes	gpt-4.1-nano	Model identifier
`temperature`	float	No	1.0	Sampling temperature (0-2). Lower = more focused, higher = more creative
`max_tokens`	integer	No	4096	Maximum tokens in response (up to 32768)
`stream`	boolean	No	false	Enable Server-Sent Events streaming
`response_format`	object	No	-	Format of response: { type: 'json_object' } for JSON mode
`tools`	array	No	-	List of tools (functions) the model can call
`top_p`	float	No	1.0	Nucleus sampling threshold (0-1)

Examples

Text Classification

Ultra-fast sentiment classification

curl -X POST "https://api.core.today/llm/openai/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "model": "gpt-4.1-nano",
  "messages": [
    {
      "role": "system",
      "content": "Classify the sentiment as positive, negative, or neutral. Respond with JSON: {\"sentiment\": \"...\", \"confidence\": 0.0}"
    },
    {
      "role": "user",
      "content": "The new update is amazing! Everything runs so much smoother now."
    }
  ],
  "response_format": {
    "type": "json_object"
  },
  "max_tokens": 50
}'

Quick Autocomplete

Low-latency text completion

curl -X POST "https://api.core.today/llm/openai/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "model": "gpt-4.1-nano",
  "messages": [
    {
      "role": "system",
      "content": "Complete the user's sentence naturally. Keep it brief."
    },
    {
      "role": "user",
      "content": "The main advantage of microservices architecture is"
    }
  ],
  "temperature": 0.3,
  "max_tokens": 100
}'