GPT 5.6 Luna

OpenAI lightweight model configured for fast, cost-efficient text generation and reasoning workloads.

Overview

GPT 5.6 Luna is a OpenAI model configured in Yolo Router. It is the lightweight variant of the GPT-5.6 series, optimized for fast responses and cost-sensitive applications. Use the model ID gpt-5.6-luna when calling compatible APIs.

Key Specifications

Parameter	Value
Provider	OpenAI
Model ID	`gpt-5.6-luna`
Input Modalities	Text, Image
Output Modalities	Text
Pricing Type	Usage-based

Capabilities

Vision Understanding - Accepts visual context for image-aware tasks
Deep Reasoning - Suitable for multi-step analysis and planning
Text Generation - Generates answers, drafts, summaries, and rewrites

Pricing

Type	Price
Input	$0.3 / 1M tokens
Output	$1.8 / 1M tokens
Cache Read	$0.03 / 1M tokens
Cache Write	$0.375 / 1M tokens

Usage Example

from openai import OpenAI

client = OpenAI(
    api_key="sk-...",
    base_url="https://api.yolorouter.com/v1",
)

response = client.responses.create(
    model="gpt-5.6-luna",
    input="Summarize this content.",
)

print(response.output_text)

Best Practices

Pass the model ID exactly as shown in the documentation.
Match the model capability tags to the text, image, audio, or video workload.
When cache prices are configured, keep stable prompt prefixes to improve cache reuse.