All models

GPT-5.6 Luna

openai/gpt-5.6-luna

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...

Modalities
File
Image
Text
In / Out price
$0.10 / $0.60 per 1M
Context
1.05M · 128K out
Released
Jul 9, 2026

Providers

Live list prices and uptime across 7 providers serving this model.

ProviderInput /MOutput /MCache read /MContextMax outputUptime 24h
OpenAI$0.20$1.20$0.021.05M128K99.70%
OpenAI$0.10$0.60$0.011.05M128K99.70%
OpenAI$0.40$2.40$0.041.05M128K99.70%
Azure$0.20$1.20$0.021.05M128K86.22%
Azure$0.22$1.32$0.0221.05M128K81.06%
Azure$0.22$1.32$0.0221.05M128K100.00%
Amazon Bedrock$0.22$1.32$0.0221.05M128K100.00%

Implicit prompt caching available — repeated context bills at the cache read rate.

Capabilities

Tool calling
Reasoning
Moderated
include_reasoning
max_completion_tokens
max_tokens
reasoning
reasoning_effort
response_format
seed
structured_outputs
tool_choice

Pricing detail

Input
$0.10
Output
$0.60
Cache read
$0.01
Cache write
$0.125

USD per 1M tokens.