azure:openai/gpt-5.6-luna
Common Name: GPT-5.6 Luna (Azure)
Directly provided by Microsoft Azure, with no built-in filters. If you require access via the official OpenAI channel, please contact us for further arrangements.
GPT-5.6 Luna is optimized for cost-sensitive, high-volume workloads in the GPT-5.6 family.
Specifications
Performance (7-day Average)
Availability Trend (24h)
Pricing
| Item | Standard | Flex | Batch | Priority |
|---|---|---|---|---|
Short Context (≤ 272K tokens)per MTokens | ||||
| Input | $0.18 | $0.09 | $0.09 | $0.36 |
| Cached Input | $0.018 | $0.009 | $0.009 | $0.036 |
| Cache Creation | $0.225 | $0.1125 | $0.1125 | $0.45 |
| Output | $1.08 | $0.54 | $0.54 | $2.16 |
Long Context (> 272K tokens)per MTokens | ||||
| Input | $0.36 | $0.18 | $0.18 | $0.72 |
| Cached Input | $0.036 | $0.018 | $0.018 | $0.072 |
| Cache Creation | $0.45 | $0.225 | $0.225 | $0.90 |
| Output | $1.62 | $0.81 | $0.81 | $3.24 |
Performance Metrics (24h)
Similar Models
GPT-6 Luna is OpenAI's efficient GPT-6 model for high-volume workloads such as extraction, summarization, and request routing, succeeding GPT-5.6 Luna.
GPT-6 Luna is OpenAI's efficient GPT-6 model for high-volume workloads such as extraction, summarization, and request routing, succeeding GPT-5.6 Luna.
GPT-5.6 Luna is optimized for cost-sensitive, high-volume workloads in the GPT-5.6 family.
OpenAI's smallest, cheapest GPT-5.4 variant. Optimized for classification, data extraction, ranking, and coding subagents where speed and cost matter most.