OpenAI: 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
In / Out Price
$0.20 / $1.20 per 1M
Context
1.1M
Released
Jul 9, 2026
Knowledge Cutoff
Feb 2026
Providers
Different carriers host the same model. Reroute routes each request to the best one on price and uptime, and fails over to the next if a carrier goes down.
| Provider | Context | Input /M | Output /M | Cache read /M | Latency | Throughput | Uptime |
|---|---|---|---|---|---|---|---|
| OpenAI | 1.1M | $0.10 | $0.60 | $0.01 | — | — | 100.00% |
 Azure | 1.1M | $0.20 | $1.20 | $0.02 | — | — | 100.00% |
| OpenAI | 1.1M | $0.20 | $1.20 | $0.02 | — | — | 100.00% |
| Azure | 1.1M | $0.22 | $1.32 | $0.022 | — | — | 100.00% |
 Amazon Bedrock | 1.1M | $0.22 | $1.32 | $0.022 | — | — | 100.00% |
| Azure | 1.1M | $0.22 | $1.32 | $0.022 | — | — | 100.00% |
| OpenAI | 1.1M | $0.40 | $2.40 | $0.04 | — | — | 100.00% |