GPT-5 vs GPT-5.6 Luna
GPT-5 (OpenAI) versus GPT-5.6 Luna (OpenAI): API pricing, context window, capabilities and uptime, from the same data as each model page, at the KumoAPI default channel price. Input costs 1.25 Credits / M for GPT-5 and 0.2 Credits / M for GPT-5.6 Luna, so GPT-5.6 Luna is 84% cheaper. Context windows are 400K and 1.05M.
GPT-5.6 Lunagpt-5.6-lunaSpecs side by side
| Item | GPT-5gpt-5 | GPT-5.6 Lunagpt-5.6-luna |
|---|---|---|
| Input (prompt) · Credits / M | 1.25 | 0.2 |
| Output (completion) · Credits / M | 10 | 1.2 |
| Cache read · Credits / M | 0.125 | 0.02 |
| Context window | 400K | 1.05M |
| Max output | 128K | 128K |
| 7-day uptime | — | — |
| Latest probe latency | — | — |
| Measured throughput | — | — |
| Protocols | — | — |
| Sample monthly cost (10M in + 2M out) | 32.5 | 4.4 |
Prices are the KumoAPI default channel price in Credits (1 Credit = ¥1); green marks the better side. Uptime and latency come from KumoAPI probes; a dash means the model is not probed yet.
Capabilities
FAQ
Which is cheaper, GPT-5 or GPT-5.6 Luna?
At the KumoAPI default channel price, GPT-5 input costs 1.25 Credits / M and GPT-5.6 Luna input costs 0.2 Credits / M, so GPT-5.6 Luna is 84% cheaper. Output and cache prices are in the specs table above.
Which has the larger context window, GPT-5 or GPT-5.6 Luna?
GPT-5 offers 400K tokens, GPT-5.6 Luna offers 1.05M tokens.
Can I switch between GPT-5 and GPT-5.6 Luna at any time?
Yes. KumoAPI calls every model with the same API key; switching is just changing the model field in the request, and billing is split per model in one console.
How do the capabilities of GPT-5 and GPT-5.6 Luna differ?
Their capability flags are identical. Every other capability is either supported by both or by neither; see the capability table above.
More comparisons
One API key for both GPT-5 and GPT-5.6 Luna
Free credits on sign-up, pay as you go, no monthly fee.