GPT-5.6 Luna pricing across providers
Across tracked provider offerings, input runs $0.180–$0.220 per million tokens and output $1.10–$1.32 per million tokens. The cheapest tracked provider offering for a typical agentic mix (2.5% input, 97% cached input, 0.5% output) is Singularity at $0.029 per million tokens.
Prices are USD per million tokens and reflect each provider offering — they are not a single intrinsic model price. 6 of 6 offerings publish a cache-read rate; 3 of 6 publish a 30-minute endpoint uptime figure.
Open the calculator filtered to GPT-5.6 Luna
Is this the right model for your workload? Compare open-weight picks and providers for your use case →
Daily price history
Loading price history…
Daily snapshots are retained for up to 90 days; history begins with the first recorded snapshot.
Provider offerings for GPT-5.6 Luna
Ranked by effective cost at a typical agentic mix. Quantized and tier variants stay separate rows.
| Provider | Quant | Input $/M | Output $/M | Cache $/M | Blended $/M | Uptime (30m) |
|---|---|---|---|---|---|---|
| Singularity | — | $0.180 | $1.10 | $0.020 | $0.029 | — |
| Azure | unknown | $0.200 | $1.20 | $0.020 | $0.032 | 100.00% |
| Openai | unknown | $0.200 | $1.20 | $0.020 | $0.032 | 100.00% |
| OpenCode | — | $0.200 | $1.20 | $0.020 | $0.032 | — |
| Aws Mantle | — | $0.220 | $1.32 | $0.022 | $0.035 | — |
| Amazon | unknown | $0.220 | $1.32 | $0.022 | $0.035 | 100.00% |
Provider-offering pricing refreshed 2026-10-29. Uptime is the 30-minute endpoint metric where a provider publishes it. Verify rates on the provider's official pricing page before committing spend.