Models / OpenAI / GPT-5.6 Luna
OpenAI · gpt-luna
GPT-5.6 Luna
Cost-efficient GPT-5.6 model for fast, high-volume workloads
$0.20 in · $1.20 out
per 1M tokens · first-party price. Reference price from OpenAI, the lab's own listing.
Provider input prices run from $0.06 to $1.00 per 1M tokens. Output prices run from $0.37 to $6.00.
- Context
- 1,050,000
- Max output
- 128,000
- Cache read
- $0.02
- Cache write
- $0.25
- Reasoning
- Yes
- Tool calls
- Yes
- Structured output
- Yes
- Vision
- Yes
- Open weights
- No
- License
- —
- Released
- Jul 9, 2026
- Updated in source
- Jul 9, 2026
- Knowledge
- 2026-02-16
- Providers
- 44
Higher rates apply above 200,000, 272,000 input tokens. The calculator switches to that rate when the input is longer.
Providers
| Provider | Input | Output | Cache read | Cache write | Status |
|---|---|---|---|---|---|
| Bothub | $0.06 | $0.37 | — | — | — |
| 302.AI | $0.20 | $1.20 | — | — | — |
| Aixy | $0.20 | $1.20 | $0.02 | $0.25 | — |
| Azure | $0.20 | $1.20 | $0.02 | $0.25 | — |
| Cloudflare AI Gateway | $0.20 | $1.20 | $0.02 | $0.25 | — |
| CrossModel | $0.20 | $1.20 | $0.02 | $0.25 | — |
| DevPass | $0.20 | $1.20 | $0.02 | $0.25 | — |
| DigitalOcean | $0.20 | $1.20 | $0.02 | — | — |
| Eden AI | $0.20 | $1.20 | $0.02 | $0.25 | — |
| GitHub Copilot | $0.20 | $1.20 | $0.02 | $0.25 | — |
| Impossibl | $0.20 | $1.20 | $0.02 | $0.25 | — |
| Kilo Gateway | $0.20 | $1.20 | $0.02 | $0.25 | — |
| LLM Gateway | $0.20 | $1.20 | $0.02 | $0.25 | — |
| Merge Gateway | $0.20 | $1.20 | $0.02 | $0.25 | — |
| NanoGPT | $0.20 | $1.20 | $0.02 | $0.25 | — |
| NEAR AI Cloud | $0.20 | $1.20 | $0.02 | — | — |
| Neon | $0.20 | $1.20 | $0.02 | $0.25 | — |
| Ofox | $0.20 | $1.20 | $0.02 | $0.25 | — |
| OpenAIreference | $0.20 | $1.20 | $0.02 | $0.25 | — |
| OpenCode | $0.20 | $1.20 | $0.02 | $0.25 | — |
| OpenCode Go | $0.20 | $1.20 | $0.02 | $0.25 | — |
| OpenRouter | $0.20 | $1.20 | $0.02 | $0.25 | — |
| Opper | $0.20 | $1.20 | $0.02 | $0.25 | — |
| OrcaRouter | $0.20 | $1.20 | $0.02 | $0.25 | — |
| Prime Inference | $0.20 | $1.20 | — | — | — |
| Requesty | $0.20 | $1.20 | $0.02 | $0.25 | — |
| Vercel AI Gateway | $0.20 | $1.20 | $0.02 | $0.25 | — |
| Cortecs | $0.22 | $1.32 | $0.022 | $0.28 | — |
| Amazon Bedrock | $0.22 | $1.32 | $0.022 | $0.28 | — |
| Venice AI | $0.25 | $1.50 | $0.025 | $0.31 | — |
| AI/ML API | $0.26 | $1.56 | $0.026 | — | — |
| routing.run | $0.70 | $4.20 | — | — | — |
| Abacus | $1.00 | $6.00 | $0.10 | — | — |
| AI-ROUTER | $1.00 | $6.00 | $0.10 | $1.25 | — |
| AIHubMix | $1.00 | $6.00 | $0.10 | $1.25 | — |
| Azure Cognitive Services | $1.00 | $6.00 | $0.10 | $1.25 | — |
| Databricks | $1.00 | $6.00 | $0.10 | — | — |
| Pioneer | $1.00 | $6.00 | $0.10 | $1.25 | — |
| SAP AI Core | $1.00 | $6.00 | $0.10 | — | — |
| Vivgrid | $1.00 | $6.00 | $0.10 | $1.25 | — |
| ZenMux | $1.00 | $6.00 | $0.10 | $1.25 | — |
| GitLab Duo | $0 | $0 | $0 | $0 | — |
| Kenari | $0 | $0 | — | — | — |
| Snowflake Cortex | — | — | — | — | beta |
Jobs this model qualifies for
- Coding agents — budget pick on that draft page
- Long-document Q&A — clears the bar
- Cheapest summarization — clears the bar