GPT 5.6 Luna
GPT 5.6 Luna is served by 2 providers that kRouter can route to, with a 272K-token context window and pricing from $3.00 per 1M input tokens. Because more than one provider offers it, the price you pay depends on which one you route to — the same request, the same model, different bills.
Where to get GPT 5.6 Luna
| Provider | Route as |
|---|---|
| Kiro AI | kr/gpt-5.6-luna |
| OpenCode Go | opencode-go/gpt-5.6-luna |
What GPT 5.6 Luna is suited for
A 272K window comfortably holds a long file plus its surrounding context, which covers most day-to-day coding turns without compaction. It supports extended reasoning, which helps on debugging and multi-step planning but spends output tokens on thinking before the answer appears — worth knowing when you set max_tokens. Tool and function calling are supported, so it can drive an agent loop. It accepts images, so screenshots and diagrams can go straight into the prompt. Cached input is billed at $1.50 against $3.00 fresh, which is the difference that matters most for agent work — the same context is resent on every turn.
Specs
- Context window
- 272K
- Max output
- 128K
- Input / 1M
- $3.00
- Output / 1M
- $12.00
- Extended reasoning
- Image input
- Tool / function calling
Cheaper alternatives to GPT 5.6 Luna
Comparable capabilities at a lower rate. With a kRouter combo you can send routine turns to one of these and reserve GPT 5.6 Luna for the work that actually needs it.
- Gemini 2.5 Pro$2.00 in · $12.00 out per 1M
- Gemini 3 Pro Preview$2.00 in · $12.00 out per 1M
- Gemini 3.1 Pro (Low)$2.00 in · $12.00 out per 1M
- Claude Sonnet 5$2.00 in · $10.00 out per 1M
GPT 5.6 Luna FAQ
How much does GPT 5.6 Luna cost?
GPT 5.6 Luna is $3.00 per 1M input tokens and $12.00 per 1M output tokens. Cached input is $1.50, which matters a lot for agent work that resends the same context each turn.
Which providers serve GPT 5.6 Luna?
2 providers: Kiro AI, OpenCode Go. Through kRouter you can switch between them by changing the route prefix, without changing your tool.
What is GPT 5.6 Luna's context window?
272K tokens, with up to 128K tokens of output. kRouter publishes this on /v1/models as context_length, so clients read the real number instead of guessing from the model name.
Is there a cheaper alternative to GPT 5.6 Luna?
Yes — Gemini 2.5 Pro ($2.00/1M in), Gemini 3 Pro Preview ($2.00/1M in), Gemini 3.1 Pro (Low) ($2.00/1M in), Claude Sonnet 5 ($2.00/1M in) are cheaper with comparable capabilities. A kRouter combo can send routine turns to one of those and keep GPT 5.6 Luna for the work that needs it.
Route to GPT 5.6 Luna from any tool
kRouter runs locally and gives Claude Code, Cursor, Codex and the rest one endpoint that reaches every provider above — with automatic failover. Free and MIT-licensed.
Install kRouter