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...
Input / 1M
$0.20
Output / 1M
$1.20
Context
1.0M
AA Intelligence
37.3
Closed weights — available only as a hosted API
file + image + text → text
Knowledge cutoff Feb 2026
View on OpenRouter ↗
Pricing
via OpenRouter · USD per 1M tokens · synced 2026-10-24$0.20
input / 1M
$1.20
output / 1M
$0.02
cached input / 1M
$1.40
1M in + 1M out
:batch variant
$0.10 in · $0.60 out
Price tiers
- Above 272K prompt tokens: input $0.40/M, output $1.80/M (2× base)
- Context window
- 1,050,000 tokens
- Max output
- 128,000 tokens
- Providers
- 3
- Cheapest provider
- OpenAI · $0.10 / $0.60
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- 37.3 / 71.4 / 42.1
✓ Tool calling
✓ Reasoning
✓ Structured outputs
✓ Image input
✓ File input
✗ Audio input
✓ Prompt caching
Price history
tracking started — chart appears after 7 days of snapshots (6 recorded)Current: $0.20 input · $1.20 output per 1M tokens
Benchmarks
Third-party indices as published through OpenRouter — Artificial Analysis and Design Arena. Not measured by us.
- AA Intelligence Index
- 37.3
- AA Coding Index
- 71.4
- AA Agentic Index
- 42.1
Providers
3 providers · per 1M tokens · last 30 min metrics| Provider | Quant | Context | Input | Output | Uptime | Tok/s |
|---|---|---|---|---|---|---|
| OpenAI | unknown | 1.0M | $0.10 | $0.60 | 100% | — |
| Azure | unknown | 1.0M | $0.20 | $1.20 | 100% | — |
| OpenAI | unknown | 1.0M | $0.20 | $1.20 | 100% | — |
| Amazon Bedrock | unknown | 1.0M | $0.22 | $1.32 | 100% | — |
| Azure | unknown | 1.0M | $0.22 | $1.32 | 100% | — |
| Azure | unknown | 1.0M | $0.22 | $1.32 | — | — |
| OpenAI | unknown | 1.0M | $0.40 | $2.40 | 100% | — |
Provider data from OpenRouter's endpoint listing, refreshed daily.
Specifications
- Organisation
- openai
- Released on OpenRouter
- 2026-07-09
- Context window
- 1,050,000 tokens
- Max output
- 128,000 tokens
- Input
- file, image, text
- Output
- text
- Knowledge cutoff
- February 2026
- Tokenizer
- GPT
- Moderated by provider
- Yes
- OpenRouter id
- openai/gpt-5.6-luna
Compare with
Popular comparisons
Prices, context and providers from the public OpenRouter API, snapshotted daily; benchmark indices from Artificial Analysis. See /methodology.