GPT-5.6 Luna Pro
OpenAI · Proprietary · Released Jul 9, 2026 · openai/gpt-5.6-luna-pro
Best $0.20 in / $1.20 out via OpenAI
1.05M contextVisionToolsReasoningStructured outputPrompt caching
Available from 4 providersUSD / MTOK · PRICES 15 MINUTES AGO · SPEED 13 DAYS AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
| $0.10 | $0.60 | $0.01 | 1.05M | — | 10.4s | 739 tok/s | 100.0% | |
| $0.20 | $1.20 | $0.02 | 1.05M | — | — | — | 100.0% | |
| $0.20 | $1.20 | $0.02 | 1.05M | — | 7s | 1731 tok/s | 100.0% | |
| $0.40 | $2.40 | $0.04 | 1.05M | — | — | — | — |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 13 days ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Pricing variants · USD / MTok in / out
STANDARD
$0.20 / $1.20
per MTok in / out
BATCH
$0.10 / $0.60
async batch
CACHE READ $0.02CACHE WRITE $0.25WEB SEARCH $0.01 / search
Recent changesRSS ↗
Nov 1, 2026endpoint removed · cheaperinference6 → 5
Oct 31, 2026endpoint added · cheaperinference5 → 6
About
GPT-5.6 Luna Pro is the same underlying model as GPT-5.6 Luna, served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...
Specifications
Context window1,050,000
Max output128,000
Modalities infile, image, text
Modalities outtext
LicenseProprietary
ReleasedJul 9, 2026
Knowledge cutoff2026-02-16
TokenizerGPT
Related
Embed badge
[](https://modelindex.ai/models/openai/gpt-5.6-luna-pro)Sources
OpenRouter API15 minutes ago
AGGREGATORModelIndex benchmarks15 days ago
MEASUREDVerified 15 minutes ago · list prices, not negotiated rates.