GPT-6 Luna Pro
OpenAI · Proprietary · Released Sep 22, 2026 · openai/gpt-6-luna-pro
Best $0.10 in / $0.50 out via OpenAI
1.05M contextVisionToolsReasoningStructured outputPrompt caching
Available from 6 providersUSD / MTOK · PRICES 20 MINUTES AGO · SPEED 7 DAYS AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
 OpenAIFLEX1ST PARTY | $0.05 | $0.25 | $0.005 | 1.05M | — | 4.2s | 735 tok/s | 99.5% |
| OpenAI1ST PARTY | $0.10 | $0.50 | $0.01 | 1.05M | — | — | — | 100.0% |
 Azure | $0.10 | $0.50 | $0.01 | 1.05M | — | 5.4s | 881 tok/s | 100.0% |
| Azure | $0.11 | $0.55 | $0.011 | 1.05M | — | — | — | 100.0% |
| Azure | $0.11 | $0.55 | $0.011 | 1.05M | — | — | — | 100.0% |
| OpenAIPRIORITY1ST PARTY | $0.20 | $1.00 | $0.02 | 1.05M | — | — | — | 100.0% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 7 days ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Pricing variants · USD / MTok in / out
STANDARD
$0.10 / $0.50
per MTok in / out
BATCH
$0.05 / $0.25
async batch
CACHE READ $0.01CACHE WRITE $0.125WEB SEARCH $0.01 / search
Recent changesRSS ↗
Sep 23, 2026model added
About
GPT-6 Luna Pro is the same underlying model as GPT-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
ReleasedSep 22, 2026
TokenizerGPT
Related
Embed badge
[](https://modelindex.ai/models/openai/gpt-6-luna-pro)Sources
OpenRouter API20 minutes ago
AGGREGATORModelIndex benchmarks11 days ago
MEASUREDVerified 20 minutes ago · list prices, not negotiated rates.