OpenAIAuto-detectedGPT 5.6 Luna Pro
Not yet ranked: too few independent results so far.
- Blended price
- $0.450/M
- $0.200 in · $1.20 out
- Output speed
- 107 tok/s
- First answer
- 9.42 s
- Context
- 1.1M
No independent quality benchmark results yet — only pricing and metadata.
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| OpenAI Fast | 209 tok/s | 7.41 s | $0.400 | $2.40 | 1.1M | – |
| Azure (EU) | 129 tok/s | 8.98 s | $0.220 | $1.32 | 1.1M | – |
| OpenAI | 107 tok/s | 9.42 s | $0.200 | $1.20 | 1.1M | – |
| Azure | 102 tok/s | 16 s | $0.200 | $1.20 | 1.1M | – |
| OpenAI Flex | 87 tok/s | 55 s | $0.100 | $0.600 | 1.1M | – |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0004 | – | 12.2 s |
| Summarise a 30-page report | 12,000 / 600 | $0.0031 | – | 15.0 s |
| Code edit | 6,000 / 1,500 | $0.0030 | – | 23.4 s |
| Agentic coding session | 60,000 / 4,000 | $0.017 | – | 46.8 s |
| Structured extraction | 2,000 / 200 | $0.0006 | – | 11.3 s |
See also
Data as of 9 Sept 2026. Compare with another model.