GPT 5.6 Luna API price
openai/gpt-5.6-luna
The cheapest GPT 5.6 Luna API is $0.08/M input at Cheaper Inference (discount marketplace) - all 7 providers compared below, per 1M tokens.
SmallOpenAI1.1M context7 sellers
Input
$0.08
per 1M tokens · Cheaper Inference (discount marketplace)
up to $0.22
Output
$0.48
per 1M tokens · Cheaper Inference (discount marketplace)
up to $1.32
Where to buy it
Cheapest GPT 5.6 Luna API providers compared - 7 sellers, from $0.08/M.
Cost calculator
| Provider | Input $/M | Output $/M | Cached in | Uptime | Your cost |
|---|---|---|---|---|---|
| Cheaper Inference (discount marketplace)60% off | 0.080cheapest | 0.480 | 0.0080 | - | |
| Official - OpenAI | 0.200 | 1.20 | 0.020 | - | |
| Batch | 0.100 | 0.600 | 0.010 | - | |
| Flex | 0.100 | 0.600 | 0.010 | - | |
| Priority | 0.400 | 2.40 | 0.040 | - | |
| OrcaRouter (aggregator) | 0.200 | 1.20 | - | - | |
| Azure (via OpenRouter) | 0.200 | 1.20 | 0.020 | 100% | |
| OpenAI (via OpenRouter) | 0.200 | 1.20 | 0.020 | 100% | |
| Flex | 0.100 | 0.600 | 0.010 | 100% | |
| TokenRouter (aggregator) | 0.200 | 1.20 | 0.020 | - | |
| Amazon Bedrock (via OpenRouter) (us-east-1) | 0.220 | 1.32 | 0.022 | 100% |
2.8× between the cheapest and the dearest of 7 sellers.
Against its tier
- This model$0.56
- Cheapest · Nemotron 3.5 Lightning$0.145
- Tier median · Qwen 3.8 Omni Flash$0.62
- Dearest · GPT 5.4 Mini (03-17 snapshot)$5.25
#9 of 19 small · cheaper than 56%
Details
- Context window
- 1.1M1,050,000 tokens
- Developer
- OpenAI
- Intelligence
- 37.3 Max
- Sellers
- 72.8× spread
- Cached input
- $0.008where the source publishes one
- Cheapest at
- Cheaper Inference (discount marketplace)
- Combined
- $0.56in + out per 1M
- Last checked
- 2026-10-12
- Availability
- 100.00%median of 7 OpenRouter endpoints, last 30 min