GPT-5.6-luna (short context) pricing
GPT-5.6-luna (short context), Small-tier from Azure OpenAI Service, costs $0.20 per 1M input tokens and $1.20 per 1M output tokens.
Input$0.20per 1M tokens
Output$1.20per 1M tokens
Context window—tokens
TierSmallAzure OpenAI Service
Price your own workload against GPT-5.6-luna (short context) in the calculator →
Specs and pricing
| Provider | Azure OpenAI Service |
| Tier | Small |
| Context window | — |
| Max output | — |
| Input price | $0.20 / 1M tokens |
| Output price | $1.20 / 1M tokens |
| Cache write | $0.25 / 1M tokens |
| Cache read | $0.02 / 1M tokens |
| Modalities | text |
Note. Global Standard tier, short-context row; USD per 1M tokens as published.
What it costs at realistic volumes
Assuming a 4:1 input:output token ratio, a common shape for chat and RAG-style workloads:
| Volume (4:1 in:out ratio) | Input cost | Output cost | Total / month |
|---|---|---|---|
| 1,000,000 in / 250,000 out | $0.20 | $0.30 | $0.50 |
| 10,000,000 in / 2,500,000 out | $2.00 | $3.00 | $5.00 |
| 100,000,000 in / 25,000,000 out | $20.00 | $30.00 | $50.00 |
Cheaper alternatives
Same tier (Small), a different provider, and a lower blended cost at the 4:1 ratio used above:
| Model | Provider | $/1M in | $/1M out | At the 4:1 ratio |
|---|---|---|---|---|
| Meta-Llama-3.1-8B-Instruct-Turbo | DeepInfra | $0.02 | $0.04 | 94% cheaper blended |
| Solar Pro 4 | OpenRouter | $0.03 | $0.12 | 88% cheaper blended |
| GPT-OSS 20B | OpenRouter | $0.03 | $0.13 | 87.5% cheaper blended |
| schematron-v2-turbo | inference.net | $0.03 | $0.15 | 86.5% cheaper blended |
| Amazon Nova Micro | Amazon (Nova) | $0.035 | $0.14 | 86% cheaper blended |