gpt-5.6-luna API — compare providers
The same model (gpt-5.6-luna) is served by 3 providers; OpenAI is the cheapest at $0.7/1M blended — the priciest (Amazon Bedrock) costs 120% more.
Quality and intelligence scores are attached to the model itself — identical whichever provider serves it.
| Rank | Provider | Input /1M | Output /1M | Blended /1M |
|---|---|---|---|---|
| 1 | OpenAI | $0.1 | $0.6 | $0.7 ← cheapest |
| 2 | Azure OpenAI | $0.2 | $1.2 | $1.4 |
| 3 | Amazon Bedrock | $0.22 | $1.32 | $1.54 |
Prices are per 1M tokens (USD). "Blended" = input + output, for coarse ranking. Same underlying model, 3 serving providers, 120% spread top to bottom. Context window: 400,000 tokens (128,000 max output) — see how it ranks in biggest context windows. See how this compares across the catalogue in same model, different price.
Cost per 1,000 requests by workload
What each provider actually bills for a representative job, not just the sticker price.
| Provider | Chatbot 1000 in / 500 out | RAG / long context 8000 in / 500 out | Batch summarize 4000 in / 1000 out |
|---|---|---|---|
| OpenAI | $0.40 | $1.10 | $1.00 |
| Azure OpenAI | $0.80 | $2.20 | $2.00 |
| Amazon Bedrock | $0.88 | $2.42 | $2.20 |
Estimate your own workload
Input tokens/request: Output tokens/request: Requests:
| Provider | Estimated cost (USD) |
|---|