GPT-5.6 Luna Pro
OpenAI · released Jul 9, 2026
- Type
- Closed
- Input
- $0.20
- Output
- $1.20
- Cached
- $0.020
List price · per 1M tokens · OpenAI at 1.1M context · source ↗
Our take
Written Sep 2, 2026GPT-5.6 Luna Pro is a proprietary multimodal model from OpenAI that can handle up to 1.05 million tokens in a single request. It accepts text, images and files, and is built for long-document and high-volume workloads where context length matters most.
Pick this when you need one of the longest request limits we track for summarising books, codebases or legal files in one pass. It suits cost-sensitive long-document work at the base tier, or throughput-sensitive tasks where 201 tokens per second justifies paying twice the base rate. Skip it if you need verified quality scores, want to self-host, or if your workload fits a smaller window.
The case for it
- Exceptionally long request limit at 1.05 million tokens — four times some mid-size alternatives and eight times earlier frontier norms.
- Seven offers with a tenfold price range, giving granular throughput choice from a budget entry point upward.
- Fastest measured throughput at the mid-tier: 201 tokens per second, quicker than the Azure options we hold.
The case against it
- No verified quality scores in our data — chat, reasoning, coding and multimodal performance all unverified.
- Premium tiers carry steep penalties for modest or undisclosed speed gains: twice the base price for 201 tokens per second, and ten times base with no published speed guarantee on the top tier.
- Proprietary weights with no local deployment, no fine-tuning, and limited provider portability beyond OpenAI and Azure.
How good is it?
We hold no score for this model.
So there is no figure here for everyday use, coding, agent work or writing. That is a gap in our data, not a low score.
Where to rent it
Prices checked between 4 hours and 2 months ago — each listing carries its own date.
OpenAI, through OpenRouter
The lab is also the cheapest we hold. The strip above and this offer are the same one, so nothing on this page undercuts OpenAI on 1.1M of context.
- per 1M tokens
- $0.20 in / $1.20 out
- Context served
- 1.1M
- Throughput
- ~111 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.20 / $1.20checked 4 hours ago | 1.1M | not measured | Unknown | Unknown | Unknown |
| OpenAIThrough OpenRouter | $0.20 / $1.20checked 4 hours ago | 1.1M128K max reply | 111 tok/s | No | Yesunknown period | Unknown |
| Microsoft Azure AIeuThrough OpenRouter | $0.22 / $1.32checked 4 hours ago | 1.1M128K max reply | 142 tok/s | No | No | Confirmed |
| OpenAIfast tierThrough OpenRouter | $0.40 / $2.40checked 4 hours ago | 1.1M128K max reply | 225 tok/s | No | Yesunknown period | Unknown |
| OpenAIflex tierThrough OpenRouter | $0.50 / $3.00checked 2 months ago | 1.1M | not measured | No | Yesunknown period | Unknown |
| Microsoft Azure AIThrough OpenRouter | $1.00 / $6.00checked 52 days ago | 1.1M | not measured | No | No | Confirmed |
OpenRouter
Microsoft Azure AIAcross the 6 listings we hold: 5 say they do not train on prompts, 0 say they do and 1 does not say. 2 appear in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| OpenAIThrough OpenRouter | ✓ | ✓ | ✓ |
| Microsoft Azure AIeuThrough OpenRouter | ✓ | ✓ | ✓ |
| OpenAIfastThrough OpenRouter | ✓ | ✓ | ✓ |
| OpenAIflexThrough OpenRouter | ✓ | ✓ | ✓ |
| Microsoft Azure AIThrough OpenRouter | ✓ | ✓ | ✓ |
Tool calling: 6 of 6 listings say yes. JSON output: 6 of 6 listings say yes. Strict schema: 6 of 6 listings say yes.
Models people weigh against GPT-5.6 Luna Pro
When we formed this view
Recent changes
What moved
input −80% ($1.10 → $0.22 per 1M tokens), output −80% ($6.60 → $1.32 per 1M tokens), cache read −80% ($0.110 → $0.022 per 1M tokens), cache write −80% ($1.38 → $0.28 per 1M tokens)What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- No independent board has scored it, so we hold no quality figures at all.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 6 listings does not say whether it trains on prompts.
- We hold no batch or off-peak rate for any of its listings.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
We hold no licence record for this model, and no record of published weights either — so we can neither summarise its terms nor point you at the weights.
Identifiers
- Takes in, gives back
- Text, images and documents in, text out
- Catalogue slug
- openai-gpt-5-6-luna-pro