GPT-5.6 Terra
OpenAI · released Jul 9, 2026
- Type
- Closed
- Input
- $2.00
- Output
- $12.00
- Cached
- $0.20
List price · per 1M tokens · OpenAI at 922K context · machine-readable source ↗
Our take
Written Sep 17, 2026GPT-5.6 Terra is a hosted-only model: we list no download for it, so using it means choosing a host. Its strongest evidence is on set-piece maths and reasoning, and it is the expensive end of the market to run at scale.
Reach for it when measured maths and reasoning quality matters more than the bill, or when long documents would otherwise need splitting before you can ask about them. It also takes images and files alongside the question. Skip it if you need to run the model on your own machine, or if cost per token is the deciding factor.
The case for it
- 94.91% on LiveBench Mathematics and 90.63% on Reasoning, both averages over competition-style problems rather than fixing issues in an existing project.
- The request capacity is large enough that long documents need not be split up first, though reliable recall across all of it is unverified in our data.
- Text, image and file input with written output, so a screenshot or a document does not have to be described in words first.
The case against it
- The cheapest listed offer sits at the top of the market, and the other hosts listed are at double that rate or above.
- Agentic coding is its weakest measured category, at 54.95% on LiveBench Agentic Coding inside an agent harness, so it reflects the model working within that scaffold rather than alone.
- We list no download for it, so using it means choosing a host.
How good is it?
A closed text model from OpenAI for everyday questions, coding and tool use, with strong steerability.
- getting answers to everyday questionsArena Text (overall) · 34th of 168
- writing and completing codeArena Coding · 28th of 168
- calling tools to carry out requestsArena Agent · Tool use · 9th of 55
- changing course when you give new instructionsArena Agent · Steerability · 13th of 55
EverydayGeneral questions and everyday reasoning
Arena Text (overall)34th of 168 · 1465
CodingWriting and fixing code on its own
Arena Coding28th of 168 · 1516
AgenticPlanning, calling tools, staying on task
Arena Agent24th of 55 · 0.008
WritingDrafting and rewriting prose
Arena Creative Writing46th of 168 · 1428
Placings on Arena's agent boards, from live sessions people ran themselves. A model can lead on one of these and sit mid-field on the others.
Boards this model appears on that none of the ratings above are built on.
Every published score for this model20 scoresEvery figure we hold, from 20 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Where to rent it
Prices checked 4 hours ago — each listing carries its own date.
Microsoft Azure AI, through OpenRouter
Why this differs from the header. The strip above quotes OpenAI's own list price; this is the cheapest live offer, whoever is serving it — a reseller undercutting a lab is ordinary commerce, not an error.
- per 1M tokens
- $2.00 in / $12.00 out
- Context served
- 1.1M
- Throughput
- ~54 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenAIflex tierThrough OpenRouter | $1.00 / $6.00checked 4 hours ago | 1.1M128K max reply | 84 tok/s | No | Yesunknown period | Unknown |
| Microsoft Azure AIThrough OpenRouter | $2.00 / $12.00checked 4 hours ago | 1.1M128K max reply | 54 tok/s | No | No | Confirmed |
| OpenRouterOpenRouter's own listing | $2.00 / $12.00checked 4 hours ago | 1.1M | not measured | Unknown | Unknown | Unknown |
| OpenAIDirect | $2.00 / $12.00checked 4 hours ago | 922K128K max reply | 46 tok/s | No | Yesunknown period | Unknown |
| Microsoft Azure AIeuThrough OpenRouter | $2.20 / $13.20checked 4 hours ago | 1.1M128K max reply | 80 tok/s | No | No | Confirmed |
| Amazon Bedrockus-east-1Through OpenRouter | $2.20 / $13.20checked 4 hours ago | 1.1M128K max reply | 89 tok/s | No | No | Unknown |
| Microsoft Azure AIusThrough OpenRouter | $2.20 / $13.20checked 4 hours ago | 1.1M128K max reply | 23 tok/s | No | No | Confirmed |
| OpenAIfast tierThrough OpenRouter | $4.00 / $24.00checked 4 hours ago | 1.1M128K max reply | 104 tok/s | No | Yesunknown period | Unknown |
OpenRouter
Amazon BedrockAcross the 8 listings we hold: 7 say they do not train on prompts, 0 say they do and 1 does not say. 3 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 |
|---|---|---|---|
| OpenAIflexThrough OpenRouter | ✓ | ✓ | ✓ |
| Microsoft Azure AIThrough OpenRouter | ✓ | ✓ | ✓ |
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| OpenAIDirect | ✓ | ✓ | ✓ |
| Microsoft Azure AIeuThrough OpenRouter | ✓ | ✓ | ✓ |
| Amazon Bedrockus-east-1Through OpenRouter | ✓ | ✗ | ✗ |
| Microsoft Azure AIusThrough OpenRouter | ✓ | ✓ | ✓ |
| OpenAIfastThrough OpenRouter | ✓ | ✓ | ✓ |
Tool calling: 8 of 8 listings say yes. JSON output: 7 of 8 listings say yes, 1 says no. Strict schema: 7 of 8 listings say yes, 1 says no.
When we formed this view
Recent changes
Each 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
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 8 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-terra