GPT-5.6 Terra
OpenAI · released Jul 9, 2026
- Type
- Proprietary
- Input
- $2.00
- Output
- $12.00
- Cached
- Not published
List price · per 1M tokens · OpenAI at 1.1M context · source ↗ · a reseller below undercuts it; the table carries the spread
Our take
Written Aug 2, 2026GPT-5.6 Terra is OpenAI's flagship hosted model that can handle up to 1.05 million tokens in a single request, accepting text, images and files. It offers a wide cost range across its tiers and scores strongly on coding leaderboards, though its creative writing and agentic task results lag well behind.
Choose this for long-document or codebase analysis at million-token scale, or for budget-conscious coding through OpenAI's entry tier with competitive throughput. It suits teams who want to trade speed against cost within the same model family. Skip it if you need strong creative writing output, reliable agentic task performance, or guaranteed throughput on every provider tier.
The case for it
- Extremely large request limit at 1,050,000 tokens, rare among hosted models for long-document and codebase work.
- Consistently strong measured coding performance: around 1520–1522 Elo on Arena Code leaderboards across multiple days.
- Wide price range lets users trade speed and cost, with a tenfold spread on input rates between entry and premium tiers.
- Competitive throughput on lower-cost tiers, at 95–99 tokens per second.
The case against it
- Creative writing scores 92.72 Elo points below its own coding performance, a notable gap within the same model.
- Agentic task performance is weak in absolute terms, at under 4% on the Arena Agent benchmark.
- Throughput drops on some higher-priced tiers, falling to 43–48 tokens per second despite paying more.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)22nd of 143 · 1467.8via xHigh
CodingWriting and fixing code on its own
Arena Coding14th of 143 · 1520.2via xHigh
AgenticPlanning, calling tools, staying on task
Arena Agent (IPS)12th of 36 · 0.035via xHigh
WritingWe do not rate this
Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage. So we show where GPT-5.6 Terra placed and give it no mark out of five.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done, which is why they get no rating.
Every published score for this model16 scoresEvery figure we hold, from 16 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Or rent it from someone else
Why this differs from the header. The strip above quotes OpenAI's own list price. This is the cheapest live offer at the widest standard context we hold, whoever is serving it — a reseller undercutting a lab is ordinary commerce, not an error.
- per 1M tokens
- $1.00 in / $6.00 out
- Context served
- 1.1M
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenAIflex tier | $0.50 / $3.00 | 1.1M | 71 tok/s | No | Yesunknown period | Unknown |
| OpenRouter | $1.00 / $6.00 | 1.1M | not measured | Unknown | Unknown | Unknown |
| OpenAI | $2.00 / $12.00 | 1.1M128K out | not measured | No | Yesunknown period | Unknown |
| Amazon Bedrockus-east-1 | $2.20 / $13.20 | 1.1M | 99 tok/s | No | No | Unknown |
| Microsoft Azure AI | $2.50 / $15.00 | 1.1M | 58 tok/s | No | No | Confirmed |
| Microsoft Azure AIeu | $2.75 / $16.50 | 1.1M | 7 tok/s | No | No | Confirmed |
| OpenAIpriority tier | $5.00 / $30.00 | 1.1M | not measured | No | Yesunknown period | Unknown |
Amazon Bedrock
Microsoft Azure AIAcross the 7 listings we hold: 6 say they do not train on prompts, 0 say they do and 1 do not say. 2 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenAIflex | ✓ | ✓ | ✓ |
| OpenRouter | ✓ | ✓ | ✓ |
| OpenAI | ✓ | ✓ | ✓ |
| Amazon Bedrockus-east-1 | ✓ | ✗ | ✗ |
| Microsoft Azure AI | ✓ | ✓ | ✓ |
| Microsoft Azure AIeu | ✓ | ✓ | ✓ |
| OpenAIpriority | ✓ | ✓ | ✓ |
Tool calling: 7 of 7 listings say yes. JSON output: 6 of 7 listings say yes, 1 says no. Strict schema: 6 of 7 listings say yes, 1 says no.
When we formed this view
Dates behind this page
Prices last checked 9d ago
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 7 listings do not say whether they train on prompts.
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
Commercial API terms. We hold no licence record for this model, so there is nothing to summarise here.
Identifiers
- Modality record
- text+image+file->text
- Catalogue slug
- openai-gpt-5-6-terra