OpenAI: GPT-5.6 Terra
GPT-5.6 Terra is a reasoning model from OpenAI released on Jul 9, 2026. It reads text, images and files and writes text, with a 1.05M token context window and up to 128K tokens per reply.
Show moreShow less
It costs $2 per million input tokens and $12 per million output tokens. Cached input bills at $0.20, 90% less than fresh input.
It supports tool calling, structured JSON output and prompt caching.
38 providers serve it, including Azure, Amazon Bedrock and Databricks. The lowest input price is $1.50 per million tokens at routing.run.
On the Artificial Analysis Intelligence Index it scores 42.1, which places it at number 13 among the 43 models I track with independent scores.
- Modalities
- In / out price
- $2 / $12 per 1M
- Context
- 1.05M
- Max output
- 128K
- Released
- Jul 9, 2026
- Knowledge cutoff
- Feb 2026
- Tool calling
- Structured output
- Reasoning
- Prompt caching
- Open weights
- Free to use
GPT-5.6 Terra pricing
USD, as listed on Oct 15, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.
| Input | $2 / 1M tokens | |
|---|---|---|
| Output | $12 / 1M tokens | |
| Cached input (read) | $0.20 / 1M tokens | 90% off input |
| Cache write | $2.50 / 1M tokens | |
| Prompts over 200K | $4 in, $18 out | long context rate |
| Prompts over 272K | $4 in, $18 out | long context rate |
GPT-5.6 Terra providers
38 providers serve it, including Azure, Amazon Bedrock and Databricks. The lowest input price is $1.50 per million tokens at routing.run. Each host sets its own price and limits, so the cheapest one is not always the one with the longest context.
| Provider | Input /M | Output /M | Cache read /M | Context | Max output |
|---|---|---|---|---|---|
| OpenAI First party | $2 | $12 | $0.20 | 1.05M | 128K |
| Azure | $2 | $12 | $0.20 | 1.05M | 128K |
| Amazon Bedrock | $2.20 | $13.20 | $0.22 | 1.05M | 128K |
| Databricks | $2.50 | $15 | $0.25 | 1.05M | 128K |
| Vercel AI Gateway | $4 | $24 | $0.40 | 1.05M | 128K |
| Snowflake Cortex | n/a | n/a | – | 1.05M | 128K |
| routing.run | $1.50 | $9 | – | 1M | 128K |
| Xpersona | $1.50 | $2 | $0.15 | 372K | 128K |
| 302.AI | $2 | $12 | – | 1.05M | 128K |
| Aixy | $2 | $12 | $0.20 | 1.05M | 128K |
| Cloudflare AI Gateway | $2 | $12 | $0.20 | 1.05M | 128K |
| CrossModel | $2 | $12 | $0.20 | 1.05M | 128K |
Showing 12 of 38 providers: the lab first, then the major clouds, then the cheapest resellers.
What GPT-5.6 Terra costs per month
Pick a workload close to yours or type your own volumes.
Independent benchmarks
Measured by third parties, not reported by OpenAI. Each links to its source and shows the date I checked it.
A composite of 10 independent evaluations (agents 30%, coding 20%, scientific reasoning 20%, general 30%), run by Artificial Analysis on each model, version 4.3.2.
Artificial Analysis, checked Oct 10, 2026
Human preference: people compare two anonymous answers and pick the better one. Ratings from the Text Arena overall board, style control on.
Arena (formerly LMArena), checked Oct 10, 2026
Agentic coding in a real terminal: can the model, driving an agent harness, finish multi step software and ops tasks. Resolution rate.
Terminal-Bench, checked Oct 10, 2026
Abstract reasoning on visual puzzles the model has not seen, semi private set. Hard to memorise, so it tracks reasoning more than knowledge.
ARC Prize, checked Oct 10, 2026
Median output tokens per second measured by Artificial Analysis on the provider API, for the same model setting as its index score.
Artificial Analysis, checked Oct 10, 2026
Benchmarks OpenAI reports (9)
- swe-bench-pro (SWE-Bench Pro)63.4%
- terminal-bench-2-1 (Terminal-Bench 2.1)87.4%
- deepswe-v1-1 (DeepSWE v1.1)69.6%
- gpqa-diamond (GPQA Diamond)92.9%
- agents-last-exam (Agents' Last Exam)50.4%
- osworld-2-0 (OSWorld 2.0 (launch table))50.2%
- browsecomp (BrowseComp)87.5%
- mmmu-pro (MMMU Pro (no tools))80.7%
- aa-intelligence-index (Artificial Analysis Intelligence Index v4.1, as reported by OpenAI)55
Labs pick their own settings and harnesses, so compare these only within one lab.
Supported request parameters
What you can set when you call GPT-5.6 Terra through an OpenAI compatible API.
- Tools
tools - Structured outputs
structured_outputs - Reasoning
reasoning
Alternatives to GPT-5.6 Terra
Models that take the same inputs and call tools, closest in price, cheaper ones first.
- Index 29.7
Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 31 providers.
by googleFeb 18, 20261.05M context$2/M input tokens$12/M output tokens31 providers
- Index 51.8
Reads text, images and files. Tool calling, structured output, reasoning. Served by 27 providers.
by openaiSep 29, 20261.05M context$2/M input tokens$10/M output tokens27 providers
- Index 56
Reads text, images and files. Tool calling, structured output, reasoning. Served by 26 providers.
by anthropicSep 26, 20261M context$2/M input tokens$10/M output tokens26 providers
- 1.05M context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 27 providers.
by openaiSep 22, 2026$2/M input tokens$10/M output tokens27 providers
- 1M context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 38 providers.
by anthropicJun 29, 2026$2/M input tokens$10/M output tokens38 providers
- 1.05M context
Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 30 providers.
by googleFeb 5, 2025$1.25/M input tokens$10/M output tokens30 providers
More from OpenAI
- Index 51.8
Reads text, images and files. Tool calling, structured output, reasoning. Served by 27 providers.
by openaiSep 29, 20261.05M context$2/M input tokens$10/M output tokens27 providers
- 1.05M context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 2 providers.
by openaiSep 29, 2026$2/M input tokens$10/M output tokens2 providers
- Index 38.1
Reads text, images and files. Tool calling, structured output, reasoning. Served by 27 providers.
by openaiSep 22, 20261.05M context$0.10/M input tokens$0.50/M output tokens27 providers
- 1.05M context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 2 providers.
by openaiSep 22, 2026$0.10/M input tokens$0.50/M output tokens2 providers
- 1.05M context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 27 providers.
by openaiSep 22, 2026$2/M input tokens$10/M output tokens27 providers
- 1.05M context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 2 providers.
by openaiSep 22, 2026$2/M input tokens$10/M output tokens2 providers
GPT-5.6 Terra questions
How much does the GPT-5.6 Terra API cost?
$2 per million input tokens and $12 per million output tokens, with cached input at $0.20. Prompts over 200K tokens bill at $4 input and $18 output. The estimator on this page turns that into a monthly bill for your own workload.
What is the context window of GPT-5.6 Terra?
1,050,000 tokens of input, and it can write up to 128,000 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.
Which providers serve GPT-5.6 Terra?
38 providers serve it, including Azure, Amazon Bedrock and Databricks. The lowest input price is $1.50 per million tokens at routing.run. Prices differ by host, so the Providers table on this page lists each one with its input and output price.
Does GPT-5.6 Terra support tool calling?
Yes. It accepts tool definitions and can return JSON that matches a schema, which is what an agent needs to call your APIs.
Is GPT-5.6 Terra open source?
No. OpenAI serves it through an API only, so you cannot download the weights or host it yourself.
When was GPT-5.6 Terra released?
Jul 9, 2026, with training data up to Feb 2026.
How good is GPT-5.6 Terra compared with other models?
It scores 42.1 on the Artificial Analysis Intelligence Index and 1466 on the Arena text leaderboard. Benchmarks are a shortlist, not a verdict: test the top two or three candidates on your own tasks before you commit.
Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 15, 2026. Independent scores from my hand checked rankings, sources linked above. The summary is written from these facts.
Building on GPT-5.6 Terra?
I test your real tasks on it and the two closest alternatives, then ship the agent on whichever wins on cost and accuracy.
Book Meeting