As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/gpt-6-1-terra/

# GPT-6.1 Terra

OpenAI, GPT-6 family. Status: current. Type: reasoning model. Released: 2026-10-26. Training cutoff: 2026-06.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| OpenAI API | `gpt-6.1-terra` | https://api.openai.com/v1/responses | https://developers.openai.com/api/docs/models/gpt-6.1-terra |
| Web app (ChatGPT Work, Plus/Pro/Enterprise/Edu) |  |  | https://chatgpt.com |
| Codex |  |  | https://developers.openai.com/codex/changelog |

## Pricing

- Input: $1 per 1M tokens
- Cached input: $0.05 per 1M tokens
- Output: $5 per 1M tokens
- Cache write: $1.25 per 1M tokens
- Unit as published: per 1M tokens (USD), standard tier
- Note: cache writes $1.25 (30-minute retention) or $2.50 (12-hour retention); prompts >272K input tokens billed at 2x input/cache and 1.5x output for the whole request
- Source: https://developers.openai.com/api/docs/models/gpt-6.1-terra
- Last checked: 2026-10-26

## Specs

- Input: text, image
- Output: text
- Context window: 1,050,000 tokens
- Max output: 128,000 tokens
- Open weights: no
- Licence: proprietary

## What it has not seen

- Published training cutoff: 2026-06 (June 2026).
- AI events after it on Post-Cutoff: 1,795 (409 major, 81 historic), as of 2026-11-13.
- Already missing at launch: 1,368.
- Briefings of the news since June 2026: https://postcutoff.com/briefings/cutoff-2026-06-s.md (short), https://postcutoff.com/briefings/cutoff-2026-06-m.md (medium), https://postcutoff.com/briefings/cutoff-2026-06.md (full).
- Its card, with five things it has never heard of: https://postcutoff.com/you/gpt-6-1-terra/

## What stands out

- Computer use at half the mid-tier price: $1/$5 per 1M tokens with the computer_use tool in the Responses API; OpenAI says it finishes computer-use tasks over 3x faster than GPT-6 Astra and GPT-6.1 Sol (vendor claim). Source: https://www.bleepingcomputer.com/news/artificial-intelligence/openai-launches-gpt-61-terra-with-3x-faster-ai-agents-50-percent-lower-pricing/
- Near-Sol intelligence per dollar: Artificial Analysis Intelligence Index 48 at max effort (GPT-6.1 Sol 52) for about $0.40 per index task; 90.9 output tokens/s. Source: https://artificialanalysis.ai/models/gpt-6-1-terra
- Fewer guesses when unsure: AA-Omniscience: guesses instead of abstaining 38% of the time, vs 88% for GPT-5.6 Terra (per The Decoder's reading of Artificial Analysis). Source: https://the-decoder.com/gpt-6-1-terra-halves-openais-api-prices-and-still-gains-ground-on-its-larger-models/
- Critical cyber classification for a mid-size model: System card addendum: treated as Critical in cybersecurity and High in biology/chemistry, with GPT-6 Astra's safeguard stack; ExploitBench 97.10%. Source: https://deploymentsafety.openai.com/gpt-6-1-terra

## Notes

Mid-size GPT-6 model between GPT-6 Luna and GPT-6.1 Sol; successor to GPT-5.6 Terra. reasoning.effort none/low/medium(default)/high/xhigh/max. Max input 922K tokens. Tool calling needs the Responses API (tools: web/file search, image generation, code interpreter, hosted shell, apply patch, skills, computer use, MCP, tool search). No audio/video input. Rate limits up to 15,000 RPM / 40M TPM (Grow tier). OpenAI still recommends GPT-6.1 Sol or GPT-6 Astra for the hardest coding.

OpenAI's cheaper everyday model for computer use, visual reasoning and writing, released Oct 26, 2026.

Model page: https://postcutoff.com/m/gpt-6-1-terra/