GPT-6.1 Terra: a cheaper API, with a few limits
On October 26, 2026, OpenAI released GPT-6.1 Terra, a model it calls fast and efficient, built for visual reasoning, precise computer use and clear writing. The headline is the price: OpenAI says its standard API prices are 50% lower than GPT-5.6 Terra and GPT-6.1 Sol.
In short
- The model ID is
gpt-6.1-terra. It is in the API now, and in ChatGPT Work and Codex for Plus, Pro, Enterprise and Edu users. - Against GPT-5.6 Terra the prices drop and the knowledge cutoff moves later. The context window and the output limit stay the same (see the table below).
- The quality gains come from OpenAI's own tests. I found no independent results.
- Before you switch, test on your own samples and check tool calling, sampling parameters and the 272K-token price threshold.
The numbers side by side
Prices are per million tokens, for prompts up to 272K input tokens. Sol is in the table because OpenAI compares against it too.
| GPT-5.6 Terra | GPT-6.1 Sol | GPT-6.1 Terra | |
|---|---|---|---|
| Input | $2 | $2 | $1 |
| Cached input | $0.20 | $0.10 | $0.05 |
| Output | $12 | $10 | $5 |
| Context window | 1,050,000 tokens | 1,050,000 tokens | 1,050,000 tokens |
| Maximum output | 128,000 tokens | 128,000 tokens | 128,000 tokens |
| Knowledge cutoff | Feb 16, 2026 | Apr 30, 2026 | Jun 1, 2026 |
none reasoning effort |
supported | not supported | supported |
Terra is the cheapest of the three on every price line. By my arithmetic the output price falls by more than half against GPT-5.6 Terra; that is my calculation, not OpenAI's wording. The window and the output limit did not move. One practical difference from Sol: Terra accepts none as a reasoning effort, so you can switch reasoning off.
The pricing page also lists higher rates for long prompts. Above 272K input tokens, input and cache rates double and output rates rise by half, and the higher rate applies to the whole request. Check where your longest prompts fall.
Where it sits in the timeline
OpenAI's model line has moved fast this year. These are the dates from its API changelog and model pages:
- July 9: GPT-5.6 Terra launches as the model that balances intelligence and cost. On July 30 its price is cut by 20%.
- September 3: GPT-6 Astra, the most capable model of the family.
- September 22: GPT-6 Sol and GPT-6 Luna.
- September 29: GPT-6.1 Sol, for complex coding and professional work at a lower cost than Astra.
So the Terra line has got cheaper twice since July: a price cut on GPT-5.6 Terra, and now a new model at a lower price. OpenAI's latest-model guide splits the jobs: Terra for visual and writing work, Sol for complex coding, computer use and professional work. The announcement also names computer use as a Terra strength, so the line between the two is not sharp.
What OpenAI claims about quality
The announcement calls GPT-6.1 Terra a significant step up from GPT-5.6 Terra. On Agents' Last Exam at medium effort it scores 15 points higher at about a third of the cost. It finishes tasks more than three times faster than GPT-6 Astra and GPT-6.1 Sol, and it beats GPT-5.6 Terra on MMMU-Pro at every effort setting. Two numbers stand out:
| OpenAI's own tests | GPT-5.6 Terra | GPT-6.1 Terra |
|---|---|---|
| Terminal-Bench 4.0, max reasoning, tasks solved | 21.5% (published score) | 50.3% |
| Error rate on error-prone prompts, low effort (internal) | 53.6% | 16.7% |
All of these are OpenAI's results, and the error-rate row comes from an internal benchmark. I read them as a reason to test, not as a result for your workload.
The good and the not-so-good
What works better
- A lower price on every line of the table, and a later knowledge cutoff.
- Image input and computer use, with the same long context window.
- Speed and error-rate claims that point the right way, if they hold on your workload.
- Reasoning can be turned off with
none, which Sol does not allow.
What is missing, unclear or costs something
- For the most complex coding, OpenAI itself points to GPT-6.1 Sol and GPT-6 Astra.
- No fine-tuning, and no audio or video input.
- Tool calling needs the Responses API.
- The price rises for prompts above 272K input tokens.
- OpenAI says Terra meets the Critical threshold for cybersecurity in its Preparedness Framework, and the safeguards built for GPT-6 Astra stay in place.
- Every benchmark above is OpenAI's own. There are no independent results yet.
My take, not fact: for high-volume jobs like OpenAI's own example of reading incoming invoices into accounting software, the price drop probably matters more than the benchmark gains. I would still run my own sample first.
Switching from GPT-5.6 Terra: a checklist
This follows OpenAI's migration advice in its latest-model guide.
- Compare at the same effort. Run both models on representative images and workflows from your own app, and keep your current reasoning effort. Start at medium and raise it only if the quality gain is worth the extra time and tokens.
- Move tool calling to the Responses API if you use tools through Chat Completions.
- Remove sampling parameters. When reasoning is on (anything other than
none), removetemperature,top_pandtop_logprobs, andlogprobsas well in Chat Completions. - Check your longest prompts against the 272K-token threshold before you trust the new price.
The guide has no Terra-specific prompting advice, so there is nothing more to follow there.
Sources
- Introducing GPT-6.1 Terra — OpenAI — the October 26, 2026 launch, the 50% lower price claim, the access in ChatGPT Work, Codex and the API, the quality, speed and error-rate claims, the advice to use Sol or Astra for the most complex coding, the Critical cybersecurity threshold
- API changelog — OpenAI Developers — the
gpt-6.1-terraentry on October 26, the GPT-5.6 Terra launch on July 9 and its 20% price cut on July 30, GPT-6 Astra on September 3, GPT-6 Sol and Luna on September 22, GPT-6.1 Sol on September 29 - GPT-6.1 Terra model page — OpenAI Developers — context window, output limit, knowledge cutoff, reasoning effort values, supported inputs, no fine-tuning, tool calling needs the Responses API
- GPT-6.1 Sol model page — OpenAI Developers — Sol's price, context window, output limit and knowledge cutoff
- GPT-5.6 Terra model page — OpenAI Developers — GPT-5.6 Terra's price, context window, output limit and knowledge cutoff
- Pricing — OpenAI Developers — the per-million-token prices and the higher rates above 272K input tokens
- Latest model guide — OpenAI Developers — the migration advice, how Terra and Sol are positioned, and that Sol does not support
none - GPT-6.1 Terra deployment safety — OpenAI — the Critical cybersecurity threshold and the safeguards carried over from GPT-6 Astra