OpenAI · language model
GPT-6.1 Terra: pricing, context and benchmarks
GPT-6.1 Terra is OpenAI's model released on October 26, 2026. It costs $1 per million input tokens and $5 per million output tokens, with a 1.1M-token context window. Epoch AI ranks it #4 of 117 rated models.
| Performance (ECI) | 39/40 | |
|---|---|---|
| Price | 8/30 | |
| Context | 15/15 | |
| Features | 11/15 |
What you need to know about GPT-6.1 Terra
OpenAI, based in United States, put GPT-6.1 Terra online on October 26, 2026. It accepts files, images, and text as input and produces text. Its context window reaches 1,050,000 tokens, larger than 99 % of the models in the registry, and it can write up to 128,000 tokens in one go.
It is a recent model: real-world feedback and independent scores are still scarce.
GPT-6.1 Terra pricing
On OpenRouter, GPT-6.1 Terra costs $1 per million input tokens and $5 per million output tokens. Counting three tokens read for every token written, its average price is $2 per million, more expensive than 72 % of paid models (2.5 times the median of $0.8).
A concrete example: a task that sends 2,000 tokens (about 1,500 words) and receives a 500-token answer costs $0.0045. At 1,000 tasks a day, budget $135 a month. The price calculator redoes this with your own volumes.
Tokens already sent and cached are billed at $0.05 per million. With batch processing (delayed answers), the price drops to $0.5 input and $2.5 output.
Performance and benchmarks
The Epoch Capabilities Index (ECI), which aggregates published results across many benchmarks, gives GPT-6.1 Terra a score of 167.8 (range 164.9 to 171.2). That places it #4 of 117 rated models.
Scores published by Epoch AI on the benchmarks the site tracks:
| Benchmark | What it measures | Score | Date |
|---|---|---|---|
| GPQA Diamond | PhD-level science questions | 94.3 % | Oct 26, 2026 |
| FrontierMath | research-level maths problems (tiers 1-3) | 90.9 % | Oct 26, 2026 |
| OTIS Mock AIME | maths competition problems | 100 % | Oct 26, 2026 |
| SimpleQA Verified | accuracy on simple facts | 57.3 % | Oct 26, 2026 |
Features, privacy and local use
- It supports tool calling, so it can drive an AI agent, call APIs or MCP servers.
- It can answer in an enforced JSON format (structured outputs).
- It is a reasoning model: it "thinks" before answering, which helps on hard tasks but uses more output tokens.
Its weights are not published: it can only be used through the OpenAI API or a broker such as OpenRouter, which means sending your data off your machines.
Other OpenAI models
| Model | Released | Avg. price | ECI |
|---|---|---|---|
| GPT-6.1 Terra Pro | Oct 26, 2026 | $2 | — |
| GPT-6.1 Sol | Sep 29, 2026 | $4 | 168.9 |
| GPT-6.1 Sol Pro | Sep 29, 2026 | $4 | — |
| GPT-6 Sol | Sep 22, 2026 | $4 | 164.1 |
| GPT-6 Luna | Sep 22, 2026 | $0.2 | 156.7 |
| GPT-6 Luna Pro | Sep 22, 2026 | $0.2 | — |
| GPT-6 Sol Pro | Sep 22, 2026 | $4 | — |
| GPT-6 Astra | Sep 4, 2026 | $20 | 169.1 |
Verdict
Computed score: 73/100, from public data (performance, price, context, features).
Strengths
- Among the top 20% of models according to Epoch AI (ECI 167.8).
- Very large context (1.1M tokens): long documents or a whole codebase fit in one request.
- Agent-ready: tool calling and structured JSON output.
- Discounted batch pricing.
Avoid if…
- you process large volumes on a tight budget;
- your data must not leave your servers;
- your tasks are mostly simple: a non-reasoning model will cost less.
Alternatives
Comparisons and tools
Learn more
Frequently asked questions
How much does GPT-6.1 Terra cost?
$1 per million input tokens and $5 per million output tokens on OpenRouter (checked November 8, 2026). A task with 2,000 tokens read and 500 written costs $0.0045.
How big is GPT-6.1 Terra's context window?
1,050,000 tokens, roughly 788,000 words, with a maximum of 128,000 output tokens.
Can GPT-6.1 Terra run locally?
No, OpenAI does not publish its weights: it is API-only.
Is GPT-6.1 Terra suitable for an AI agent?
Technically yes: it supports tool calling and structured outputs. Then check its cost for your volume.
How good is GPT-6.1 Terra?
Epoch AI ranks it #4 of 117 rated models (ECI 167.8). On GPQA Diamond, it scores 94.3%.
What are the alternatives to GPT-6.1 Terra?
The closest models on price and performance are Gemini 4 Argon, Claude Sonnet 5.5, and Gemini 3.8 Flash.
Related articles
- DeepSeek for AI agents: strengths, limits and real costsOctober 27, 2026
- Mistral AI: models, pricing and agentsOctober 25, 2026
- LLM benchmarks: how to read model rankingsOctober 24, 2026
- Running a local LLM: hardware, software, and limitationsOctober 24, 2026
Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score