OpenAI GPT-6.1 Terra: Pricing, Specs and Limits
OpenAI GPT-6.1 Terra: mid-tier model in the GPT-6.1 series, 1M context, 1.00 in / 5.00 out per 1M tokens. Specs, limits and test prompts.
By ShilpBot Team · Published · 3 min read
GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series and is priced below GPT-6.1 Sol. The listing says it suits everyday agentic, coding and writing work and is particularly strong at understanding screenshots.
A separate listing, GPT-6.1 Terra Pro, is the same model with a "pro" reasoning mode. This page covers both, because the choice between them is mainly about cost versus depth.
Prices and specifications checked against the public OpenRouter catalogue on 2026-11-16. See the live model page for current limits.
OpenAI GPT-6.1 Terra quick facts
| Detail | Value |
|---|---|
| Developer | OpenAI |
| Model ID | openai/gpt-6.1-terra |
| Added to the catalogue | 2026-10-26 |
| Type | Mid-tier model in the GPT-6.1 series |
| Parameters | Not listed |
| Context window | about 1M tokens (1,050,000) |
| Maximum output | 128,000 tokens |
| Input types | file, image, text |
| Price | 1.00 in / 5.00 out per 1M tokens (cached input 0.050) |
Feature support from the catalogue: Tool calling: listed; JSON / structured output: listed; Adjustable reasoning effort: listed.
What OpenAI GPT-6.1 Terra is good for
- Everyday coding, writing and agent tasks at $1 per million input tokens.
- Screenshot understanding, which the listing singles out.
- Teams that want a mid-priced OpenAI model with a 1.05M-token context window.
Limits of OpenAI GPT-6.1 Terra
- Terra Pro looks the same price per token but spends far more reasoning tokens, so its bills can be much higher.
- Use standard Terra by default and switch to Pro only for tasks that need it.
- No audio or video input in the listing.
How OpenAI GPT-6.1 Terra compares
- OpenAI GPT-6.1 Sol: Both have a 1,050,000-token context window; both cap output at 128,000 tokens; it costs 1.00 input and 5.00 output per million tokens against 2.00 and 10.00.
- OpenAI GPT-6 Luna: Both have a 1,050,000-token context window; both cap output at 128,000 tokens; it costs 1.00 input and 5.00 output per million tokens against 0.10 and 0.50.
- Anthropic Claude Sonnet 5.5: It has a larger context window (1,050,000 against 1,000,000 tokens); both cap output at 128,000 tokens; it costs 1.00 input and 5.00 output per million tokens against 2.00 and 10.00.
Calling OpenAI GPT-6.1 Terra from code
Use the model ID openai/gpt-6.1-terra with any OpenAI-compatible client pointed at OpenRouter:
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "openai/gpt-6.1-terra", "messages": [{"role": "user", "content": "Explain what you can do in two sentences."}]}'Prompts that show what OpenAI GPT-6.1 Terra can do
- Upload a screenshot of an error dialog and ask for likely causes.
- Draft a 300-word product update from bullet points and compare tone with Sonnet 5.5.
- Run one hard problem in standard and pro mode and compare tokens used and quality.
What OpenAI GPT-6.1 Terra costs
The catalogue lists 1.00 per million input tokens and 5.00 per million output tokens, with cached input at 0.050 per million. Sending 1 million input tokens and receiving 100,000 output tokens would cost about 1.50. A single coding-agent step with a 150,000-token prompt and a 10,000-token answer would cost about $0.20 before caching. If your client reuses the same prompt prefix, cached input at 0.050 per million tokens can cut the input side of that bill by about 95 percent. GPT-6.1 Terra Pro is the same underlying model served with reasoning mode set to pro for higher-quality answers on complex tasks. It has the same listed per-token price, but pro mode uses far more tokens, so the real cost of a request is much higher. Prices are set by the provider, can change, and may differ between hosting providers, so check the live model page before you budget.
Keep reading
Compare every paid model by price in our AI model pricing roundup, or see the free models roundup. New to terms like mixture-of-experts? Start with how neural networks learn.
Frequently asked questions
What is the difference between GPT-6.1 Terra and Terra Pro?
They are the same underlying model. Terra Pro runs with reasoning mode set to pro, which gives higher quality on complex tasks but spends many more tokens, so each request costs far more.
What are the cost and limits of OpenAI GPT-6.1 Terra?
As of 2026-11-16 the catalogue lists 1.00 per million input tokens and 5.00 per million output tokens. About 1M tokens (1,050,000) context window, up to 128,000 output tokens, model ID openai/gpt-6.1-terra. Prices can change, so check the live model page.
