GPT-6.1 Terra
Pricing & Specs
OpenAI · $1 input / $5 output per 1M tokens · 1.05M context window
The per-token price never tells the full story. A typical task (1K input + 500 output tokens) on GPT-6.1 Terra costs about $0.0035, roughly $3.50 per 1,000 runs. But if it needs 3x the tokens of a cheaper model to match quality on YOUR task, the economics flip. The only way to know is to benchmark it on your actual workload.
GPT-6.1 Terra API Pricing
| Tokens | Price |
|---|---|
| Input | $1 / 1M tokens |
| Output | $5 / 1M tokens |
| Cached input | $0.05 / 1M tokens |
Prompts >272K tokens priced at 2x input and cache rates, 1.5x output. Cached input at 5% of input. Cache writes at 1.25x uncached input rate ($1.25/MTok 30m, $2.50/MTok 12h). Batch and Flex at 50% of Standard. Fast mode at 2x. Regional processing +10%.
What that means in practice
GPT-6.1 Terra Specs
| Spec | Value |
|---|---|
| Context window | 1.05M tokens |
| Max output tokens | 128K tokens |
| Input modalities | text, image |
| Output modalities | text |
| Knowledge cutoff | June 1, 2026 |
| Reasoning model | Yes |
| Tool / function calling | Yes |
| JSON mode | Yes |
| Streaming | Yes |
| Prompt caching | Yes |
| Batch API | Yes |
Notes
Fast, efficient model for visual reasoning, precise computer use, and natural writing. Max input 922,000 tokens. Effort levels: none, low, medium (default), high, xhigh, max. Tool calling requires Responses API; Chat Completions supported without tools.
FAQ
How much does GPT-6.1 Terra cost?
GPT-6.1 Terra costs $1 per 1M input tokens and $5 per 1M output tokens ($0.05 per 1M cached input tokens).
What is GPT-6.1 Terra's context window?
GPT-6.1 Terra has a 1.05M-token context window. Maximum output is 128K tokens.
Can I test GPT-6.1 Terra on my own task?
Yes. OpenMark lets you benchmark GPT-6.1 Terra against 100+ models on your own task with real API calls, with no API keys needed, free tier available.
Is GPT-6.1 Terra the right model for YOUR task?
Pricing tables can't answer that. Benchmark it against 100+ models
on your actual workload: real API calls, real costs. Free tier available.