openai/gpt-6.1-terra
GPT-6.1 Terra accepts text and images and generates text. It supports a 1.05M-token context window and up to 128K output tokens, with reasoning effort none, low, medium (default), high, xhigh and max. Use the Responses API for tool calling. Standard OneHop prices are 15% of official USD rates: $0.15 input, $0.75 output, $0.0075 cached input and $0.1875 cache writes per million tokens. Cache-write pricing covers the current 30-minute route. For prompts above 272K tokens, input and cache prices double and output prices increase by 50% for the full request.
Source: https://developers.openai.com/api/docs/models/gpt-6.1-terra · Verified 2026-10-27
Cache read $0.0075/M · Cache write $0.1875/M
| Tier | Input | Cache read | Cache write | Output |
|---|---|---|---|---|
| Standard ≤272K | $0.15 | $0.0075 | $0.1875 | $0.75 |
| Standard >272K | $0.3 | $0.015 | $0.375 | $1.125 |
Use either ID to call this model via the API.
openai/gpt-6.1-terraReplace the ONEHOP_KEY placeholder with your API key. Create one →
from openai import OpenAI
client = OpenAI(
base_url="https://api.onehop.ai/v1",
api_key="<ONEHOP_KEY>",
)
completion = client.chat.completions.create(
model="openai/gpt-6.1-terra",
messages=[{"role": "user", "content": "What is the meaning of life?"}],
)
print(completion.choices[0].message.content)OpenAI's new flagship — the strongest reasoning, coding, and agentic model in the GPT line.
$1.5/M↓ · $7.5/M↑
The balanced GPT-6 for interactive and agentic coding — near-Astra reliability at a fraction of the price.
$0.3/M↓ · $1.5/M↑
The upgraded GPT-6 Sol — near-Astra agentic coding and computer use, with cached input at 5% of the input price.
$0.3/M↓ · $1.5/M↑
The fastest, lowest-cost GPT-6 for high-volume, well-defined tasks.
$0.03/M↓ · $0.15/M↑