Tokenless
G
OpenAI

GPT-6.1 Terra API at half of list price

OpenAI's efficient GPT-6.1 model for visual reasoning, precise computer use, and clear, natural writing, with a 1M-token context and reasoning effort from none to max. It lists at half the price of GPT-6.1 Sol.

ReasoningComputer useVision1M contextTool use

GPT-6.1 Terra API pricing

Every rate is 50% of the provider's official list price. USD per million tokens.

Token typeList priceTokenless
Input$1.00$0.50
Output$5.00$2.50
Cache write$1.25$0.625
Cache read$0.05$0.025
Prompts over 272K tokens
Input$2.00$1.00
Output$7.50$3.75
Cache write$2.50$1.25
Cache read$0.10$0.05

A request whose prompt, including cached tokens, is over the threshold is billed entirely at the long-prompt rates, as the provider bills it.

Call GPT-6.1 Terra in one request

Tokenless speaks the OpenAI Chat Completions format. Point your client at the base URL, set model to gpt-6.1-terra, and you are done.

request.sh
curl https://api.tokenless.store/api/v1/chat/completions \
  -H "Authorization: Bearer $TOKENLESS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-6.1-terra",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'

GPT-6.1 Terra API questions

How much does the GPT-6.1 Terra API cost?

On Tokenless, GPT-6.1 Terra costs $0.50 per million input tokens and $2.50 per million output tokens, half of OpenAI's list price of $1.00 and $5.00. Prompts over 272K tokens bill at $1.00 input and $3.75 output per million.

Is it the genuine GPT-6.1 Terra?

Yes. Tokenless routes a request for gpt-6.1-terra to the genuine GPT-6.1 Terra and returns its response unchanged. No cheaper model is substituted.

How do I call the GPT-6.1 Terra API?

Point any OpenAI-compatible SDK at https://api.tokenless.store/api/v1, use your Tokenless API key, and set the model to gpt-6.1-terra. You pay per token from a prepaid balance, and your first $1 is free.

What is the GPT-6.1 Terra context window?

GPT-6.1 Terra accepts up to 1,050,000 tokens of context and returns up to 128,000 output tokens per request.

More GPT models