one chat reply3,000 tokens in, 500 outGPT-6.1 Sol costs 2.0× as much as GPT-6.1 Terra
$0.0055
$0.01
summarise a 100-page report50,000 tokens in, 1,500 out, one request
$0.06
$0.12
1,000 classification calls500 tokens in, 20 out, per call
$0.60
$1.20
coding-agent session2M tokens in across ~60 turns, 60,000 out, no cache
$2.30
$4.60
same session, cached85% of input read from the prompt cache, the rest written to it
$0.76
$1.52
at listed rates. token counts are typical sizes, not measurements.
GPT-6.1 Terra pricing notes
requests over 272K input tokens bill the entire request at 2x the input and cache rates and 1.5x the output rate; the listed price is the short-context rate.
cache hits bill at $0.05 per 1M tokens; cache writes cost $1.25 (30-minute) or $2.50 (12-hour).
GPT-6.1 Sol pricing notes
requests over 272K input tokens bill the entire request at 2x the input and cache rates and 1.5x the output rate; the listed price is the short-context rate.
cache hits bill at $0.10 per 1M tokens, half GPT-6 Sol's $0.20; cache writes cost $2.50 (30-minute) or $5.00 (12-hour).
OpenAI's GPT-6.1 Terra is a fast, efficient model for visual reasoning, precise computer use and natural writing. at $1 / $5 it costs half of GPT-6.1 Sol and sits above GPT-6 Luna; it replaces GPT-5.6 Terra.
pick it if
your prompts mix text and images and you want half of GPT-6.1 Sol's token price
you resend long prompts; cache hits bill at 5% of input
you want reasoning switched off entirely; Terra accepts reasoning effort none
skip it if
GPT-6 Luna at $0.10 / $0.50 covers your workload
your prompts often pass 272K input tokens; the whole request then bills higher
OpenAI's GPT-6.1 Sol, for complex coding and professional work, replaced GPT-6 Sol at the same $2 / $10 rate with half Sol's cache-hit price. it sits below GPT-6 Astra and above GPT-6 Luna in price.
pick it if
you want complex coding work at one-fifth of GPT-6 Astra's token price
you resend long prompts; cache hits bill at 5% of input
your prompts mix text and images
skip it if
GPT-6 Luna at $0.10 / $0.50 covers your workload
your prompts often pass 272K input tokens; the whole request then bills higher
faq
which is cheaper, GPT-6.1 Terra or GPT-6.1 Sol?
GPT-6.1 Terra lists lower input and output prices. on a coding-agent session (2M tokens in, 60,000 out) GPT-6.1 Terra costs $2.30 and GPT-6.1 Sol $4.60.
can i switch between GPT-6.1 Terra and GPT-6.1 Sol mid-task?
yes. in an octomind session, /model octohub:gpt-6.1-terra and /model octohub:gpt-6.1-sol switch models without losing the conversation, so you can draft on one and review on the other.
try either model
switch between models inside the same octomind session.