One chat reply3,000 tokens in, 500 outGPT-6.1 Terra costs 1.1× as much as Inkling
$0.0055
$0.005
Summarise a 100-page report50,000 tokens in, 1,500 out, one requestWithin 5%
$0.06
$0.06
1,000 classification calls500 tokens in, 20 out, per call
$0.60
$0.58
Coding-agent session2M tokens in across ~60 turns, 60,000 out, no cache
$2.30
$2.24
Same session, cached85% of input read from the prompt cache, the rest written to itInkling costs 1.1× as much as GPT-6.1 Terra
$0.76
$0.83
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).
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
Inkling is Thinking Machines' open-weights model and the first in its family: a 975B-parameter mixture-of-experts (41B active) that reasons over text, images and audio with controllable thinking effort. Inkling Small is its smaller, cheaper sibling.
Pick it if
you want Apache 2.0 open weights you can later fine-tune on Tinker
you send images with text and want to tune thinking effort
you run coding or agent harnesses, the work it was trained for
Skip it if
cheaper Inkling Small, at half the input price, covers your workload
you need the strongest model; Thinking Machines says Inkling is not it
FAQ
Which is cheaper, GPT-6.1 Terra or Inkling?
Inkling lists the lower output price; input prices match. On a coding-agent session (2M tokens in, 60,000 out) GPT-6.1 Terra costs $2.30 and Inkling $2.24.
Can I switch between GPT-6.1 Terra and Inkling mid-task?
Yes. In an Octomind session, /model octohub:gpt-6.1-terra and /model octohub:inkling 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.