Inkling 2 Small is Thinking Machines' second-generation 594B-total, 17B-active mixture-of-experts model with image input. its weights are closed for now; the lab plans an Apache 2.0 release. on octomind it is served only through Tinker.
pick it if
want the lowest-priced Inkling on octomind, below Inkling Small on both input and output
need adjustable reasoning effort, with chain-of-thought you can switch off
work on long agent runs: the lab trained it with a 256K window plus compaction
skip it if
you need open weights today; the lab has not released them yet
you need audio input; Inkling 2 Small takes text and images only
the first open-weights model from Reflection, a 501B-total, 23B-active mixture-of-experts built for agentic tool use, coding and general reasoning. it reads text only and its weights ship under Apache 2.0.
pick it if
you want a long-window text model priced with the flash tier
you want Apache 2.0 weights, with BF16, FP8 and NVFP4 builds to self-host
you run tool-calling agents on text and repeat long prompts, so cached input matters
skip it if
you need image, audio or video input; Beam reads text only
long autonomous coding is the job; its reported DeepSWE v1.1 score sits below GLM-5.3 Flash and DeepSeek V4.1 Flash
faq
which is better, Inkling 2 Small or Beam?
on DeepSWE v1.1, as each maker reports it, Inkling 2 Small scores 72.1% and Beam 43.3%. these are each maker's own numbers, not a controlled head-to-head; the spec table lists every benchmark both publish.
which is cheaper, Inkling 2 Small or Beam?
Beam lists lower input and output prices. on a coding-agent session (2M tokens in, 60,000 out) Inkling 2 Small costs $0.66 and Beam $0.27.
can i switch between Inkling 2 Small and Beam mid-task?
yes. in an octomind session, /model octohub:inkling-2-small and /model octohub:beam 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.