model comparison

vs

Inkling 2 Small vs MiMo V2.6 Pro

Thinking Machines against Xiaomi, compared on listed price, real workload cost, context and capabilities.

the short answer

  • on DeepSWE v1.1, as each maker reports it, Inkling 2 Small scores 72.1% and MiMo V2.6 Pro 71.9.
  • Inkling 2 Small lists the lower input price, while MiMo V2.6 Pro lists the lower output price.
  • MiMo V2.6 Pro offers the larger context window.
  • MiMo V2.6 Pro reads cached input for less ($0.004/M against Inkling 2 Small's $0.03/M), which decides the bill for agents that resend long context.

side-by-side specs

specInkling 2 SmallMiMo V2.6 Pro
providerThinking MachinesXiaomi
input price$0.3/M$0.435/M
output price$1/M$0.87/M
cached input$0.03/M$0.004/M
blended price (3:1)$0.475/M$0.544/M
context window256k tokens1M tokens
max output—128k tokens
inputtext, imagestext, images, video, audio
structured outputnoyes
weightsclosedopen (MIT)
releasedNovember 5, 2026September 2026
DeepSWE v1.1 (maker-reported)72.1%71.9

same work, both models

workloadInkling 2 SmallMiMo V2.6 Pro
one chat reply3,000 tokens in, 500 outMiMo V2.6 Pro costs 1.2× as much as Inkling 2 Small$0.0014$0.0017
summarise a 100-page report50,000 tokens in, 1,500 out, one requestMiMo V2.6 Pro costs 1.4× as much as Inkling 2 Small$0.02$0.02
1,000 classification calls500 tokens in, 20 out, per call$0.17$0.23
coding-agent session2M tokens in across ~60 turns, 60,000 out, no cache$0.66$0.92
same session, cached85% of input read from the prompt cache, the rest written to itInkling 2 Small costs 1.1× as much as MiMo V2.6 Pro$0.20$0.19

at listed rates. token counts are typical sizes, not measurements.

MiMo V2.6 Pro pricing notes

  • Xiaomi lists a batch api tier at half the real-time rate.
  • cache writes are free for a limited time; Xiaomi gives no end date.

when to pick which

Inkling 2 Small

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

MiMo V2.6 Pro

Xiaomi's flagship open-weights omnimodal model, a 1.02T-total, 42B-active mixture-of-experts with a 1M window. it replaces the text-only MiMo V2.5 Pro and adds image, video and audio input.

pick it if

  • you want Xiaomi's strongest model for agent, coding and computer-use work
  • you need image, video or audio input on a 1M window
  • you want MIT-licensed weights you can self-host

skip it if

  • you only need Flash-level quality; Flash scores close to Pro on most maker-reported rows at a third of the price

faq

which is better, Inkling 2 Small or MiMo V2.6 Pro?

on DeepSWE v1.1, as each maker reports it, Inkling 2 Small scores 72.1% and MiMo V2.6 Pro 71.9. 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 MiMo V2.6 Pro?

Inkling 2 Small lists the lower input price, while MiMo V2.6 Pro lists the lower output price. on a coding-agent session (2M tokens in, 60,000 out) Inkling 2 Small costs $0.66 and MiMo V2.6 Pro $0.92.

which has the larger context window?

MiMo V2.6 Pro offers the larger context window. Inkling 2 Small: 256k tokens; MiMo V2.6 Pro: 1M tokens.

can i switch between Inkling 2 Small and MiMo V2.6 Pro mid-task?

yes. in an octomind session, /model octohub:inkling-2-small and /model octohub:mimo-v2.6-pro 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.

open the panel all models

prices from the catalog of 2026-11-09