Thinking Machines language model

Inkling Small

Inkling Small is Thinking Machines' 276B-total, 12B-active mixture-of-experts open-weights model, the smaller sibling of Inkling. the lab reports performance comparable to Inkling at a quarter of its size; on octomind it costs half Inkling's input rate and under a third of its output rate.

01

price

$0.5/M

input tokens

$1.2/M

output tokens

per 1M tokens. octomind bills the listed provider price, with no markup, on every plan, including the free one (pay as you go from credits).

02

what real work costs

workloadcost
one chat reply 3,000 tokens in, 500 out $0.0021
summarise a 100-page report 50,000 tokens in, 1,500 out, one request $0.03
1,000 classification calls 500 tokens in, 20 out, per call $0.27
coding-agent session 2M tokens in across ~60 turns, 60,000 out, no cache $1.07

at the listed rate. token counts are typical sizes, not measurements.

03

specs

provider
Thinking Machines
context window
256k tokens — ≈ 380 pages of prose or 26,000 lines of code
input
text, images
output
text
structured output
yes — JSON schema
reasoning mode
yes
weights
open — Apache 2.0
released
July 30, 2026
status
live
model id
inkling-small

integration notes

  • it reasons by default; chain-of-thought can be disabled via a renderer or argument for direct answers.
  • for optimal performance, each image dimension should be between 40px and 4096px.

04

benchmarks

as published by the maker; not measured by octomind.

benchmarkscore
SWE-bench Verifiedsource80.2%
Terminal Bench 2.1 (best harness)source64.7%

05

when to pick it

pick it if

  • want the Inkling family's lower-priced tier with image input
  • need adjustable thinking effort, from minimal to xhigh
  • want Apache 2.0 open weights you can fine-tune or self-host

06

where it sits on price

blended price $0.675/M at 3 input tokens per output token: 16 live language models cost less, 27 cost more.

  1. MiniMax M3 $0.525/M
  2. MiMo V2.6 Pro $0.544/M
  3. Inkling Small $0.675/M
  4. Qwen3.7 Plus $0.7/M
  5. Gemini 3.5 Flash Lite $0.85/M

07

use Inkling Small in octomind

one octohub login reaches every model in the catalog. pick this one per run, per session, or as your default.

run it
octomind login
octomind run -m octohub:inkling-small
switch mid-session
/model octohub:inkling-small
make it the default — config.toml
[model]
name = "octohub:inkling-small"

08

compare Inkling Small

all model comparisons →

09

similar models

nearest live models by listed input price.

view all models →

10

Inkling Small faq

how much does Inkling Small cost?

Inkling Small lists at $0.5/M input, $1.2/M output per 1M tokens. a typical coding-agent session (2M tokens in, 60,000 out) comes to $1.07. octomind bills the listed provider price, with no markup, on every plan, including the free one (pay as you go from credits).

what is the context window of Inkling Small?

256k tokens, ≈ 380 pages of prose or 26,000 lines of code.

does Inkling Small accept images?

yes. it takes text and images as input and returns text.

is Inkling Small open source?

its weights are open under Apache 2.0, so it can also be self-hosted.

when was Inkling Small released?

July 30, 2026, by Thinking Machines.

is Inkling Small free?

no. Inkling Small bills per token at $0.5/M input, $1.2/M output per 1M. octomind's free plan reaches it pay as you go from credits, so you pay only for the tokens you use, at the provider price. credits carry a 3% top-up fee.

how do i use Inkling Small in octomind?

run octomind login once, then octomind run -m octohub:inkling-small. inside a running session, /model octohub:inkling-small switches to it without losing context.

use Inkling Small in octomind

choose a model when you start, then switch mid-session when the work changes.