Thinking Machines: Inkling Small

Name: Thinking Machines: Inkling Small
Brand: Thinkingmachines
Price: 3.3 USD

Thinkingmachines · thinkingmachines/inkling-small

Runs in the cloud, on our API — not on your own machine.

open weights tools reasoning optional hears

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...

Install on 00

What it costs

Input / 1M

$0.9

Output / 1M

$2.40

1M in + 1M out

$3.30

Cache read / 1M

$0.2

Audio input has no separate rate: a recording counts against the input price above.

Final AI-token prices, per million tokens. Bring your own provider key in the app to pay provider rates directly.

What it can do

Takes

text, images and audio

Returns

text

Tools

yes

Reasoning

optional

Context window

1M tokens

Max output

262K tokens

Open weights

yes

Effort: max, high, medium, low, minimal and none — high by default. More effort means more thinking tokens, billed at the output rate.

Benchmarks

Benchmark	What it measures	Score
Epoch Capabilities Index	one score summarising the benchmarks below — an index, not a percentage	150.1
GPQA Diamond	graduate-level science questions	88.5% ± 1.9
AIME	competition mathematics	90.0% ± 4.0
SimpleQA	short factual questions — the test for making things up	19.1% ± 1.2

Scores by Epoch AI, CC BY 4.0. The ± is the margin of error: models inside each other's margins are tied, not ranked. Epoch's notes on this row: source “epoch”, accessibility “Open weights (unrestricted)”.

Dates

Released

2026-07-30

Knowledge cutoff

—

Retires

—

Using it

In the 00 app — pick it per agent, and per tier, then build your own agents on it. Get 00.

As a drop-in API — the same model at an OpenAI-compatible endpoint. Two settings:

Create a workspace API key in the Overblast console — usage bills that workspace's AI tokens, at the prices on this page.
Point your base URL at https://brain.deployd.network/ai/v1. Chat completions with streaming, embeddings, /images, /audio/transcriptions and /videos.

curl https://brain.deployd.network/ai/v1/chat/completions \
  -H "Authorization: Bearer ob_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "thinkingmachines/inkling-small",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'

It transcribes too — it takes audio, so the same key reaches it at https://brain.deployd.network/ai/v1/audio/transcriptions. No per-minute rate: a recording is billed as the tokens it becomes, at the input price above.

curl https://brain.deployd.network/ai/v1/audio/transcriptions \
  -H "Authorization: Bearer ob_live_YOUR_KEY" \
  -F file=@audio.mp3 \
  -F model=thinkingmachines/inkling-small

# → { "text": "…what was said…" }

← all models · compare it with another · calling image, video and speech models