T

Inkling Small

Jul 2026
TInkling Small
Compare in
on
$0.089per task?
$0.45 / $1.20per 1M in / out?
219 tok/sfirst token in 1.3 s?
256Kcontext

Run it yourself

estimate
Fits on✗ 8 GB (phone, laptop)✗ 16 GB✗ 24 GB GPU✗ 48 GB GPU✗ 80 GB GPU
LicenceApache-2.0free for commercial use

Benchmarks

in Vision & Documents

FAQ

How much does Inkling Small cost?›

$0.45 per 1M input tokens and $1.20 per 1M output tokens (cheapest host: DeepInfra). A typical benchmark task costs about $0.089 at default effort.

Is Inkling Small free to use?›

There is no free API; the cheapest paid price is $0.45 per 1M input tokens. The weights are open, so you can run it yourself.

How good is Inkling Small, and what is it best at?›

#72 of 334 in Chat & Knowledge, #54 of 132 in Coding, #86 of 133 in Agents & Tool Use, #120 of 195 in Writing & Language, #57 of 124 in Vision & Documents. Strongest at: Reasoning, Science.

Is Inkling Small better than Claude Opus 4.5?›

On MMMU-Pro (vision), Inkling Small scores 74 vs 74 — about the same.

How can I use Inkling Small?›

Through the API of DeepInfra.

What is the context window of Inkling Small?›

256K tokens, with up to 262K output tokens.

When was Inkling Small released? Is there a newer version?›

Released 2026-07-30. It is the current version in its line.

Is Inkling Small open source?›

Yes, the weights are open (Apache-2.0 licence).

Can I run Inkling Small locally?›

The weights are open and can be self-hosted; hardware needs are not confirmed yet.

Can Inkling Small read images?›

It accepts text and images, audio as input.

What is Inkling Small?›

Inkling Small is an open-weights language model from Thinking Machines, released Jul 2026.

What are the best alternatives to Inkling Small?›

GPT-6 Luna (cheaper), Qwen3.8 Flash (open weights).