When was Inkling-Small released?

Thinking Machines released Inkling-Small on 30 Jul 2026. It is available through the Opper gateway.

Does Inkling-Small support zero data retention?

Yes. Inkling-Small is available with zero data retention on DeepInfra through the Opper gateway.

Where is Inkling-Small hosted?

Inkling-Small runs on US hosting routes through the Opper gateway.

Is Inkling-Small trained on prompts and outputs?

No. Every hosting route for Inkling-Small is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Inkling-Small?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Inkling-Small. Contact hello@opper.ai to receive it.

Inkling-Small

by Thinking Machines

Released 15 days after Inkling · All Thinking Machines releases

Inkling-Small is the smaller sibling of Inkling, previewed alongside the flagship in July 2026 and released with full weights on July 30, 2026 under Apache 2.0. It keeps the Inkling recipe in a 42-layer body with 276 billion total and 12 billion active parameters, each token drawing on 6 of 256 routed experts together with 2 shared ones, and it takes text, image, and audio input and produces text. Thinking Machines reports that the smaller model lands close to, and on several coding benchmarks above, the 975B Inkling: 80.2% on SWE-bench Verified against 77.6% for the larger model, 89.5% on GPQA Diamond, 95.5% on AIME 2026, 90.2% on HMMT February 2026, 74.0% on MMMU Pro, and 47.8% on Humanity's Last Exam with tools. The lab aims it at agent and tool-use systems, coding assistants, chat, and retrieval-augmented generation. Weights are available in BF16 and NVFP4, and the model can be fine-tuned on the Tinker platform, so it suits teams that want the Inkling recipe at a per-token compute budget closer to a mid-sized dense model.

Call Inkling-Small on Opper with the OpenAI SDK. Sign up without a credit card. Get started

Get your API key Try in chat Compare

Key info

Input

Output

Features

Context window

524K

Max output

524K

Input price

$0.45 /1M$0.10 cache read

Output price

$1.20 /1M

Released

30 Jul 2026

US residency available
Zero data retention on pay-as-you-go
No training by default
GDPR DPA available

Available routes

Inkling-Small runs on 1 route through the Opper gateway. Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below.

Provider	Region	Zero data retention	Training	Input	Output	Cache read
DeepInfra	US		No	$0.45	$1.20	$0.10

Uptime and availability

Inkling-Small runs on a single route through the Opper gateway today, so its availability is that provider's availability.

100%route uptime, last 30 days

Single route, no failover target within this model.

Name a second model in the same request and the gateway tries it on retriable errors, so a busy hour never has to reach your users. Set up a fallback chain.

Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. See uptime for every provider Opper monitors.

Data handling per route

Each route hosting Inkling-Small has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

DeepInfra — United States🇺🇸

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; unknown; DPA available.

Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
Training: No training on customer data.
Logging: None
Abuse monitoring: No classifier
GDPR DPA: DPA available
Transfer mechanism: unknown

Benchmarks

Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.

Global rank#145 of 677 LLMs

TierEfficient

Output speed200 tok/s

First token1.87s

Intelligence Index25.7

Coding Index52.9

Reasoning & knowledge

GPQA Diamond

90%

Humanity's Last Exam

33%

Long-context reasoning

76%

Coding

SciCode

50%

See full leaderboard →Benchmarks via Artificial Analysis · View on AA

Get started

Call Inkling-Small through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

Inkling-Small is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

Set it up with your agent

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.

Or call it directly

1import OpenAI from "openai";
2
3const client = new OpenAI({
4  apiKey: process.env.OPPER_API_KEY,
5  baseURL: "https://api.opper.ai/v3/compat",
6});
7
8const completion = await client.chat.completions.create({
9  model: "deepinfra/thinkingmachines/Inkling-Small",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);