All Thinking Machines releases
Inkling is the first model Thinking Machines Lab trained from scratch, released in July 2026 with fully open weights. It is a Mixture-of-Experts transformer carrying 975 billion total parameters and 41 billion active per token, pretrained on 45 trillion tokens spanning text, images, audio and video, with a context window reaching 1 million tokens. The lab is unusually direct that Inkling is not the strongest model available, open or closed, positioning it instead as a base worth customizing. Thinking effort is adjustable when speed matters more than depth, and the model is tuned to answer with calibration, flagging uncertainty rather than guessing at it. Open weights, multimodal input and fine-tuning support together suit teams building a specialized model on top of a general base rather than calling one behind somebody else's API.
Inkling runs on 1 route through the qynio gateway. Compare residency, zero retention, and training posture at a glance — full data-handling detail per route below.
| Provider | Region | Zero data retention | Training | Input | Output |
|---|---|---|---|---|---|
| Multi | Zero data retention | No | $1.00 | $4.05 |
Inkling runs on a single route through the qynio gateway today, so its availability is that provider's availability.
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. .
Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. See uptime for every provider qynio monitors.
Each route hosting Inkling has its own privacy posture, residency, and no-KYC terms. Postures are maintained by qynio with a last-verification timestamp.
Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. GLOBAL; wallets; deposit available.
Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.
Call Inkling through the qynio gateway with one API key. Let your coding agent set it up, or call it directly — qynio is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.
Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up qynio for you.
import OpenAI from "openai";const client = new OpenAI({apiKey: process.env.QYN_API_KEY,baseURL: "https://api.qyn.io/v3/compat",});const completion = await client.chat.completions.create({model: "fireworks/inkling",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, crypto rails, pricing, and benchmarks.
