Skip to content

Thinking Machines · Chat

Inkling 256K

Thinking Machines 🇺🇸ChatInkling familyOpen weights. One of its sources says the weights are publicly available.
From Requesty's listing:
Inkling 256K is the extended context variant of Inkling, a large MoE hybrid reasoning model from Thinking Machines with audio and vision input support and a 256K context window.
Market median price
$2.5725 blended / 1M
Max context
262K
Listings
1
Providers
1

Evidence and sources

Maker HQ: US (source)
Sources: Models.dev data, Requesty dataPrimary data from Models.dev from Requesty: description

Advantages and trade-offs

Compared with 10 representative chat models

Advantages

Open weights available

The weights are public. 4 of the 10 peers that say either way have open weights.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 6 maker's prices; 1 market median price.

Input & output

as stated by the model's providers
Text
Text

Listings

 RequestyInference by Thinking Machinesthinkingmachines/inkling-256kSource: Requesty data262K$1.87cache read $0.374$4.68

Benchmarks

No benchmark scores yet.

Around the web

  • Inkling: Our open-weights model - Thinking Machines Lab
    Inkling: Our open-weights model - Thinking Machines Lab Inkling is not the strongest overall model …Inkling: Our open-weights model - Thinking Machines Lab Inkling is not the strongest overall model available today, open or closed. Instead, a combination of qualities makes it a good open-weights ba…

    thinkingmachines.ai

  • Inkling - Thinking Machines Lab
    Inkling Inkling-Small Interaction Tinker Overview Docs Company About Connectionism News Careers Legal Terms of service …Inkling Inkling-Small Interaction Tinker Overview Docs Company About Connectionism News Careers Legal Terms of service Privacy notice Security Disclosure policy Connect X LinkedIn YouTube Thinking Ma…

    thinkingmachines.ai

  • thinkingmachines/Inkling · Hugging Face
    Inkling results are reported at effort=0.99. Comparison scores are generated Jul 14, 2026. Nemotron 3 …Inkling results are reported at effort=0.99. Comparison scores are generated Jul 14, 2026. Nemotron 3 Ultra, Kimi K2.5, Kimi K2.6, GLM 5.2, and DeepSeek V4 Pro are open weights models; Gemini 3.1 Pro…

    huggingface.co

  • Thinking Machines debuts Inkling, top U.S. open-weight AI model - Bay Area Times
    Inkling, top U.S. open-weight AI model Inkling scored 41 on the Artificial Analysis Intelligence Index …Inkling, top U.S. open-weight AI model Inkling scored 41 on the Artificial Analysis Intelligence Index , surpassing Nemotron 3 Ultra and Gemma 4 31B: X: Artificial Analysis. It costs $3.74/$9.36 per …

    bayareatimes.com

  • Thinking Machines bets on efficiency over size with its second model, Inkling Small
    above its weight. · Image: Artificial Analysis The model handles text, image, and speech inputs, …above its weight. · Image: Artificial Analysis The model handles text, image, and speech inputs, has a 256K-token context window, and ships under Apache 2.0. Weights are on Hugging Face , and users c…

    the-decoder.com

  • Thinking Machines has released Inkling, the new leading ...
    Thinking Machines has released Inkling, the new leading ... Jul 15, 2026 — Pricing per …Thinking Machines has released Inkling, the new leading ... Jul 15, 2026 — Pricing per 1M tokens (64K context window): $1.87 input / $0.374 cached / $4.68 output ➤ Pricing per 1M tokens (256K context…

    artificialanalysis.ai

  • Inkling Playground & API on Vercel AI Gateway — Providers
    that reasons over text, images, and audio. It supports controllable thinking effort and a context …that reasons over text, images, and audio. It supports controllable thinking effort and a context window of 256K tokens. Call Inkling on AI Gateway with thinkingmachines/inkling . Your use is subject…

    vercel.com

  • Thinkingmachines Models & Pricing | Vercel AI Gateway
    nkingmachines /inkling · 256K · 0.2s · 232tps · $1/M · $4.05/M · Read: $0.17/M …nkingmachines /inkling · 256K · 0.2s · 232tps · $1/M · $4.05/M · Read: $0.17/M Write: — · — · +1 · baseten logo togetherai logo · US · 07/15/2026

    vercel.com

  • Inkling Uptime | Vercel AI Gateway
    Inkling is an open-weights multimodal Mixture-of-Experts model that reasons over text, images, and audio. It …Inkling is an open-weights multimodal Mixture-of-Experts model that reasons over text, images, and audio. It supports controllable thinking effort and a context window of 256K tokens. Call Inkling on…

    vercel.com

  • models.dev/providers/thinkingmachines at dev - models.dev - Gitea
    Logo Explore Help Register Sign In yushanhe / models.dev Watch 1 Star 0 Fork 0 …Logo Explore Help Register Sign In yushanhe / models.dev Watch 1 Star 0 Fork 0 You've already forked models.dev mirror of https://github.com/anomalyco/models.dev.git synced 2026-08-13 05:59:09 +08:00…

    git.osc.life

Also known as: thinkingmachines/inkling-256k

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works