Thinkingmachines

Inkling 2 Small

Generally availableOpen weights1M contextReasoning

Summary

Inkling 2 Small is an open-weight language model from Thinkingmachines, released on 5 Nov 2026. It accepts text and images and generates text, with a 1M-token context window and up to 262K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.30 per million input tokens and $1 per million output tokens (Cloudflare Workers AI), across 6 providers we track.

Multimodal MoE reasoning model (594B total, 17B active) for agentic coding, vision, and knowledge work

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperThinkingmachines
Release date5 Nov 2026 [models.dev]
StatusGenerally available [models.dev]
WeightsOpen weights [Hugging Face]
Licenseapache-2.0 [Hugging Face]
Parameters594B [Hugging Face]
Context window1M (1,048,576 tokens) [models.dev]
Max output262K tokens [models.dev]
InputText and images [models.dev]
OutputText [models.dev]
Reasoning modeYes [models.dev]
Tool callingYes [models.dev]
Structured outputYes [models.dev]
Hugging Facethinkingmachines/Inkling-2-Small [Hugging Face]

Inkling 2 Small API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
Cloudflare Workers AI
@cf/thinkingmachines/inkling-2-small
$0.30$1$0.101Mmodels.dev, 18 Nov 2026
DeepInfra
thinkingmachines/Inkling-2-Small
$0.30$1$0.031Mmodels.dev, 18 Nov 2026
Hugging Face Inference Providers
thinkingmachines/Inkling-2-Small
$0.30$1–1Mmodels.dev, 18 Nov 2026
Nebius AI Studio
thinkingmachines/Inkling-2-Small
$0.30$1$0.061Mmodels.dev, 18 Nov 2026
OpenRouter
thinkingmachines/inkling-2-small
$0.30$1$0.031MOpenRouter, 18 Nov 2026
Vercel AI Gateway
thinkingmachines/inkling-2-small
$0.30$1$0.031Mmodels.dev, 18 Nov 2026

Running Inkling 2 Small locally

Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.

QuantizationWeightsTotal, 8K contextTotal, 32K context
Q4_K_M (4-bit)360 GB363 GB367 GB
Q8_0 (8-bit)631 GB634 GB638 GB
FP16 / BF16 (16-bit)1188 GB1191 GB1195 GB

At 4-bit with an 8K conversation, Inkling 2 Small needs about 363 GB, more than any single consumer graphics card; it needs a unified-memory machine, a multi-GPU setup or a split between graphics card and system RAM. Check your own hardware, or see Best computer for local AI on our sister site AIPCs.

Frequently asked questions

What is the context window of Inkling 2 Small?

Inkling 2 Small has a context window of 1,048,576 tokens (1M) and can generate up to 262,144 tokens in a single response, according to models.dev.

How much does the Inkling 2 Small API cost?

Inkling 2 Small is listed from $0.30 per million input tokens and $1 per million output tokens (Cloudflare Workers AI). Prices last verified 18 Nov 2026.

Is Inkling 2 Small open source?

Inkling 2 Small is an open-weight model: its weights are published on Hugging Face as thinkingmachines/Inkling-2-Small under the apache-2.0 license. Check the license terms before commercial use.

When was Inkling 2 Small released?

Thinkingmachines released Inkling 2 Small on 5 Nov 2026, according to models.dev.

Which providers offer Inkling 2 Small?

We track Inkling 2 Small on 6 providers: Cloudflare Workers AI, DeepInfra, Hugging Face Inference Providers, Nebius AI Studio, OpenRouter, Vercel AI Gateway.

How much VRAM does Inkling 2 Small need?

About 363 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 634 GB at 8-bit. That is more than any single consumer graphics card holds. These are estimates from the model's published parameter count and architecture.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
Beam 1.0Reflection5 Oct 20261M$0.25$1Open
GLM 5.3 FlashX LegalZhipu AI (Z.ai)2 Nov 20261M$0.37$1.25–
MiMo-V2.6-ProXiaomi (MiMo)22 Sept 20261M$0.43$0.87Open
GLM 5.3 FlashXZhipu AI (Z.ai)18 Sept 20261M$0.37$1.25–
DeepSeek V4 ProDeepSeek13 Aug 20261M$0.11$0.87Open
NVIDIA Nemotron 3.5 Super VLNVIDIA15 Oct 20261M$0.15$0.50Open

Change history

  • Max output changed from 131K to 262K
  • Max output changed from 944K to 131K
  • Release date changed from 9 Nov 2026 to 5 Nov 2026
  • Max output changed from 1M to 944K
  • Now listed on Hugging Face Inference Providers
  • Now listed on Nebius AI Studio
  • Now listed on DeepInfra
  • Parameter count changed from 383B to 594B
  • License changed from none to apache-2.0
  • Parameter count changed from none to 383B
  • Now listed on OpenRouter
  • Now listed on Vercel AI Gateway
  • Now listed on Cloudflare Workers AI
  • Structured output changed from no to yes
  • Open weights changed from no to yes
  • Release date changed from 5 Nov 2026 to 9 Nov 2026
  • Max output changed from 131K to 1M
  • Name changed from Inkling 2 Small Free to Inkling 2 Small
  • Structured output changed from none to no
  • Added to the directory

Sources