Thinkingmachines

About Thinkingmachines

Thinking Machines Lab is an artificial intelligence research and product company. We’re building a future where everyone has access to the knowledge and tools to make AI work for their unique needs and goals.

While AI capabilities have advanced dramatically, key gaps remain. The scientific community’s understanding of frontier AI systems lags behind rapidly advancing capabilities. Knowledge of how these systems are trained is concentrated within the top research labs, limiting both the public discourse on AI and people’s abilities to use AI effectively. And, despite their potential, these systems remain difficult for people to customize to their specific needs and values. To bridge the gaps, we’re building Thinking Machines Lab to make AI systems more widely understood, customizable, and generally capable.

We are scientists, engineers, and builders who’ve created some of the most widely used AI products, including ChatGPT and Character.ai , open-weights models like Mistral , as well as popular open source projects like PyTorch , OpenAI Gym , Fairseq , and Segment Anything .

Website ↗Documentation ↗

Source ↗ · 2026-11-12T02:17:05.050420409Z

6 indexed models

6 matching models

Thinking Machines: Inkling 2 Small (free)

thinkingmachines/inkling-2-small-20261107

Inkling 2 Small is a multimodal mixture-of-experts reasoning model from Thinking Machines Lab, with 17B active parameters out of 594B total. It is the first model in the second Inkling generation. It was trained with reinforcement learning on long-horizon coding tasks across many

Context window
1,048,576
Input modalities
text, image
Output modalities
text
Capabilities
multimodal, reasoning, toolCalling, visionInput

Benchmarks

  • Artificial Analysis: 30.6
  • OpenRouter Benchmarks: 91.077%

Inference prices

Thinking Machines: Inkling Small

thinkingmachines/inkling-small-20260730

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of the Inkling family and is suited for reasoning, coding, agentic workflows, retri

Context window
524,288
Input modalities
text, image, audio
Output modalities
text
Capabilities
audioInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput

Benchmarks

  • Artificial Analysis: 12.9
  • OpenRouter Benchmarks: 87.037%

Inference prices

  • Published price : $0.10 / cache_read_tokens_per_million · openRouter ↗
  • Published price : $0.45 / input_tokens_per_million · openRouter ↗
  • Published price : $1.20 / output_tokens_per_million · openRouter ↗

Thinking Machines: Inkling

thinkingmachines/inkling-20260715

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems, retrieval-augmented generation, instruction following, and m

Context window
524,288
Input modalities
text, image, audio
Output modalities
text
Capabilities
audioInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput

Benchmarks

  • Artificial Analysis: 12.5
  • OpenRouter Benchmarks: 69%

Inference prices

  • Published price : $0.17 / cache_read_tokens_per_million · openRouter ↗
  • Published price : $1.00 / input_tokens_per_million · openRouter ↗
  • Published price : $4.05 / output_tokens_per_million · openRouter ↗

Inkling-NVFP4

vertexAI/publishers/thinkingmachines/models/inkling@inkling-nvfp4

Input modalities
text
Output modalities
text

Inkling-Small-NVFP4

vertexAI/publishers/thinkingmachines/models/inkling@inkling-small-nvfp4

Input modalities
text
Output modalities
text

thinkingmachines: Inkling 256K

cloudflareWorkersAI/thinkingmachines/inkling-256k

The 256K-context variant of Inkling, Thinking Machines' open-weights hybrid reasoning MoE model. Same hybrid reasoning, tool-use, and streaming support as the base model, with an extended context window for longer conversations and documents. Currently intended for low-traffic te

Context window
262,144
Input modalities
text
Output modalities
text
Capabilities
reasoning

Inference prices

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace