LLM Perks

Inkling Small

Thinking Machines Lab · All Inkling models
Free right now Small
ReasoningLong contextOpen weights

Inkling Small is a language model from Thinking Machines Lab. It is currently free at 1 provider with up to 1M tokens of context. The model supports step-by-step reasoning. Its weights are open, so it can also run locally.

Developer
Thinking Machines Lab
Context
1M tokens
Type
Text
License
Open weights

Where to use Inkling Small for free

Each row is a separate free endpoint with its own limits.

ProviderContextLimitCard
OpenRouter
thinkingmachines/inkling-small:free
1M Free tier No Open

Quick start

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "thinkingmachines/inkling-small:free",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Example for OpenRouter. Any OpenAI-compatible client works: Cursor, Cline, OpenCode, Open WebUI.

Benchmarks

Intelligence Index
27.8
GPQA Diamond
89.5%
Humanity's Last Exam
33.3%
Long context (LCR)
75.7%

Source: Artificial Analysis · Inkling Small

Similar free models

FAQ

Is Inkling Small free?

Yes. As of September 26, 2026, Inkling Small is free at OpenRouter. Each provider has its own limits — see the table above.

What is the context window of Inkling Small?

The largest context among free routes is 1,048,576 tokens. Some providers cap it lower.

How do I call Inkling Small via API?

Use any OpenAI-compatible client with base URL https://openrouter.ai/api/v1, model ID thinkingmachines/inkling-small:free, and a OpenRouter key.

How good is Inkling Small?

Artificial Analysis Intelligence Index: 27.8, GPQA Diamond: 90%. For comparison, the strongest free model in the catalog right now is GLM 5.3.

Is Inkling Small open-weight?

Yes, the weights are published — you can download and run it locally, for example with Ollama or LM Studio.