Inkling 2 Mini via the Tokenator API

What the model is for

Inkling 2 Mini is an open-weight multimodal looped transformer from Thinking Machines Lab, with 3.4B active parameters out of 26.4B total (MoE). Its middle layers run three times with shared weights, so it does more computation per token than its size suggests while staying small enough to run on a laptop or a single workstation GPU. It is the smallest model in the second Inkling generation, below Inkling 2 Small, and is suited for agentic and tool-use systems, coding assistants, chatbots and retrieval-augmented generation, with English and general multilingual support.

Specification

Full nameInkling 2 Mini
API IDinkling-2-mini
Model vendorThinking Machines
TypeText model (chat / completions)
Context window1.05M tokens
Max output65.5K tokens
Image inputyes
Tokenator usage multiplier1.4×
Output token multiplier4×
BadgeNEW
Input modalitiestext, image
Aliasescursor-inkling-2-mini
Supported API formats/v1/chat/completions /v1/responses /v1/messages
Upstream providers1
Current statusavailable
Data updated2026-11-22

Benchmarks

Intelligence index20.1

Artificial Analysis data loaded into the catalog for this model.

Upstream providers

ProviderMultiplierOutput token multiplier
Unified LLM API1.4×4×

A request goes to the first available provider by priority; if it fails, Tokenator switches to the next one.

Example request

curl
curl https://api.tokenator.top/v1/chat/completions \
  -H "Authorization: Bearer sk-your-tokenator-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "inkling-2-mini",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Compatible tools

The model can be used in any tool that accepts a custom base URL: Claude Code, Codex CLI, OpenCode, Cursor, Cline, Kilo Code, Cherry Studio, DeepSeek Harness, Hermes, Pi, OpenClaw.

FAQ about Inkling 2 Mini

What is the API ID of Inkling 2 Mini?

inkling-2-mini — put this into the model field of your request.

What context window does Inkling 2 Mini have?

1.05M tokens; max output is 65.5K tokens.

How many tokens will a request cost?

(input × 1.4×) + (output × 4×). See the documentation for details.

Which tools support this model?

Any tool that accepts a custom base URL: Claude Code, Codex CLI, OpenCode, Cursor, Cline, Kilo Code. Setup guides are in the integrations section.