← All models

thinkingmachines

Thinking Machines: Inkling 2 Mini

thinkingmachines/inkling-2-mini

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...

text

Try in Playground ↗

Input / 1M tokens$0.1
Output / 1M tokens$0.4
Context window1,048,576
Maximum output65,536

Provider-supported parameters

These are upstream capabilities. Jevrouter supports the subset described in the API contract; chat input is currently text only.

frequency_penaltyinclude_reasoninglogprobsmax_completion_tokensmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_pstreamdeveloper_role

Capabilities are imported from OpenRouter’s catalog. This does not mean every model has been independently tested by Jevrouter.

Catalog updated: 2026-11-21T10:54:46.156Z · Price version: cmwpxouxi9wviid10f4bx5h1l:2

Provider pricing fields · USD per indicated unit
{
  "prompt": "0.0000001",
  "completion": "0.0000004",
  "input_cache_read": "0.00000002"
}

Make a request

curl --no-buffer https://api.jevrouter.io/v1/chat/completions \
  -H "Authorization: Bearer $JEVROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d @- <<'JSON'
{
  "model": "thinkingmachines/inkling-2-mini",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "max_tokens": 1024
}
JSON

Plan your integration

Source: OpenRouter model catalog. Imported descriptions and capabilities are provider declarations, not independent benchmark results. Jevrouter currently uses OpenRouter as its managed upstream.