Piramyd
All models

Thinking Machines

Inkling

inkling

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total.

Context window
524K

tokens

Max output
472K

tokens per response

Input
Text, Images, Audio
Price per token
$0

included in your plan

Capabilities

  • Reasoning
  • Image input
  • Tool calling

Reasoning effort: low, medium, high, xhigh

API

  • OpenAI Chat CompletionsPOST /v1/chat/completions

Supported parameters

  • frequency_penalty
  • logit_bias
  • max_tokens
  • min_p
  • presence_penalty
  • reasoning
  • reasoning_effort
  • repetition_penalty
  • seed
  • stop
  • temperature
  • tool_choice
  • tools
  • top_k
  • top_p

Quickstart

Any OpenAI-compatible client works; point it at Piramyd and use your key. In a coding agent, run npx piramyd instead.

curl https://api.piramyd.cloud/v1/chat/completions \
  -H "Authorization: Bearer $PIRAMYD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "inkling",
  "messages": [
    {
      "role": "user",
      "content": "Refactor this function to be pure: ..."
    }
  ]
}'

Also on Piramyd

Stop rationing your agents.
Let them finish the job.

The agents you already use, every frontier model, and a bill that doesn’t move when they work harder.

Start 3-day trial

3-day trial on Solo · Card required · Cancel before day 4 and pay nothing

For AI agents

Give this link to any agent: it describes the whole API.