All models

Inkling 256K

thinkingmachines/inkling-256k
Thinking Machines LLMChat

Inkling with a 256K context window for long documents and codebases.

Quick start

# Inspect the price — a plain request returns the 402 challenge:
curl -i https://api.glianalabs.com/v1/chat/completions \
  -H "content-type: application/json" \
  -d '{
    "model": "thinkingmachines/inkling-256k",
    "max_tokens": 0,
    "messages": [{"role": "user", "content": "<your message>"}]
  }'

# Pay + run in one step with the mppx CLI (create a wallet: npx mppx account create):
npx mppx https://api.glianalabs.com/v1/chat/completions \
  -J '{"model": "thinkingmachines/inkling-256k", "max_tokens": 0, "messages": [{"role": "user", "content": "<your message>"}]}'

Parameters

Input
max_tokens number required
messages array required
metadata object optional
stream boolean optional
system string optional
temperature number optional
top_k number optional
top_p number optional
Output
Chat completion (OpenAI-compatible)