Skip to contentx402 is live on Robinhood Chain: agents can now pay for any model, per call, in USDG →
OmniRail
← All models

Thinking Machines · Language model

Inkling

thinkingmachines/inkling
  • Language
Released Jul 17, 2026

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...

Specifications

Context window
524,288 tokens
Max output
471,859 tokens
Input
text, image, audio
Output
text
Reasoning effort
max, high, medium, low, minimal, none
Tokenizer
Other

Supported parameters

Accepted by the model and forwarded as-is by the gateway.

  • 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

Use it

POST /api/v1/chat/completions · MCP chat · full reference

curl https://omnirail.org/api/v1/chat/completions \
  -H "Authorization: Bearer $OMNIRAIL_KEY" -H "Content-Type: application/json" \
  -d '{"model":"thinkingmachines/inkling","messages":[{"role":"user","content":"Hello"}],"max_tokens":300}'