---
id: "thinkingmachines/inkling-small"
also: ["thinkingmachines/inkling-small-20260730", "thinkingmachines/Inkling-Small", "hf/thinkingmachines/Inkling-Small", "vercel/thinkingmachines/inkling-small"]
cheapest_list_usd_per_m: "0.3 in, 1.2 out, at thinkingmachines on vercel"
cheapest_effective_usd_per_m: "0.1244 in, 1.1995 out, at baseten/fp8 on openrouter"
context: 524288
max_output: 262144
input: ["text", "image", "audio"]
output: ["text"]
released: "2026-07-30"
reasoning: ["max", "high", "medium", "low", "minimal", "none"]
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "reasoning_effort", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p"]
endpoints: 11
gateways: "vercel (5), hf (3), openrouter (3)"
no_training: 7
trains: 1
retains_prompts: 2
intelligence: 12.9000
coding: 52.9000
agentic: 23.5000
---
# Thinking Machines: Inkling Small

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...