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...
11 providers
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
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,...
21 providers
MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...
23 providers
Open multimodal Qwen MoE for local agents that need vision, audio, and code
19 providers
Turkish-language multimodal instruct model built on Gemma 3 12B for e-commerce text, chat, and image-text tasks
1 provider
Large open Qwen multimodal MoE for visual agents and long technical tasks
18 providers
| Model | Creator | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| Thinking Machines: Inkling Smallthinkingmachines/inkling-small | Thinkingmachines |
524.288K | $0.45 | $1.2 | 2026-07-30 | ||
| Thinking Machines: Inklingthinkingmachines/inkling | Thinkingmachines |
524.288K | $1 | $4.05 | 2026-07-15 | ||
| Xiaomi: MiMo-V2.5xiaomi/mimo-v2.5 | Xiaomi |
1.04858M | $0.14 | $0.28 | 2026-04-22 | ||
| Qwen3.6 35B-A3Balibaba/qwen3.6-35b-a3b | Alibaba Qwen |
262.144K | $0.248 | $1.485 | 2026-04-17 | ||
| Trendyol Asure 12Btrendyol/asure-12b | 131.072K | $0.1 | $0.5 | 2026-02-19 | |||
| Qwen3.5 397B-A17Balibaba/qwen3.5-397b-a17b | Alibaba Qwen |
262.144K | $0.6 | $3.6 | 2026-02-15 |