Multimodal Open Models Model serving Inference Optimization Inkling Benchmarks

Inkling

Open weights, ready to tinker

Inkling is an open-weights, general-purpose multimodal autoregressive transformer model from Thinking Machines Lab. The official model card states it accepts text, image, and audio inputs and generates text outputs; it is a sparse Mixture-of-Experts model with 975B total parameters, 41B active parameters, Apache 2.0 licensing, and support for up to a 1M-token context window.

Pricing

Model profile · Current snapshot

Input / 1M

$1.00

Output / 1M

$4.05

Blended / 1M

$1.76

Output TPS

80.15

TTFT (s)

2.15

Model Intelligence

Context window

1,000,000 tokens

Arena ranking

Benchmarkable

Yes

Model level

release

Intelligence Index

42.3

Coding Index

52.1

GPQA

0.87

HLE

0.32

SciCode

0.46

LCR

0.73

Recent stories

3 linked stories

releaseSECONDARY2026-07-30

Thinking Machines releases Inkling-Small 276B open-weight MoE

Thinking Machines released Inkling-Small, a 276B-parameter MoE with 12B active parameters, multimodal inputs, and a 1M-token context window. Providers added day-zero vLLM, SGLang, Modal, and gateway support.

newsPRIMARY2026-07-16

Inkling adds early llama.cpp serving via 1-bit GGUF

Inkling's 1-bit GGUF ran in llama.cpp at 30–40 TPS, and TokenSpeed added day-zero support with a flat KV cache pool. Arena posts put Inkling #10 among open models in frontend code and text, while docs drew scrutiny.

releasePRIMARY2026-07-15

Thinking Machines releases Inkling: 975B open-weight multimodal MoE

Thinking Machines released Inkling with Apache 2.0 weights, 975B parameters, 41B active parameters, text/image/audio support, and up to 1M context. vLLM, SGLang, Modal, Databricks, and Vercel added day-zero support.