Inkling
Active Parameters
975B
Context Length
1.05M
Modality
Multimodal
Architecture
Mixture of Experts
KV Cache Rate
264 KB/tok
License
Apache 2.0
Release Date
15 Jul 2026
Knowledge Cutoff
-
API Pricing (per 1M)
Input: $1.00 · Output: $4.05
Hardware Sizing
Precision
Context
Workload Memory: 1897.01 GB
FP16 · 8K context
Base Weights: 1892.45 GB
KV Cache: 2.06 GB
Runtime & Graphs: 2.50 GB
Minimum Required Hardware
Cluster: 16x NVIDIA H200 141GB
1897.0 / 2030.4 GB usable · TP 8 · PP 2
Determine requirements for datacenter hardware:
Upgrade to Pro
Architecture Diagram
Evaluation Benchmarks
Rank
#126
| Benchmark | Score | Rank |
|---|---|---|
Agentic Coding | max 0.49 | 39 |
Mathematics | max 0.88 | 39 |
Data Analysis | max 0.73 | 41 |
General | max 0.72 | 49 |
LiveBench Average | max 0.72 | 49 |
Coding | max 0.71 | 55 |
Reasoning | max 0.78 | 55 |
Agent Arena | -15.8 | 63 |
Agentic Index | max 0.23 | 75 |
Web Development | 1415 | 76 |
General Text | 1442 | 76 |
Coding Index | max 0.52 | 82 |
Intelligence Index | max 0.13 | 218 |
Rankings
Overall Rank
#126
Coding Rank
#89
About Inkling
Inkling is a general-purpose open-weights 975B Mixture-of-Experts (MoE) multimodal model developed by Thinking Machine Labs. It features a 1M token context window, relative position embeddings for superior extrapolation, and native support for text, image, and audio inputs.
Technical Specifications
Attention
Attention Structure
Multi-Head Attention
Attention Heads
64
Key-Value Heads
8
Attention Head Dimension
128
Position Embedding
Relative Position Embedding
Sliding Window Attention
Yes
Sliding Window Size
512
Sliding Window Ratio
83.3%
Normalization
RMS Normalization
Dimensions
Hidden Dimension Size
6,144
Number of Layers
66
FFN Intermediate Size (Dense)
24,576
Multi-Token Prediction Heads
8
Tokenizer
Vocabulary Size
201,024
Mixture of Experts
Total Expert Parameters
41.0B
Number of Experts
256
Active Experts
6
Shared Experts
2
FFN Intermediate Size (per Expert)
3,072
About Inkling
Inkling is a family of open-weights multimodal Mixture-of-Experts (MoE) models developed by Thinking Machine Labs.