All models
Thinkingmachines
Inkling balancedruns locally
thinkingmachines/inkling
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,...
Input / 1M
$1.00
USD per million tokens
Output / 1M
$4.05
USD per million tokens
Est. cost / token
$0.000001763
$1.76 per 1M, 3:1 mix
Context window
524K
max output 472K
Major features
VisionOpen weightsCachingReasoningTools
Task suitability (heuristic 1–5, not a benchmark)
- coding4
- reasoning4
- math4
- summarization4
- extraction4
- classification4
- chat4
- creative4
- translation4
- vision4
- long context4
- agentic4
Run it locally
Will it run on my machine? →| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 427 GB |
| Q3_K_M | fair | 497 GB |
| Q4_K_Mrecommended | good | 620 GB |
| Q5_K_M | very good | 720 GB |
| Q6_K | excellent | 829 GB |
| Q8_0 | near-lossless | 1071 GB |
| F16 | lossless | 2009 GB |
Estimates.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $1.00 | $4.05 | $0.17 | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $1.00
- Output
- $4.05
- Cached input
- $0.17
- Blended (3:1)
- $1.76
Details
- Company
- Thinkingmachines
- Version
- —
- Family
- Inkling
- Released
- 2026-07-17
- Parameters
- 952.4B
- Max output
- 472K
- Open weights
- Yes
- Inputs
- audio, image, text
- Last synced
- 32 min ago