Inkling
ModelOpen sourceActiveby Thinking Machines Lab · family “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,... (description from the OpenRouter listing)
in: textin: imagein: audioout: textReasoningTool use
Epoch Capabilities Index
148.6 #57 of 268
90% CI 145.9 – 150.5
Released
15 Jul 2026
Context window
524K tokens
Max output
472K tokens
Input $ / 1M tokens
$1.00
Output $ / 1M tokens
$4.05
Cached input $ / 1M
$0.17
Each benchmark shown separately with its own source
Benchmark results (7)
| Benchmark | Domain | Score | vs best recorded | Setting | Run | Source |
|---|---|---|---|---|---|---|
| FrontierCode | coding | 14.0% | 26% | — | — | External ↗ |
| ProofBench | math | 0.0% | 0% | — | — | External ↗ |
| APEX-Agents | agents | 33.8% | 49% | — | — | External ↗ |
| ARC-AGI-2 | reasoning | 36.5% | 38% | — | — | External ↗ |
| WeirdML | coding | 32.3% ±0.0 | 35% | high | — | External ↗ |
| SimpleBench | reasoning | 50.0% | 61% | — | — | External ↗ |
| ARC-AGI | reasoning | 79.5% | 81% | — | — | External ↗ |
Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.
API list price over time
Price history
$ per 1M tokens
3 observations (OpenRouter listing + Internet Archive snapshots). History accumulates with every ingest run; a single point means no change has been observed yet.
Events
- Open release3mo agoThinking Machines releases InklingEpoch AI Benchmarking Hub