TM
Context
1.0M tokens (~524 books)
Input $/1M
$0.30
Output $/1M
$1.00
Type
multimodal
License
Proprietary
Benchmarks
0 tested
Data as of
About
Inkling 2 Small is Thinking Machines Lab's multimodal MoE · 594B total and 17B active parameters · 1,048,576 token context · text and image in, text out · closed weights on Tinker for now with Apache 2.0 weights planned after safety testing · $0.30 input, $1.00 output and $0.03 cached input per million tokens.
No benchmark data available yet.
Links
Research
Documentation
Community
BenchGecko API
inkling-2-small
Specifications
- Typemultimodal
- Context1.0M tokens (~524 books)
- ReleasedNov 2026
- LicenseProprietary
- StatusActive
- Cost / Message~$0.002
Available On
TM
Thinking Machines$0.30Learn More
Share & Export
Frequently Asked Questions
Inkling 2 Small is a proprietary multimodal AI model by Thinking Machines, released in November 2026. Context window: 1M tokens.
Related Models
Qwen3 Coder Next FP8 · AlibabaQwen2.5 Coder 32B Instruct AWQ · AlibabaSpeaker Diarization Community 1 · PyannoteJais 3 0.9B · MBZUAIGemma 3 12B (free) · Google DeepMindBenchmarks
Key facts · as of 2026-11-09
- Inkling 2 Small by Thinking Machines. Not enough public benchmark scores to rank yet.
- List price $0.30 input · $1.00 output per 1M tokens (as of 2026-11-09).
How to cite · data as of 2026-11-09
Inkling 2 Small · benchmarks, pricing and providers. BenchGecko, data as of 2026-11-09. https://benchgecko.ai/model/inkling-2-small
Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP