Inkling 2 Small
Released
2026-11-05
Last refreshed
2026-11-06
Status
Researched 3d ago
ProprietaryCommercial use: restrictedMultimodalRAGAgentsLong contextVisionJSON / Tool use
Thinking Machines Lab releases · 3 in the last 12 monthsChangelog →
Specifications
- Family
- Inkling
- Released
- 2026-11-05
- Context
- 256K
- Parameters
- 594B (17B active)
- Architecture
- Mixture of Experts
- Specialization
- general
- Openness
- Proprietary
- License
- ProprietaryRestricted
- Weights
- Not released
- Code
- Unknown
- Training
- Pretrained
Created by
Building collaborative AI aligned with human values.
San Francisco, California, United States
Founded 2025
WebsitePricing
Output / 1M
$1.00
Input / 1M
$0.300
Cheapest of 1 route · Tinker · cache read $0.030
Providers(1)
Links
About
Inkling 2 Small is Thinking Machines Lab's first second-generation Inkling model, released November 5, 2026. It is a 594B-total / 17B-active MoE for text and image inputs with controllable reasoning effort. It is available for inference and fine-tuning on Tinker; downloadable weights are closed at launch.
Providers(1)
Compare API pricing across 1 tracked provider route for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Cache | Route |
|---|---|---|---|---|
| Tinker | $0.300 | $1.00 | read $0.030 | Serverless |
Capabilities
VisionMultimodalReasoningJSON / Tool useFine-tuning
Benchmark peer barsfor RAG
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
API versions
thinkingmachines/Inkling-2-SmallRankings & picks(2)
Created by
Building collaborative AI aligned with human values.
San Francisco, California, United States
Founded 2025
WebsitePricing
Output / 1M
$1.00
Input / 1M
$0.300
Cheapest of 1 route · Tinker · cache read $0.030
Providers(1)
Links