Thinking Machines' Inkling 2 Small goes live on Together AI: 594B MoE, 1M context
togethercompute · x · 2026-11-13
Inkling 2 Small, the first model in Thinking Machines Lab's second Inkling generation, is now live on Together AI under Apache 2.0.
- MoE with 594B total / 17B active parameters, routing each token to 8 of 384 experts; 1M-token context; native image input; variable reasoning effort.
- Priced at $0.30/1M input and $1.00/1M output tokens on Together AI.
- Trained with an NVFP4-native pre-training run plus a single large unified RL run.
- Targets long-horizon agentic coding and autoresearch with self-verification, vision-in-the-loop for building/refining websites, games, and 3D designs, and spreadsheet/filing/document work in finance and legal; fine-tunes faster than the first-gen Inkling Small on the same data.
Related event: Thinking Machines open-sources Inkling 2 Small: 594B MoE under Apache 2.0(8 posts)→
More from Models
- Inkling 2 Small available on Nebius Token Factory from day 0 — Arindam_1729 · 2026-11-13
- Raon-1 nano tops consumer-GPU agent tests: 96/96 tasks, 187 tok/s at ~2GB Q4 — Kangwook_Lee · 2026-11-13
- Same harness, same rules: Argon used the code graph in 12/17 sessions, Opus only 4/17 — rseroter · 2026-11-13
- Massive eval table update benchmarks open-weight models across coding, finance, legal — siyan_zhao · 2026-11-13
- Did Kimi K3 and DeepSeek-V4-Pro each train on 2,000-3,000 Blackwells? Claim disputed — teortaxesTex · 2026-11-13
- Community notes: Ling's Blackwell usage was an open secret, papers admitted renting compute — teortaxesTex · 2026-11-13