Inkling 2 Small
NEWThinking Machines · Open weights · Released Nov 9, 2026 · thinkingmachines/inkling-2-small
Best $0.15 in / $0.50 out via PrimeIntellect · fp4
1.05M contextVisionToolsReasoningStructured outputPrompt cachingOpen weights
Available from 5 providersUSD / MTOK · PRICES 14 MINUTES AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
 PrimeIntellect | $0.15 | $0.50 | $0.03 | 1.05M | fp4 | — | — | 99.4% |
 Cloudflare | $0.30 | $1.00 | $0.10 | 1.05M | — | — | — | 100.0% |
 Modal | $0.30 | $1.00 | $0.03 | 1.05M | nvfp4 | — | — | 100.0% |
 Nebius | $0.30 | $1.00 | $0.06 | 1.05M | fp4 | — | — | 99.5% |
 Together | $0.30 | $1.00 | $0.03 | 1.05M | — | — | — | 100.0% |
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Pricing variants · USD / MTok in / out
STANDARD
$0.15 / $0.50
per MTok in / out
FREE
Free / Free
per MTok in / out
CACHE READ $0.03
Recent changesRSS ↗
Nov 13, 2026model added
About
Inkling 2 Small is an open-weight multimodal mixture-of-experts reasoning model from Thinking Machines Lab, with 17B active parameters out of 594B total. It is the first model in the second...
Specifications
Context window1,048,576
Max output943,718
Modalities intext, image
Modalities outtext
LicenseOpen weights
ReleasedNov 9, 2026
TokenizerOther
WeightsHugging Face ↗
Open weights
safetensors
Embed badge
[](https://modelindex.ai/models/thinkingmachines/inkling-2-small)Sources
OpenRouter API14 minutes ago
AGGREGATORHugging Face14 minutes ago
COMMUNITYVerified 14 minutes ago · list prices, not negotiated rates.