Inkling
Thinking Machines · Open weights · Released Jul 17, 2026 · thinkingmachines/inkling
1.05M contextVisionToolsReasoningStructured outputPrompt cachingAudio inputOpen weights
Available from 3 providersUSD / MTOK · VERIFIED 13 MINUTES AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
 DeepInfra | $0.95 | $4.05 | $0.16 | 524K | fp8 | 0.46s | 199 tok/s | 97.7% |
 Together | $1.00 | $4.05 | $0.17 | 524K | — | 0.68s | 151 tok/s | 99.8% |
 BaseTen | $1.00 | $4.05 | $0.17 | 1.05M | fp8 | 0.57s | 248 tok/s | 100.0% |
TTFT/TPS: median (P50) over trailing 72h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 44 hours ago
Pricing variants · USD / MTok in / out
STANDARD
$0.95 / $4.05
per MTok in / out
BATCH
$1.00 / $4.05
async batch
FREE
Free / Free
per MTok in / out
CACHE READ $0.16
About
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,...
Specifications
Context window1,048,576
Max output—
Modalities intext, image, audio
Modalities outtext
LicenseOpen weights
ReleasedJul 17, 2026
TokenizerOther
WeightsHugging Face ↗
Open weights
safetensors
Related
Embed badge
[](https://modelindex.ai/models/thinkingmachines/inkling)Sources
OpenRouter API13 minutes ago
AGGREGATORHugging Face13 minutes ago
COMMUNITYModelIndex benchmarks44 hours ago
MEASUREDVerified 13 minutes ago · list prices, not negotiated rates.