Inkling
Thinking Machines · Open weights · Released Jul 17, 2026 · thinkingmachines/inkling
Best $0.95 in / $4.05 out via DeepInfra · fp8
524K contextVisionToolsReasoningPrompt cachingAudio inputOpen weights
Available from 2 providersUSD / MTOK · PRICES 23 MINUTES AGO · SPEED 14 DAYS 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 | 0.38s | 261 tok/s | 100.0% |
 Together | $1.00 | $4.05 | $0.17 | 524K | — | 0.51s | 134 tok/s | 87.0% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 14 days ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Pricing variants · USD / MTok in / out
STANDARD
$0.95 / $4.05
per MTok in / out
FREE
Free / Free
per MTok in / out
CACHE READ $0.16
Recent changesRSS ↗
Sep 26, 2026endpoint removed · baseten4 → 2
Sep 26, 2026context changed1048576 → 524288
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 window524,288
Max output471,859
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 API23 minutes ago
AGGREGATORHugging Face23 minutes ago
COMMUNITYModelIndex benchmarks20 days ago
MEASUREDVerified 23 minutes ago · list prices, not negotiated rates.