← Model list

Inkling

thinkingmachines·thinkingmachines/inkling·GA·Open weights·ling series·Video gen·NEW

Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio

At a glance
Official price$1.87 / $4.68 per 1M
Cache read $0.374 · Thinking Machines
Lowest paid$0.95 / $4.05
Deep Infra Cloud · 3.9× spread
1 more $0 channels
Context65,536
⚠ Providers report 65,536–1,048,576; the table below is authoritative
Output limit65,536
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
TextImageAudioPDF
Knowledge cutoff
Released / updated2026-07-15 / 2026-07-15

Quality & performanceArtificial Analysis · Intelligence Index v4.1 · rep. tier xhigh

Intelligence42.3
Value25
Coding52.1
Agentic34.1
Output speed74 tok/s
TTFT1.82 s
Cost per task$0.3389
Value formulaIQ 42.3 ÷ min blended $1.725 = 25

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 21 providers19 with public prices · 1 free

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
NvidiaFirst-partyFree1,048,57616,384
Deep Infra
thinkingmachines/Inkling
Cloud$0.95$4.05$0.16524,2881,048,576
OpenRouterGateway$0.95$4.05$0.161,048,576262,144
Eden AI
deepinfra/thinkingmachines/Inkling
Gateway$0.95$4.05$0.16524,2881,048,576
Kilo GatewayGateway$0.95$4.05$0.16524,288262,144
NanoGPTGateway$1.00$4.05$0.171,048,00032,768
Hugging Face
thinkingmachines/Inkling
Cloud$1.00$4.051,048,5761,048,576
Merge GatewayGateway$1.00$4.05$0.171,048,00032,000
Together AI
thinkingmachines/Inkling
Cloud$1.00$4.05$0.17524,288131,072
BasetenCloud$1.00$4.051,048,57632,768
Thinking MachinesOfficial
thinkingmachines/Inkling
First-party$1.87$4.68$0.37465,53665,536

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

1Deep Infra$297.70
2OpenRouter$297.70
3Eden AI$297.70
4Kilo Gateway$297.70
5NanoGPT$302.90
6Merge Gateway$302.90
17Thinking Machines · Official$428.48

1 more channels offer $0 (Nvidia); free tiers usually have rate limits and no SLA, excluded from ranking.

Switch to Deep Infra to save $130.78/mo (31%)

Benchmark

No upstream benchmark data for this model. For quality, see the Artificial Analysis intelligence score above.

Reasoning control

effort = noneeffort = minimaleffort = loweffort = mediumeffort = higheffort = maxeffort = xhighbudget_tokensToggle (on / off)

6 / 21 providers expose no reasoning control (reasoning_options: []).

Related models

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$4.68$02026-08-052026-08-132026-08-05 · Input list $1.872026-08-06 · Input list $1.872026-08-07 · Input list $1.872026-08-08 · Input list $1.872026-08-09 · Input list $1.872026-08-10 · Input list $1.872026-08-11 · Input list $1.872026-08-12 · Input list $1.872026-08-13 · Input list $1.872026-08-05 · Output list $4.682026-08-06 · Output list $4.682026-08-07 · Output list $4.682026-08-08 · Output list $4.682026-08-09 · Output list $4.682026-08-10 · Output list $4.682026-08-11 · Output list $4.682026-08-12 · Output list $4.682026-08-13 · Output list $4.682026-08-05 · Min blended $1.732026-08-06 · Min blended $1.732026-08-07 · Min blended $1.732026-08-08 · Min blended $1.732026-08-09 · Min blended $1.732026-08-10 · Min blended $1.732026-08-11 · Min blended $1.732026-08-12 · Min blended $1.732026-08-13 · Min blended $1.73