LLM Pricing
PricingLeaderboardsToolsProvidersReleasesGuides

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← 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

Inkling by thinkingmachines is offered by 20 providers on this page. Public prices are shown for 19 of them. Its official list price is $1.87 per 1M input tokens and $4.68 per 1M output tokens. The lowest paid channel is Deep Infra at $0.95 / $4.05 per 1M, about 3.9× below the list price. It also has 1 free ($0) channel; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.

Artificial Analysis rates it 42.3 on the Intelligence Index, with 52.1 for coding and 34.1 for agentic tasks. Against its lowest blended price of $1.73 per 1M, that is roughly 25 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 73 tokens per second, with 2.36s to the first token. Running one task of the Artificial Analysis suite costs about $0.3389, which reflects how many tokens its reasoning consumes rather than the unit price alone.

The context window is 65,536 tokens at the reference host, but hosts report different limits, from 65,536 to 1,048,576, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, Audio, and PDF. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use.

Specs & pricing

Input / output per 1M tokens
Official price·Thinking Machines
$1.87 / $4.68
Blended $2.57 · Cache read $0.374
Lowest paid·Deep InfraCloud
$0.95 / $4.05
Blended $1.73 · 3.9× spread
1 more $0 channels
Context
65,536
Output limit
65,536
Knowledge cutoff
—
Released / updated
2026-07-15 / 2026-07-15
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImageAudioPDF

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

Intelligence42.3
Value25
Coding52.1
Agentic34.1
Output speed73 tok/s
TTFT2.36 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 20 providers19 with public prices · 1 free

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
NvidiaFirst-partyFree——1,048,576 ⚠16,384
Deep Infra
thinkingmachines/Inkling
Cloud$0.95$4.05$0.16—524,288 ⚠1,048,576
Kilo GatewayGateway$0.95$4.05$0.16—524,288 ⚠471,859
NanoGPTGateway$1.00$4.05$0.17—1,048,000 ⚠32,768
Hugging Face
thinkingmachines/Inkling
Cloud$1.00$4.05——1,048,576 ⚠1,048,576
BasetenCloud$1.00$4.05——1,048,576 ⚠32,768
Vercel AI GatewayCloud$1.00$4.05$0.17—256,000 ⚠256,000
Fireworks AICloud$1.00$4.05$0.17—1,048,576 ⚠1,048,576
Merge GatewayGateway$1.00$4.05$0.17—1,048,000 ⚠32,000
OpenRouterGateway$1.00$4.05$0.17—1,048,576 ⚠471,859
Thinking MachinesOfficial
thinkingmachines/Inkling
First-party$1.87$4.68$0.374—65,53665,536

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
2Kilo Gateway$297.70
3NanoGPT$302.90
4Vercel AI Gateway$302.90
5Fireworks AI$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%)

Reasoning control

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

6 / 20 providers expose no reasoning control (reasoning_options: []).

Related models

inLing 3.0 Flash Sante (Free)same series$0 / $0inLing 3.0 Flash Santesame series$0 / $0inLing 3.0 Flash Finsame series$0.06 / $0.18DeepSeek V4 Flashcheaper alternative$0.14 / $0.28DeepSeek V4 Procheaper alternative$0.435 / $0.87GLM-5.3-Flashcheaper alternative$0.075 / $0.25DeepSeek V4 Flash 0731cheaper alternative$0.445 / $1.34

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
Data partly from models.dev (MIT) · Thinking Machines official docs ↗