LLM Pricing
PricingLeaderboardsToolsProvidersReleasesGuides

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Inkling (256K)

thinkingmachines·thinkingmachines/inkling-peft-262144·GA·Open weights·ling series·NEW
Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio

Specs & pricing

Input / output per 1M tokens
Official price·Thinking Machines
$3.74 / $9.36
Blended $5.15 · Cache read $0.75
Lowest paid·RequestyGateway
$1.87 / $4.68
Blended $2.57 · 2× spread
Context
262,144
Output limit
262,144
Knowledge cutoff
—
Released / updated
2026-07-15 / 2026-07-16
Capabilities
✓ Reasoning✓ Tool useStructured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImage

Available at 2 providers2 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Requesty
inkling-256k
Gateway$1.87$4.68$0.37—262,14432,768
Thinking MachinesOfficial
thinkingmachines/Inkling:peft:262144
First-party$3.74$9.36$0.75—262,144262,144

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.

Reasoning control

effort = noneeffort = loweffort = mediumeffort = higheffort = maxToggle (on / off)effort = xhigh

Your usage cost

1Requesty$428.48
2Thinking Machines · Official$856.96
Switch to Requesty to save $428.48/mo (50%)
Note: this is a gateway; verify availability and rate limits yourself.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$9.36$02026-08-052026-09-242026-08-05 · Input list $3.742026-08-06 · Input list $3.742026-08-07 · Input list $3.742026-08-08 · Input list $3.742026-08-09 · Input list $3.742026-08-10 · Input list $3.742026-08-11 · Input list $3.742026-08-12 · Input list $3.742026-08-13 · Input list $3.742026-09-24 · Input list $3.742026-08-05 · Output list $9.362026-08-06 · Output list $9.362026-08-07 · Output list $9.362026-08-08 · Output list $9.362026-08-09 · Output list $9.362026-08-10 · Output list $9.362026-08-11 · Output list $9.362026-08-12 · Output list $9.362026-08-13 · Output list $9.362026-09-24 · Output list $9.362026-08-05 · Min blended $5.152026-08-06 · Min blended $5.152026-08-07 · Min blended $5.152026-08-08 · Min blended $5.152026-08-09 · Min blended $5.152026-08-10 · Min blended $5.152026-08-11 · Min blended $5.152026-08-12 · Min blended $5.152026-08-13 · Min blended $5.152026-09-24 · Min blended $2.57

Related models

inLing 3.1 Flashsame series$0.075 / $0.22inLing 3.1 Flash (Free)same series$0 / $0inLing 3.0 Flash VLsame series$0.075 / $0.22GLM-5.2cheaper alternative$1.40 / $4.40GLM-5.3cheaper alternative$1.40 / $4.40GLM-5.3-Flashcheaper alternative$0.15 / $0.50DeepSeek V4.1 Flashcheaper alternative$0.15 / $0.60
Data partly from models.dev (MIT) · Thinking Machines official docs ↗