ModelPickr

Models / Thinking Machines / Inkling Small

Thinking Machines · ling

Inkling Small

Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio

$0.50 in · $1.20 out

per 1M tokens · provider rate closest to the median. No first-party Thinking Machines price was listed. The reference price is Arcee's rate, the provider closest to the median.

Provider input prices run from $0.45 to $0.80 per 1M tokens. Output prices run from $1.20 to $1.98.

Context
1,048,576
Max output
1,048,576
Cache read
$0.10
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Unknown
Vision
Yes
Open weights
Yes
License
Apache-2.0
Released
Jul 30, 2026
Updated in source
Jul 30, 2026
Knowledge
—
Providers
12

Hugging Face weights

What this model costs per month

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Providers

Base rates from Models.dev. Where a provider lists the model more than once, the row is the listing whose id is closest to the canonical model id.
ProviderInputOutputCache readCache writeStatus
Deep Infra$0.45$1.20$0.10——
Eden AI$0.45$1.20$0.10——
Kilo Gateway$0.45$1.20$0.10——
OpenRouter$0.45$1.20$0.10——
Vercel AI Gateway$0.45$1.20$0.10——
Arceereference$0.50$1.20$0.10—beta
Baseten$0.50$1.20$0.10——
Hugging Face$0.50$1.20———
NanoGPT$0.50$1.20$0.10——
Pioneer$0.50$1.20$0.10$0.50—
LLMTR$0.58$1.44———
AI/ML API$0.80$1.98$0.16——