Thinking Machines: Inkling
budgetthinkingmachines/inkling
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,...
AA INDEX25.0
CONTEXT524K
MODALITYtext+image+audio->text
OPENNESSProprietary
ADDEDAug 2026
LAST PRICED20 min ago
Input
$0.97 /M
Output
$4.05 /M
Blended (40/60)
$2.82 /M
Cost / IQ
$4.5147 /M
Cost / IQ = Blended Price ÷ (AA Intelligence Score ÷ 40). Normalises price by model intelligence so you can compare value across tiers. Lower = better value per unit of intelligence. Not a transactional price.
24h0%
7d0%
Price History
30-day view, daily close
Low: $2.82/M
High: $2.83/M
Average: $2.82/M
Pricing Variants
Cached Input
$0.17/M
83% cheaper than standard
Batch (async)
$2.83/M
-0.4% cheaper than standard
In: $1.00/M · Out: $4.05/M
Cost / IQ Comparison
Cost / IQ (quality-adjusted $/M)$4.5147/M
Cost per GPT-4-equivalent token. Lower = better value. Comparable across all models.
148.5% above SIT TPI
Value Ranking (by Cost / IQ)
Rank #158 of 189 budget models
← YOU ARE HERE | Thinking Machines: Inkling
Data Sources
Source
Aggregator & direct provider data
2 sources · updated recently
API Access
# Get this model's current price
curl https://api.inferenceindexer.ai/v1/models/thinkingmachines/inkling
# Response (truncated)
{ "model_id": "thinkingmachines/inkling", "name": "Thinking Machines: Inkling", "blended_price_per_m": 2.82, "sit_adjusted_price": 4.514748 }