#25
Inkling
Thinking Machines Lab · Open Weight · Hybrid · 1M context
60/ 100 composite
Released 2026-07-15
Benchmark Scores by Category
Coding
48.9
Knowledge
69.1
Agentic
57.4
Math
79.1
Multimodal
52.6
Scores based on weighted benchmarks: SWE-bench, LiveCodeBench (Coding); HLE, MMLU-Pro (Knowledge); ARC-AGI-2, LongBench v2 (Reasoning); Terminal-Bench, BrowseComp (Agentic); FrontierMath, AIME (Math).
API Pricing
Input
$1.87
per 1M tokens
Output
$4.68
per 1M tokens
Value Score
14.2
score per $1 output
Estimate Your Costs
Use our cost calculators to estimate monthly spend based on your specific workload: