Inkling Small
AI model by Thinking Machines. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. Inkling Small is a budget-tier option from Thinking Machines at $1.20/M output tokens. Despite the low price, it scores competitively on GPQA Diamond (89.5%) and Coding Index (52.9) — making it a candidate for high-volume production workloads where unit cost dominates.
Latency. On latency, Inkling Small reports 97 tok/s output speed and 1688ms time-to-first-token. Output speed is on the slower end; for real-time chat consider pairing with a streaming front-end or routing latency-sensitive requests to a faster model.
Cost model. For a workload of 1M input tokens + 100K output tokens, Inkling Small costs $0.42 per million input-equivalent requests. Multiply by your monthly request volume to project the bill, and compare against the speed/correctness profile above to decide if the trade-off is worth it for your workload.
Editorial summary generated from public pricing and benchmark data (Artificial Analysis API). All numbers are sourced — see the Artificial Analysis methodology for benchmark definitions. Last refreshed 2026-07-30.
Compare with similar models
| Model | Input | Output | Speed |
|---|---|---|---|
Inkling SmallCurrent | $0.30 | $1.20 | 97 tok/s |
| GPT-5.6 Luna (Non-reasoning) | $0.20 | $1.20 | 168 tok/s |
| GPT-5.6 Luna (high) | $0.20 | $1.20 | 175 tok/s |
| GPT-5.6 Luna (xhigh) | $0.20 | $1.20 | 174 tok/s |
| GPT-5.6 Luna (max) | $0.20 | $1.20 | 187 tok/s |
| GPT-5.6 Luna (low) | $0.20 | $1.20 | 171 tok/s |