Inkling (xhigh)
AI model by Thinking Machines. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. Inkling (xhigh) is positioned in the mid-tier at $4.05/M output tokens. The benchmark profile is balanced — strongest on Coding Index (52.1) — making it a default choice for teams that need general-purpose reasoning without paying frontier-model prices.
Latency. On latency, Inkling (xhigh) reports 73 tok/s output speed and 3000ms 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 (xhigh) costs $1.41 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 2026-09-06.
Compare with similar models
| Model | Input | Output | Speed |
|---|---|---|---|
Inkling (xhigh)Current | $1.00 | $4.05 | 73 tok/s |
| GLM-5.1 (Reasoning) | $1.28 | $4.07 | 51 tok/s |
| Kimi K2.6 | $0.95 | $4.00 | 40 tok/s |
| DeepSeek R1 (Jan '25) | $2.00 | $4.00 | — |
| Kimi K2.6 (Non-reasoning) | $0.95 | $4.00 | 42 tok/s |
| Kimi K2.7 Code | $0.95 | $4.00 | 39 tok/s |