# Thinking Machines: Inkling 2 Small — price and measured latency by host

Updated November 17, 2026. Served by 6 providers; 3 of them measured here.

Latency and uptime are measured by llmlatency.dev probes. Prices are published by the providers and read via OpenRouter on 2026-11-17 — not measured.

| Host | Input $/M | Output $/M | Context | Fastest p50 | From | Uptime |
| --- | --- | --- | --- | --- | --- | --- |
| deepinfra | $0.285 | $0.950 | 1,048,576 | 163 ms | us-central | 100% |
| nebius | $0.300 | $1.000 | 1,048,576 | 34 ms | eu-hetzner | 100% |
| together | $0.300 | $1.000 | 1,048,576 | 122 ms | us-central | 100% |

Source: https://llmlatency.dev/model/thinkingmachines-inkling-2-small · CC BY 4.0
