Models /GPT-4.1 Nano /Where to run

Provider guide

Where to run GPT-4.1 Nano

4 live listings tracked.

CHEAPEST

$0.10 / $0.40

per 1M tokens in / out

FASTEST MEASURED

41 tok/s

measured throughput · $0.10 input / $0.40 output per million tokens

ProviderIn / 1MOut / 1MThroughputContextQuantSynced

OpenRouter$0.10 in/1M$0.40 out/1M—1M—5 hours ago Microsoft Azure AIzero-retention$0.10 in/1M$0.40 out/1M32 tok/s1M—5 hours ago OpenAICHEAPEST$0.10 in/1M$0.40 out/1M41 tok/s1M—5 hours ago Microsoft Azure AIzero-retention$0.11 in/1M$0.44 out/1M38 tok/s1M—5 hours ago

Full specs, hardware verdicts and benchmarks on the GPT-4.1 Nano model page →