Provider latency

Median provider latency across OpenRouter endpoints, in seconds (3d).

183 models · 183 results · data as of 2026-11-06 · openrouter.ai ↗

All results

183 rows

#	Model	Effort	Provider latency
1	Llama 3.2 3b	none	0.2s
2	Llama 3.2 1b	none	0.3s
3	Qwen 2.5 7B		0.3s
4	Codestral 2508		0.3s
5	Llama 3.1 8b	medium	0.3s
6	Inkling	max	0.3s
7	Llama 4 Maverick	medium	0.4s
8	Mistral Small 3	none	0.4s
9	Gemma 2 27B		0.4s
10	Llama 3.1 70b	none	0.4s
11	Mistral	none	0.4s
12	gpt-oss-120b	high	0.5s
13	Mistral Small 3.1	none	0.5s
14	Mistral Medium 3	none	0.5s
15	Qwen 3 235B-A22B	xhigh	0.5s
16	Qwen 3.5 Flash	max	0.5s
17	Mistral Small 4	high	0.5s
18	Inkling Small	max	0.5s
19	gpt-oss-20b	high	0.5s
20	Gemini 2.5 Flash Lite	none	0.5s
21	Qwen 3 30B-A3B	none	0.5s
22	Haiku 4.5	xhigh	0.5s
23	Qwen 3.5 9B	low	0.6s
24	Gemma 4 26B	xhigh	0.6s
25	Qwen 2.5 72B	none	0.6s
26	Mistral Small 3.2	none	0.6s
27	Mistral Medium 3.5	high	0.6s
28	Qwen 3.6 Flash	max	0.6s
29	GPT-3.5	high	0.6s
30	Grok 4.20	xhigh	0.6s