Fastest AI APIs from Amsterdam
How long five AI APIs take to start answering from a server in Amsterdam, Netherlands, measured every day. Useful if your app runs there or serves users in Europe.
Mistral is the fastest AI API we measure from Amsterdam: 214 ms to the first word, on its default settings.
Of the APIs that use low reasoning effort, ChatGPT is fastest at 1,025 ms, ahead of Claude (1,105 ms) and Grok (3,026 ms).
From Amsterdam, Grok takes 552 ms longer to start answering than from San Francisco, its fastest city.
Which AI API answers fastest from Amsterdam?
Typical time until the first word of the reply arrives, measured from Amsterdam, 27 September to 10 October 2026.
MistralMistral AI · Provider default settings · Live status
214 ms typical
p95 TTFT: 490 ms
DeepSeekDeepSeek · Reasoning turned off · Live status
700 ms typical
p95 TTFT: 918 ms
ChatGPTOpenAI · Low reasoning effort · Live status
1,025 ms typical
p95 TTFT: 1,612 ms
ClaudeAnthropic · Low reasoning effort · Live status
1,105 ms typical
p95 TTFT: 1,702 ms
GrokxAI · Low reasoning effort
3,026 ms typical
p95 TTFT: 4,975 ms
Mistral runs on its default settings, DeepSeek runs with reasoning turned off, and ChatGPT, Claude and Grok use low reasoning effort. Typical is the middle request of the period; p95 means 95% of requests got their first word within that time.
Technical details
| API | Model | Requests in the period | Failed |
|---|---|---|---|
| Mistral | mistral-medium-latest | 65 | 0 of 65 |
| DeepSeek | deepseek-v4-flash | 65 | 0 of 65 |
| ChatGPT | gpt-5.6-sol | 65 | 0 of 65 |
| Claude | claude-opus-5 | 65 | 0 of 65 |
| Grok | grok-4.6 | 65 | 0 of 65 |
Compared to the fastest city
How much longer each API takes to start answering from Amsterdam than from its own fastest test city.
How steady each API was from Amsterdam
Each API's daily time from Amsterdam, 11 September to 10 October 2026: one point per day, the middle of that day's five requests. Each chart has its own scale.
MistralVaries
9 days in 10 no more than 19% above its usual 233 ms
No failed requests · one day without a run
DeepSeekSteady
9 days in 10 no more than 12% above its usual 734 ms
No failed requests · one day without a run
ChatGPTVaries a lot
9 days in 10 no more than 36% above its usual 1,063 ms
No failed requests · one day without a run
ClaudeVaries a lot
9 days in 10 no more than 37% above its usual 1,288 ms
No failed requests · one day without a run
GrokSteady
9 days in 10 no more than 12% above its usual 2,839 ms
No failed requests · one day without a run
What to do with this
- Base timeouts on the slower figure: from Amsterdam, 1 in 20 requests to Grok waited more than 4,975 ms for the first word.
- For predictable times, DeepSeek was the steadiest from Amsterdam: on 9 days in 10 it stayed within 12% of its usual time. Claude swung the most: on 1 day in 10 it was 37% or more above its usual time.
- If your backend doesn't have to run in Amsterdam: ChatGPT took 748 ms from Montreal, against 1,025 ms here. DeepSeek took 527 ms from Singapore, against 700 ms here. Your users' trip to that server comes on top, so moving only helps when the API call is the slow part.
Good to know
- This is one server in a datacenter in Amsterdam, measured once a day.
- Every API gets the same one-line prompt, but the reasoning settings differ (named on each row), so compare APIs with the same setting.
- Time to first token stops at the first visible word. It doesn't measure how fast the rest of the reply arrives or how good it is.
How fast is your API from Amsterdam?
Run a free test from Amsterdam and the other test cities, and see where the time goes.
Free, no account needed.