HomeTime to first token
Data API

Which LLM API has the lowest time to first token?

Measured over the last 24 hours, the lowest median time to first token (TTFT) is 194 ms — typesafe running jev-1.13.0, requested from Europe (Germany). Read that as one measurement, not as a provider ranking: every provider here answers on a different model, and model size moves TTFT far more than the provider does. What is comparable like-for-like is the same provider on the same model from different regions — and that alone varies 4.7× for typesafe.

Measured time to first token, by region

Requested fromProviderModel answeringTTFT p50TTFT p95Samples
Europe (Germany)typesafejev-1.13.0194 ms229 ms72
Europe (Germany)groqopenai/gpt-oss-120b290 ms509 ms72
South America (Santiago)typesafejev-1.13.0294 ms399 ms72
US (Central)typesafejev-1.13.0597 ms812 ms71
South America (Santiago)groqopenai/gpt-oss-120b803 ms1032 ms72
Asia (Tokyo)typesafejev-1.13.0909 ms1116 ms71
Europe (Germany)googlegemini-flash-lite-latest912 ms8150 ms72
US (Central)groqopenai/gpt-oss-120b1307 ms1780 ms71
Asia (Tokyo)groqopenai/gpt-oss-120b1433 ms1860 ms71
US (Central)googlegemini-flash-lite-latest1943 ms8809 ms71
Asia (Tokyo)googlegemini-flash-lite-latest2000 ms7613 ms71
South America (Santiago)googlegemini-flash-lite-latest2006 ms7141 ms72

Real streamed completions, last 24 hours, requested from each probe region. The model is named on every row because it is the dominant factor in the number next to it.

What is the difference between time to first token and time to first byte?

Time to first byte (TTFB) is how long it takes the network and the provider’s edge to begin responding at all: the time from sending a request over an open TLS connection to the first byte back. DNS, TCP and TLS setup are timed separately. It does not involve the model. Time to first token (TTFT) is how long a real streamed completion takes to emit its first token, measured from opening a fresh connection: connection setup, the network round trip, queueing at the provider and the model’s prefill over your prompt.

TTFB measures endpoint response time. TTFT measures the wait until the first generated token. The two metrics are reported separately.

How much of time to first token is network latency?

Between 2% and 81% of time to first token is network time — the rest is the provider queuing your request and the model generating its first token. That is why a TTFT number quoted without the model name tells you almost nothing about the API: most of what it measures is the model.

Requested fromProviderTTFT p50TTFB p50Network share of TTFT
Europe (Germany)typesafe194 ms157 ms81%
Europe (Germany)groq290 ms218 ms75%
South America (Santiago)typesafe294 ms174 ms59%
US (Central)typesafe597 ms79 ms13%
South America (Santiago)groq803 ms191 ms24%
Asia (Tokyo)typesafe909 ms144 ms16%
Europe (Germany)google912 ms93 ms10%
US (Central)groq1307 ms131 ms10%
Asia (Tokyo)groq1433 ms155 ms11%
US (Central)google1943 ms43 ms2%
Asia (Tokyo)google2000 ms66 ms3%
South America (Santiago)google2006 ms957 ms48%

Can providers be ranked by time to first token?

These measurements use different models, named in the table above. Model size and inference behaviour affect TTFT, so these figures do not isolate provider performance. Use them to track each provider and model combination over time.

Measured from Europe (Germany), google has the lowest edge latency (93 ms TTFB) while typesafe has the lowest time to first token (194 ms TTFT, on jev-1.13.0). Both were measured from the same region on the same schedule, but the two metrics have different leaders.

Which providers have measured TTFT here, and why not all of them?

Inference is measured for 3 of 45 providers (google, groq, typesafe), because a streamed completion needs a paid API key for that provider and every probe spends tokens. Edge latency needs no key, so TTFB is published for all 45. We would rather publish 3 measured TTFT figures than estimate 45: an estimate presented as a measurement is the one thing this site does not do.

Method in full, including limits: methodology · Edge latency for every provider: fastest AI API by region · Availability: uptime comparison · Raw numbers under CC BY 4.0: JSON API.