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 757 ms — cerebras running gpt-oss-120b, requested from South America (São Paulo). 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 2.0× for cerebras.
Measured time to first token, by region
| Requested from | Provider | Model answering | TTFT p50 | TTFT p95 | Samples |
|---|---|---|---|---|---|
| South America (São Paulo) | cerebras | gpt-oss-120b | 757 ms | 1215 ms | 57 |
| South America (São Paulo) | groq | llama-3.3-70b-versatile | 764 ms | 1126 ms | 57 |
| Europe (Germany) | cerebras | gpt-oss-120b | 801 ms | 1398 ms | 58 |
| Europe (Germany) | groq | llama-3.3-70b-versatile | 899 ms | 1370 ms | 58 |
| South America (São Paulo) | openrouter | nvidia/nemotron-3-nano-30b-a3b:free | 1037 ms | 1343 ms | 57 |
| South America (São Paulo) | gemini-flash-lite-latest | 1143 ms | 1724 ms | 57 | |
| Asia (Tokyo) | groq | llama-3.3-70b-versatile | 1280 ms | 1624 ms | 57 |
| Europe (Germany) | openrouter | nvidia/nemotron-3-nano-30b-a3b:free | 1282 ms | 2009 ms | 58 |
| Asia (Tokyo) | openrouter | nvidia/nemotron-3-nano-30b-a3b:free | 1292 ms | 1761 ms | 57 |
| Asia (Tokyo) | cerebras | gpt-oss-120b | 1337 ms | 1669 ms | 57 |
| Europe (Germany) | gemini-flash-lite-latest | 1351 ms | 2384 ms | 58 | |
| US (Central) | groq | llama-3.3-70b-versatile | 1355 ms | 1984 ms | 57 |
| US (Central) | cerebras | gpt-oss-120b | 1485 ms | 1841 ms | 57 |
| Asia (Tokyo) | gemini-flash-lite-latest | 1488 ms | 1827 ms | 57 | |
| US (Central) | gemini-flash-lite-latest | 1498 ms | 2140 ms | 57 | |
| US (Central) | openrouter | nvidia/nemotron-3-nano-30b-a3b:free | 1570 ms | 1981 ms | 57 |
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: DNS resolution, TCP connect, TLS handshake and the first byte back. It does not involve the model. Time to first token (TTFT) is how long a real streamed completion takes to emit its first token: that same network time, plus queueing at the provider, plus the model’s prefill over your prompt.
TTFB is the floor — you pay it on every request no matter which model you call, and no prompt engineering removes it. TTFT is what a human actually waits for before words appear on screen. They are different questions and they have different answers, which is why this site measures both and never averages them together.
How much of time to first token is network latency?
Between 3% and 33% 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 from | Provider | TTFT p50 | TTFB p50 | Network share of TTFT |
|---|---|---|---|---|
| South America (São Paulo) | cerebras | 757 ms | 183 ms | 24% |
| South America (São Paulo) | groq | 764 ms | 235 ms | 31% |
| Europe (Germany) | cerebras | 801 ms | 201 ms | 25% |
| Europe (Germany) | groq | 899 ms | 296 ms | 33% |
| South America (São Paulo) | openrouter | 1037 ms | 58 ms | 6% |
| South America (São Paulo) | 1143 ms | 160 ms | 14% | |
| Asia (Tokyo) | groq | 1280 ms | 146 ms | 11% |
| Europe (Germany) | openrouter | 1282 ms | 100 ms | 8% |
| Asia (Tokyo) | openrouter | 1292 ms | 56 ms | 4% |
| Asia (Tokyo) | cerebras | 1337 ms | 196 ms | 15% |
| Europe (Germany) | 1351 ms | 101 ms | 7% | |
| US (Central) | groq | 1355 ms | 107 ms | 8% |
| US (Central) | cerebras | 1485 ms | 68 ms | 5% |
| Asia (Tokyo) | 1488 ms | 56 ms | 4% | |
| US (Central) | 1498 ms | 43 ms | 3% | |
| US (Central) | openrouter | 1570 ms | 56 ms | 4% |
Can providers be ranked by time to first token?
Not across different models, and that is the honest answer rather than a hedge. Each provider here is measured on whichever model that account can call — the models are named in the table above — and model size drives first-token time far more than the network or the provider’s hardware does. A ranking built from those numbers would be a ranking of models wearing provider names.
Measured from South America (São Paulo), openrouter has the lowest edge latency (58 ms TTFB) while cerebras has the lowest time to first token (757 ms TTFT, on gpt-oss-120b). Same region, same probes, same schedule — two different winners. “Fastest AI API” is not a question that has one answer until you say which of the two you are paying for.
Which providers have measured TTFT here, and why not all of them?
Inference is measured for 4 of 45 providers (cerebras, google, groq, openrouter), 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 4 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.