---
id: provider-latency/2026-09
series: provider-latency
title: Time to first token by provider, September 2026
period: 2026-09
period_start: 2026-09-01
period_end: 2026-09-30
updated: 2026-11-11
license: CC BY 4.0
canonical: https://www.requesty.ai/data/provider-latency/2026-09
latest: https://www.requesty.ai/data/provider-latency
---

# Time to first token by provider, September 2026

> Sference had the fastest median time to first token among major providers in September 2026 at 267 ms. The median major provider took 1.37 s.

Question: Which LLM provider returns the first token fastest?

## Key findings

1. Fastest median TTFT: Sference at 267 ms, then Azure at 796 ms.
2. Highest median output speed: Vertex (Gemini) at 169 tokens per second.
3. Fastest median full streamed response: Sference at 2.12 s.
4. Novita moved the most since August 2026: median TTFT went from 1.40 s to 2.79 s (+1.39 s).

## Data

| Provider | Median TTFT | p90 TTFT | Median total | Median tokens/s | Streamed share | Organizations (band) |
| --- | --- | --- | --- | --- | --- | --- |
| Sference | 267 ms | 1.93 s | 2.12 s | 149.600 | 60.76% | 500+ |
| Azure | 796 ms | 4.45 s | 2.68 s | 58.100 | 36.38% | 500+ |
| Nebius | 983 ms | 3.40 s | 2.98 s | 82.200 | 6.54% | 500+ |
| TensorX | 1.02 s | 5.81 s | 3.32 s | 66.200 | 20.54% | 500+ |
| DeepSeek | 1.04 s | 2.19 s | 4.41 s | 96.800 | 24.05% | 500+ |
| DeepInfra | 1.14 s | 3.54 s | 3.29 s | 73.100 | 13.31% | 500+ |
| OpenAI | 1.16 s | 6.74 s | 6.11 s | 71.700 | 18.43% | 500+ |
| Vertex (Claude) | 1.24 s | 2.98 s | 5.54 s | 78.200 | 57.72% | 500+ |
| Fireworks | 1.37 s | 3.88 s | 4.83 s | 65.800 | 29.28% | 500+ |
| Mistral | 1.46 s | 9.60 s | 2.67 s | 137.400 | 15.68% | 500+ |
| Anthropic | 1.52 s | 3.38 s | 6.22 s | 73.800 | 18.20% | 500+ |
| xAI | 1.53 s | 4.32 s | 5.10 s | 40.900 | 16.09% | 100-499 |
| Bedrock | 1.70 s | 3.42 s | 6.00 s | 82.600 | 30.28% | 500+ |
| Runware | 2.00 s | 4.72 s | 4.11 s | 129.400 | 44.88% | 500+ |
| Vertex (Gemini) | 2.06 s | 8.24 s | 3.16 s | 169.000 | 5.40% | 500+ |
| NVIDIA | 2.22 s | 19.2 s | 10.3 s | 58.900 | 62.02% | 500+ |
| Novita | 2.79 s | 7.52 s | 6.89 s | 83.400 | 22.63% | 500+ |

## Method

- Time to first token and tokens per second are measured on streamed, successful requests only, with the same formulas /rankings uses. Tokens per second counts visible output tokens after the first token, with a 250 ms floor on decode time and at least 20 output tokens.
- A provider needs at least 500 streamed successes in the month for latency to be published. Only providers with at least 0.5% of published traffic are shown.
- A row is published only when it has at least 20 requests, at least 5 distinct organizations, and no single organization above 80% of its traffic. These are the same floors /rankings uses. Rows below the floors are withheld, not estimated.
- Only shares, rates, medians and organization bands are published. Absolute request, token and spend totals stay private.

## Caveats

- Latency depends on the model mix. A provider serving mostly small models will look faster than one serving large reasoning models.
- Reasoning models think before the first visible token, which raises TTFT.

## Cite as

Requesty (2026). Time to first token by provider, September 2026. Requesty Data. https://www.requesty.ai/data/provider-latency/2026-09

```bibtex
@misc{requesty_provider_latency_2026_09,
  author       = {{Requesty}},
  title        = {Time to first token by provider, September 2026},
  year         = {2026},
  howpublished = {\url{https://www.requesty.ai/data/provider-latency/2026-09}},
  note         = {Requesty Data}
}
```

Source: Requesty production gateway. License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/).
Downloads: [JSON](https://www.requesty.ai/data/provider-latency/2026-09/data.json) · [CSV](https://www.requesty.ai/data/provider-latency/2026-09/data.csv) · [Markdown](https://www.requesty.ai/data/provider-latency/2026-09/data.md)