Celeris | Creating the world's fastest LLMs

Celeris

2 min read Original article ↗

The fastest LLM on Earth.

Frontier level intelligence, 15x faster.

Benchmarks

A fraction of the latency.

Same tasks, same scoring. Celeris lands within a few points of the frontier on accuracy - and at more than 10x the speed.

Read the full breakdown

01 · Intelligence

response time (ms, log scale) → slower MMLU-Pro accuracy → 1003001,0003,000 806040200 Gemini 3.5 Flash Lite 83.0% · 1.2s GPT-5 81.9% · 2.0s GPT-5 mini 78.5% · 2.5s Gemini 2.5 Flash 73.0% · 2.6s Mercury 2 63.7% · 257 ms Celeris-1 158 ms · 75.9%

Figure 1. MMLU-Pro accuracy (5-shot, chain-of-thought) vs. response time (log scale). Up and to the left is better. The reasoning budget for Celeris, GPT-5, GPT-5 mini, and the Gemini models was set to 0, and Mercury 2 ran in instant mode - the fastest possible configuration for every model.

MMLU-Pro accuracy75.9

Response time · p50158 ms

Speedup vs GPT-513×

Output tok/s · p501,664

Speedup vs GPT-524×

Server time vs GPT 525×

02 · Speed

06001,2001,800 tok/s Celeris 1,664 Mercury 2 324 Gemini 3.5 Flash Lite 224 Gemini 3.5 Flash 134 GPT-5 mini 99 GPT-5 69

Figure 2. Output speed (p50 tokens per second) on ~1,000-token long-form prompts - 50 requests per model, outputs capped at 1,024 tokens. Full methodology →

Architecture

A new architecture for language model inference.

Current autoregressive models generate one token at a time. Every token depends on the one before it, making latency fundamentally sequential. Celeris is a new inference architecture for language models, built on diffusion, that achieves latency and quality previous diffusion systems could not.

The result is an OpenAI-compatible API that delivers intelligent responses in milliseconds.

For builders

Three lines to swap. Then everything is faster.

  • The API is OpenAI-compatible. Point your SDK at inference.celeris.ai and keep the code you already wrote.
  • Streaming is on by default. Responses as low as 24 ms, with no buffering or batch delay.
  • Pricing is per token. You are billed for the tokens you generate, so speed costs you nothing extra.

quickstart.pypython

from openai import OpenAI

client = OpenAI(
    base_url="https://inference.celeris.ai/celeris-1/v1",
    api_key="ck_…",
)

# same call shape you already wrote
stream = client.chat.completions.create(
    model="celeris-1",
    messages=[{"role": "user",
               "content": "Explain a Kalman filter"}],
    stream=True,
)

Start building with Celeris.

Experience the new paradigm of inference.