Virtual poolant:fast

ANT Fast

Latency first — the quickest model that can still do the job.

Try in Playground

How this pool routes

ant:fast weights speed at the maximum and accepts lower quality scores in exchange. Use it for interactive paths where a fast adequate answer beats a slow excellent one.

Best For

AutocompleteInteractive UIHigh-volume classification

Where requests went

Live routing over the last 30 days

Requests

324

Success rate

4.63%

Avg latency

139ms

ant:fastUnknown95.4% · 309
deepseek/deepseek-v4-flash-0731Semantic-cache2.5% · 8
~deepseek/deepseek-v4-flash-latestOpenRouter1.2% · 4
qwen/qwen3-next-80b-a3b-thinkingOpenRouter0.6% · 2
apodex/apodex-1.1-mini:freeOpenRouter0.3% · 1

Models in this pool

23,798 models across 34 providers currently qualify. Per-request limits (context size, cost caps, your model allowlist) narrow this further at routing time.

o1-pro

OpenAI200K👁🧠Q:97

o1-pro

OpenAI200K👁🧠Q:97

o3

OpenAI200K👁🧠Q:96

o3

OpenAI200K👁🧠Q:96

Claude Sonnet 5

Anthropic1M👁🧠Q:96

OpenAI: o4 Mini High

OpenRouter200K👁🧠Q:95

Anthropic: Claude Opus Latest

OpenRouter1M👁Q:95

Anthropic: Claude Opus 4.7

OpenRouter1M👁Q:95

GPT-5

OpenAI400K👁🧠Q:95

Anthropic: Claude Opus 4.1 (batch)

OpenRouter200K👁Q:95

Anthropic: Claude Opus 5.5

OpenRouter1M👁Q:95

Anthropic: Claude Opus 4.1

OpenRouter200K👁Q:95

Anthropic: Claude Opus 4.5

OpenRouter200K👁Q:95

Anthropic: Claude Opus 4.6

OpenRouter1M👁Q:95

OpenAI: o4 Mini (batch)

OpenRouter200K👁🧠Q:95

OpenAI: o3 Mini High

OpenRouter200K🧠Q:95

Anthropic: Claude Opus 4.8

OpenRouter1M👁Q:95

o1

OpenAI200K👁🧠Q:95

Anthropic: Claude Opus 4.7 (batch)

OpenRouter1M👁Q:95

Anthropic: Claude Opus 5.5 (batch)

OpenRouter1M👁Q:95

Anthropic: Claude Opus 5

OpenRouter1M👁Q:95

Anthropic: Claude Opus 4.8 (batch)

OpenRouter1M👁Q:95

Anthropic: Claude Opus 4.5 (batch)

OpenRouter200K👁Q:95

Anthropic: Claude Opus 4.6 (batch)

OpenRouter1M👁Q:95

Showing the 24 highest-scoring of 23,798.

Quick Start

from openai import OpenAI

client = OpenAI(
    base_url="https://api.antbase.ai/v1",
    api_key="YOUR_ANT_API_KEY",
)

response = client.chat.completions.create(
    model="ant:fast",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

Routing weights

Speed100/100
Quality30/100
Cost70/100

Selection criteria

Speed weight100/100
Quality weight30/100
Cost weight70/100
Model IDant:fast

Other pools

Every virtual pool accepts the same request shape — swap the model id to change the routing policy.

Browse all virtual models →