Virtual poolant:creative

ANT Creative

Tuned for open-ended and generative writing.

Try in Playground

How this pool routes

ant:creative weights quality high without imposing a hard floor, leaving room for models that write well but score modestly on technical benchmarks.

Best For

CopywritingStory and script draftsBrainstorming

Where requests went

Live routing over the last 30 days

Requests

11

Success rate

100%

Avg latency

5,677ms

deepseek/deepseek-v3.1-terminusOpenRouter81.8% · 9
deepseek-v4-flashSemantic-cache9.1% · 1
deepseek/deepseek-v4-flashDeepSeek9.1% · 1

Models in this pool

23,777 models across 35 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

Claude Sonnet 5

Anthropic1M👁🧠Q:96

o3

OpenAI200K👁🧠Q:96

o3

OpenAI200K👁🧠Q:96

Anthropic: Claude Opus 4.1

OpenRouter200K👁Q:95

Anthropic: Claude Opus 4.5

OpenRouter200K👁Q:95

Anthropic: Claude Opus 4.7

OpenRouter1M👁Q:95

Anthropic: Claude Opus 5 (batch)

OpenRouter1M👁Q:95

Anthropic: Claude Opus Latest

OpenRouter1M👁Q:95

Anthropic: Claude Opus 4.5 (batch)

OpenRouter200K👁Q:95

Anthropic: Claude Opus 4.6 (batch)

OpenRouter1M👁Q:95

GPT-5

OpenAI400K👁🧠Q:95

Anthropic: Claude Opus 4.1 (batch)

OpenRouter200K👁Q:95

OpenAI: o4 Mini High

OpenRouter200K👁🧠Q:95

o1

OpenAI200K👁🧠Q:95

Anthropic: Claude Opus 5.5

OpenRouter1M👁Q:95

Anthropic: Claude Opus 5.5 (batch)

OpenRouter1M👁Q:95

Anthropic: Claude Opus 4.8

OpenRouter1M👁Q:95

OpenAI: o4 Mini (batch)

OpenRouter200K👁🧠Q:95

Anthropic: Claude Opus 4.7 (batch)

OpenRouter1M👁Q:95

Anthropic: Claude Opus 5

OpenRouter1M👁Q:95

Anthropic: Claude Opus 4.8 (batch)

OpenRouter1M👁Q:95

OpenAI: o3 Mini High

OpenRouter200K🧠Q:95

Showing the 24 highest-scoring of 23,777.

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:creative",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

Routing weights

Speed40/100
Quality85/100
Cost40/100

Selection criteria

Speed weight40/100
Quality weight85/100
Cost weight40/100
Model IDant:creative

Other pools

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

Browse all virtual models →