Virtual poolant:auto

ANT Auto

The default pool — every request classified, then routed to the model that fits it.

Try in Playground

How this pool routes

ant:auto applies no capability floor of its own. Each request is classified for task type, complexity and context size, and the router balances speed, quality and cost evenly from there. It is the right default when your traffic is mixed and you would rather not pick a model per call.

Best For

General chatMixed workloadsDrop-in default

Where requests went

Live routing over the last 30 days

Requests

236

Success rate

99.15%

Avg latency

2,102ms

command-a-03-2025Semantic-cache13.1% · 31
deepseek-ai/DeepSeek-V4.1-FlashSemantic-cache12.3% · 29
Qwen3 CoderNVIDIA NIM8.1% · 19
meta-llama/Llama-4-Scout-17B-16E-InstructSemantic-cache7.6% · 18
deepseek/deepseek-v4-flash-0731Semantic-cache7.2% · 17
qwen/qwen3-next-80b-a3b-thinkingSemantic-cache6.4% · 15
gemini-2.5-flashSemantic-cache5.9% · 14
deepseek-ai/DeepSeek-V3-0324Semantic-cache4.7% · 11
openai/o4-miniOpenRouter4.7% · 11
qwen/qwen3.7-flashSemantic-cache3.8% · 9

Models in this pool

23,799 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

Claude Sonnet 5

Anthropic1M👁🧠Q:96

o3

OpenAI200K👁🧠Q:96

GPT-5

OpenAI400K👁🧠Q:95

OpenAI: o4 Mini High

OpenRouter200K👁🧠Q:95

Anthropic: Claude Opus 4.5 (batch)

OpenRouter200K👁Q:95

Anthropic: Claude Opus 4.7 (batch)

OpenRouter1M👁Q:95

o1

OpenAI200K👁🧠Q:95

Anthropic: Claude Opus Latest

OpenRouter1M👁Q:95

Anthropic: Claude Opus 4.1 (batch)

OpenRouter200K👁Q:95

Anthropic: Claude Opus 4.5

OpenRouter200K👁Q:95

Anthropic: Claude Opus 4.1

OpenRouter200K👁Q:95

OpenAI: o3 Mini High

OpenRouter200K🧠Q:95

OpenAI: o4 Mini (batch)

OpenRouter200K👁🧠Q:95

Anthropic: Claude Opus 4.6

OpenRouter1M👁Q:95

Anthropic: Claude Opus 4.7

OpenRouter1M👁Q:95

Anthropic: Claude Opus 5

OpenRouter1M👁Q:95

Anthropic: Claude Opus 4.8

OpenRouter1M👁Q:95

Anthropic: Claude Opus 4.8 (batch)

OpenRouter1M👁Q:95

Anthropic: Claude Opus 5.5 (batch)

OpenRouter1M👁Q:95

Anthropic: Claude Opus 5.5

OpenRouter1M👁Q:95

Anthropic: Claude Opus 4.6 (batch)

OpenRouter1M👁Q:95

Showing the 24 highest-scoring of 23,799.

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

Routing weights

Speed50/100
Quality50/100
Cost50/100

Selection criteria

Speed weight50/100
Quality weight50/100
Cost weight50/100
Model IDant:auto

Other pools

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

Browse all virtual models →