Virtual poolant:coder

ANT Coder

Code-oriented routing with a quality floor of 75.

Quality floor: 75/100 or above

How this pool routes

ant:coder weights quality heavily while keeping cost low, and excludes models below 75. It is the pool behind the default model in the Hermes and OpenClaw agent integrations.

Best For

Code generationRefactoringAgentic coding

Where requests went

Live routing over the last 30 days

Requests

148

Success rate

51.35%

Avg latency

665ms

ant:coderUnknown48.6% · 72

deepseek/deepseek-v4-flash-0731Semantic-cache16.9% · 25

qwen/qwen3.7-flashSemantic-cache16.2% · 24

qwen/qwen3-next-80b-a3b-thinkingSemantic-cache5.4% · 8

openai/o3-miniOpenRouter5.4% · 8

~deepseek/deepseek-v4-flash-latestOpenRouter2.7% · 4

openai/o4-miniOpenRouter2.7% · 4

openai/o3OpenRouter2% · 3

Models in this pool

202 models across 12 providers currently qualify. Per-request limits (context size, cost caps, your model allowlist) narrow this further at routing time.

o1-pro

o1-pro

Claude Sonnet 5

Anthropic: Claude Opus 5.5 (batch)

OpenRouter1M👁Q:95

Anthropic: Claude Opus 4.6

OpenRouter1M👁Q:95

Anthropic: Claude Opus 4.7

OpenRouter1M👁Q:95

Anthropic: Claude Opus 4.6 (batch)

OpenRouter1M👁Q:95

Anthropic: Claude Opus 5

OpenRouter1M👁Q:95

OpenAI: o3 Mini High

OpenRouter200K🧠Q:95

OpenAI200K👁🧠Q:95

Anthropic: Claude Opus 4.1

OpenRouter200K👁Q:95

Anthropic: Claude Opus 4.1 (batch)

OpenRouter200K👁Q:95

Anthropic: Claude Opus 4.8 (batch)

OpenRouter1M👁Q:95

OpenAI200K👁🧠Q:95

GPT-5

OpenAI400K👁🧠Q:95

Anthropic: Claude Opus Latest

OpenRouter1M👁Q:95

Anthropic: Claude Opus 5 (batch)

OpenRouter1M👁Q:95

OpenAI: o4 Mini High

OpenRouter200K👁🧠Q:95

Anthropic: Claude Opus 4.8

OpenRouter1M👁Q:95

Anthropic: Claude Opus 4.5

OpenRouter200K👁Q:95

Anthropic: Claude Opus 5.5

OpenRouter1M👁Q:95

Anthropic: Claude Opus 4.5 (batch)

OpenRouter200K👁Q:95

Showing the 24 highest-scoring of 202.

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

Routing weights

Speed40/100

Quality95/100

Cost30/100

Selection criteria

Quality floorrequired75/100 or above

Speed weight40/100

Quality weight95/100

Cost weight30/100

Model IDant:coder

Other pools

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

Browse all virtual models →