Virtual poolant:vision

ANT Vision

Image-capable models only.

Vision: Required

How this pool routes

ant:vision hard-requires vision support, so a request carrying an image can never be routed to a text-only model. Detection is instant — the heuristic pass spots image content before classification runs.

Best For

Image understandingScreenshot analysisVisual QA

Where requests went

Live routing over the last 30 days

Requests

204

Success rate

60.78%

Avg latency

8,294ms

ant:visionUnknown36.8% · 75

openai/o4-miniSemantic-cache23.5% · 48

qwen/qwen3.7-flashSemantic-cache14.7% · 30

qwen/qwen3.5-9bSemantic-cache12.7% · 26

openai/o3OpenRouter4.9% · 10

openai/gpt-4.1-nanoOpenRouter3.9% · 8

openai/gpt-5OpenRouter2.5% · 5

openai/o4-mini-highOpenRouter0.5% · 1

qwen/qwen3.5-flash-02-23OpenRouter0.5% · 1

Models in this pool

595 models across 21 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

OpenAI: o4 Mini High

Anthropic: Claude Opus 4.8 (batch)

OpenRouter1M👁Q:95

Anthropic: Claude Opus 5.5

OpenRouter1M👁Q:95

OpenAI200K👁🧠Q:95

Anthropic: Claude Opus Latest

OpenRouter1M👁Q:95

Anthropic: Claude Opus 4.1

OpenRouter200K👁Q:95

Anthropic: Claude Opus 5

OpenRouter1M👁Q:95

Anthropic: Claude Opus 4.8

OpenRouter1M👁Q:95

Anthropic: Claude Opus 5.5 (batch)

OpenRouter1M👁Q:95

Anthropic: Claude Opus 4.5

OpenRouter200K👁Q:95

GPT-5

OpenAI400K👁🧠Q:95

Anthropic: Claude Opus 4.6 (batch)

OpenRouter1M👁Q:95

Anthropic: Claude Opus 4.6

OpenRouter1M👁Q:95

Anthropic: Claude Opus 4.1 (batch)

OpenRouter200K👁Q:95

Anthropic: Claude Opus 4.7

OpenRouter1M👁Q:95

Anthropic: Claude Opus 5 (batch)

OpenRouter1M👁Q:95

OpenAI200K👁🧠Q:95

Anthropic: Claude Opus 4.5 (batch)

OpenRouter200K👁Q:95

Anthropic: Claude Opus 4.7 (batch)

OpenRouter1M👁Q:95

Showing the 24 highest-scoring of 595.

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

Routing weights

Speed50/100

Quality80/100

Cost50/100

Selection criteria

VisionrequiredRequired

Speed weight50/100

Quality weight80/100

Cost weight50/100

Model IDant:vision

Other pools

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

Browse all virtual models →