Virtual poolant:free

ANT Free

Zero-cost routing across every free model in the pool.

Try in Playground

How this pool routes

ant:free routes only to models that cost nothing, drawing on the free-model pool and its own fallback chain across providers. Throughput is bounded by upstream free-tier rate limits rather than your balance.

Best For

PrototypingSide projectsCost-free experimentation

Where requests went

Live routing over the last 30 days

Requests

47,763

Success rate

99.98%

Avg latency

504ms

accounts/fireworks/models/gpt-oss-120bSemantic-cache28.6% · 13,682
gemini-2.5-flashSemantic-cache15.1% · 7,204
openai/gpt-oss-120bSemantic-cache13.4% · 6,424
meta-llama/Llama-4-Scout-17B-16E-InstructSemantic-cache13.2% · 6,287
openai/gpt-oss-20bSemantic-cache12.8% · 6,092
command-a-03-2025Semantic-cache6% · 2,889
GPT-OSS 20BHugging Face5.4% · 2,586
deepseek-ai/DeepSeek-V4.1-FlashSemantic-cache2.7% · 1,305
Llama 4 ScoutHugging Face1.2% · 586
Gemini 2.5 FlashHugging Face0.5% · 253

Models in this pool

28 models across 10 providers currently qualify. Per-request limits (context size, cost caps, your model allowlist) narrow this further at routing time.

Nemotron 3 Ultra 550B

OpenRouter1M🧠Q:90

GPT-OSS 120B

Groq131KQ:88

DeepSeek R1

Hugging Face164K🧠Q:88

Command A (2025)

Cohere256K🧠Q:88

Gemini 3.6 Flash

Google Gemini1M👁Q:86

Nemotron 3.5 Super VL

NVIDIA NIM1M👁🧠Q:85

Gemini 2.5 Flash

Google Gemini1M👁🧠Q:85

DeepSeek V3.1

Hugging Face128KQ:84

Qwen3.8 27B

Groq262K🧠Q:84

Command R+

Cohere128KQ:82

North Mini Code

OpenRouter256KQ:80

Flint v1.0

OpenRouter262K🧠Q:78

Llama 3.3 70B

Hugging Face128KQ:78

Llama 4 Scout

Hugging Face131K👁Q:78

Nemotron 3.5 Lightning

NVIDIA NIM1M🧠Q:76

GLM 4.7 Flash

Zai33K🧠Q:76

Dots 3 Note Preview

OpenRouter512KQ:76

GLM 4.6V Flash

Zai33K👁🧠Q:74

Nemotron 3 Nano Omni Reasoning

OpenRouter256K🧠Q:74

Gemma 4 31B

OpenRouter262KQ:72

GPT-OSS 20B

Groq131KQ:72

Command R

Cohere128KQ:72

Mistral Small 3.1

Mistral128K👁Q:70

Xing4.0 29B A4B

OpenRouter262K🧠Q:70

Showing the 24 highest-scoring of 28.

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

Routing weights

Speed50/100
Quality30/100
Cost100/100

Selection criteria

Speed weight50/100
Quality weight30/100
Cost weight100/100
Model IDant:free

Other pools

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

Browse all virtual models →