Huggingface

AI inference provider available on Antbase

OpenAI-compatible

About Huggingface

Huggingface is an AI model provider accessible through Antbase. Use intelligent routing to automatically select the best model from this provider based on your task requirements.

Live Performance Data

Intelligence Score
47.0
Total Requests
499
Success Rate
9840.0%
Avg Latency
875ms
Models
136
Tokens Processed
5.4M

Huggingface Models on Antbase

ModelScoreRequestsSuccess RateAvg Latencyp95 LatencyCapabilities
Llama 4 Maverick 17B 128E Instruct78.000.0%400ms1000ms
🔧
Qwen2.5 72B Instruct76.000.0%400ms1000ms
🔧
DeepSeek R1 Distill Llama 70B74.000.0%400ms1000ms
🧠
Qwen2.5 VL 72B Instruct74.000.0%400ms1000ms
👁
Llama 4 Scout 17B 16E Instruct72.000.0%400ms1000ms
🔧
QwQ 32B72.000.0%400ms1000ms
🧠
Qwen2.5 Coder 32B Instruct70.000.0%400ms1000ms
🔧
Llama 4 Scout63.019210000.0%4904ms10434ms
DeepSeek V3.162.025410000.0%5671ms17904ms
Mistral Small 3.162.0110000.0%1657ms1657ms
GPT-4o Mini (AskCodi)62.0410000.0%1883ms2583ms
Kimi K359.0110000.0%2924ms2924ms
GPT-OSS 20B59.0110000.0%3086ms3086ms
OpenAI GPT-4.158.0110000.0%3406ms3406ms
Gemini 2.5 Flash57.02710000.0%2755ms8254ms
Command A (2025)51.0310000.0%5818ms13831ms
Qwen3 Coder Next46.0710000.0%9462ms12749ms
🔧
Tiny Aya Global45.000.0%400ms1000ms
Kimi K2 Instruct 090545.000.0%400ms1000ms
GLM 4.7 Flash45.000.0%400ms1000ms
MiniMax M2.145.000.0%400ms1000ms
Qwen3 Coder 30B A3B Instruct45.000.0%400ms1000ms
🔧
GLM 4.5 Air45.000.0%400ms1000ms
Qwen2.5 7B Instruct45.000.0%400ms1000ms
🔧
Qwen3 4B Thinking 250745.000.0%400ms1000ms
🧠🔧
Kimi K2 Thinking45.000.0%400ms1000ms
🧠
GLM 4.745.000.0%400ms1000ms
Olmo 3 7B Instruct45.000.0%400ms1000ms
Qwen2.5 VL 7B Instruct45.000.0%400ms1000ms
👁🔧
Qwen3 Next 80B A3B Instruct45.000.0%400ms1000ms
🔧
Rnj 1 Instruct45.000.0%400ms1000ms
Qwen2.5 Coder 7B Instruct45.000.0%400ms1000ms
🔧
Qwen3 VL 30B A3B Instruct45.000.0%400ms1000ms
🔧
DeepSeek V345.000.0%400ms1000ms
🔧
Qwen3 Coder Next FP845.000.0%400ms1000ms
🔧
DeepSeek R1 052845.000.0%400ms1000ms
🧠
Gemma 3n E4B It45.000.0%400ms1000ms
🔧
Qwen3 4B Instruct 250745.000.0%400ms1000ms
🔧
C4ai Command A 03 202545.000.0%400ms1000ms
Hermes 2 Pro Llama 3 8B45.000.0%400ms1000ms
🔧
Tiny Aya Fire45.000.0%400ms1000ms
DeepSeek R1 Distill Qwen 32B45.000.0%400ms1000ms
🧠🔧
DeepSeek R1 Distill Qwen 7B45.000.0%400ms1000ms
🧠🔧
DeepSeek V3.2 Exp45.000.0%400ms1000ms
🔧
Molmo2 8B45.000.0%400ms1000ms
GLM 4.6V Flash45.000.0%400ms1000ms
Qwen3 235B A22B45.000.0%400ms1000ms
🔧
Qwen3 14B45.000.0%400ms1000ms
🔧
Olmo 3.1 32B Instruct45.000.0%400ms1000ms
DeepSeek V3.1 Terminus45.000.0%400ms1000ms
🔧
Trinity Mini45.000.0%400ms1000ms
Qwen3 30B A3B45.000.0%400ms1000ms
🔧
L3 8B Stheno V3.245.000.0%400ms1000ms
Command A Reasoning 08 202545.000.0%400ms1000ms
GLM 4.5V45.000.0%400ms1000ms
MiniMax M245.000.0%400ms1000ms
Meta Llama 3 70B Instruct45.000.0%400ms1000ms
🔧
C4ai Command R7b 12 202445.000.0%400ms1000ms
🔧
DeepSeek Prover V2 671B45.000.0%400ms1000ms
Qwen3 VL 235B A22B Thinking45.000.0%400ms1000ms
🧠🔧
GLM 4 32B 041445.000.0%400ms1000ms
C4ai Command R 08 202445.000.0%400ms1000ms
🔧
Apriel 1.6 15b Thinker45.000.0%400ms1000ms
Gpt Oss Safeguard 20b45.000.0%400ms1000ms
Aya Vision 32b45.000.0%400ms1000ms
👁
GLM 4.645.000.0%400ms1000ms
Qwen3 Coder 480B A35B Instruct FP845.000.0%400ms1000ms
🔧
Olmo 3.1 32B Think45.000.0%400ms1000ms
Command A Translate 08 202545.000.0%400ms1000ms
GLM 4.5V FP845.000.0%400ms1000ms
Qwen3 235B A22B Thinking 250745.000.0%400ms1000ms
🧠🔧
Llama Guard 4 12B45.000.0%400ms1000ms
Apertus 8B Instruct 250945.000.0%400ms1000ms
ERNIE 4.5 21B A3B PT45.000.0%400ms1000ms
Qwen3 235B A22B Instruct 250745.000.0%400ms1000ms
🔧
DeepSeek R1 Distill Llama 8B45.000.0%400ms1000ms
🧠
Qwen3 VL 30B A3B Thinking45.000.0%400ms1000ms
🧠🔧
L3 70B Euryale V2.145.000.0%400ms1000ms
Tiny Aya Earth45.000.0%400ms1000ms
C4ai Command R7b Arabic 02 202545.000.0%400ms1000ms
🔧
ERNIE 4.5 VL 424B A47B Base PT45.000.0%400ms1000ms
L3 8B Lunaris V145.000.0%400ms1000ms
ERNIE 4.5 VL 28B A3B PT45.000.0%400ms1000ms
Cogito 671b V2.145.000.0%400ms1000ms
MiniMax M1 80k45.000.0%400ms1000ms
Qwen3 Next 80B A3B Thinking45.000.0%400ms1000ms
🧠🔧
Arch Router 1.5B45.000.0%400ms1000ms
Cogito 671b V2.1 FP845.000.0%400ms1000ms
DictaLM 3.0 24B Thinking45.000.0%400ms1000ms
🧠
Kimi K2 Instruct45.000.0%400ms1000ms
Qwen3 VL 235B A22B Instruct45.000.0%400ms1000ms
🔧
Tiny Aya Water45.000.0%400ms1000ms
DeepSeek V3.145.000.0%400ms1000ms
🔧
Qwen2.5 Coder 3B Instruct45.000.0%400ms1000ms
🔧
GLM 4.6 FP845.000.0%400ms1000ms
GLM 4.6V FP845.000.0%400ms1000ms
GLM 4.7 FP845.000.0%400ms1000ms
Command A Vision 07 202545.000.0%400ms1000ms
👁
GLM 4.5 Air FP845.000.0%400ms1000ms
Aya Expanse 32b45.000.0%400ms1000ms
Llama 3.3 Swallow 70B Instruct V0.445.000.0%400ms1000ms
🔧
GLM 4.545.000.0%400ms1000ms
Llama 3.1 70B Instruct45.000.0%400ms1000ms
🔧
EuroLLM 22B Instruct 251245.000.0%400ms1000ms
Apertus 70B Instruct 250945.000.0%400ms1000ms
Qwen SEA LION V4 32B IT45.000.0%400ms1000ms
🔧
Llama 4 Maverick 17B 128E Instruct FP845.000.0%400ms1000ms
🔧
Qwen3 32B45.000.0%400ms1000ms
🔧
DeepSeek R1 Distill Qwen 1.5B45.000.0%400ms1000ms
🧠🔧
MiniMax M2.545.000.0%400ms1000ms
GLM 4.6V45.000.0%400ms1000ms
AutoGLM Phone 9B Multilingual45.000.0%400ms1000ms
Qwen3.5 9B45.000.0%400ms1000ms
🔧
WizardLM 2 8x22B45.000.0%400ms1000ms
ERNIE 4.5 300B A47B Base PT45.000.0%400ms1000ms
Qwen3 VL 8B Instruct45.000.0%400ms1000ms
🔧
Gemma SEA LION V4 27B IT45.000.0%400ms1000ms
🔧
Qwen3.5 35B A3B45.000.0%400ms1000ms
🔧
Qwen3.5 27B45.000.0%400ms1000ms
🔧
GLM 545.000.0%400ms1000ms
Qwen3.5 397B A17B45.000.0%400ms1000ms
🔧
Kimi K2.545.000.0%400ms1000ms
Gpt Oss 120b45.000.0%400ms1000ms
DeepSeek V3.245.000.0%400ms1000ms
🔧
Llama 3.1 8B Instruct45.000.0%400ms1000ms
🔧
Qwen3.5 122B A10B45.000.0%400ms1000ms
🔧
Meta Llama 3 8B Instruct45.000.0%400ms1000ms
🔧
MiMo V2 Flash45.000.0%400ms1000ms
Gemma 3 27b It45.000.0%400ms1000ms
🔧
Gpt Oss 20b45.000.0%400ms1000ms
Llama 3.2 1B Instruct45.000.0%400ms1000ms
🔧
Qwen3 8B45.000.0%400ms1000ms
🔧
Qwen3 Coder 480B A35B Instruct45.000.0%400ms1000ms
🔧
huggingface/deepseek-ai/DeepSeek-V3-0324-34.010.0%457ms457ms
Qwen: Qwen3 Coder 480B A35B (free)15.040.0%9932ms15554ms
🔧
deepseek/deepseek-v3.115.030.0%17892ms37687ms

How to Use Huggingface on Antbase

All Huggingface models are available through Antbase's unified OpenAI-compatible API. You can either route directly to a specific Huggingface model or let ANT's intelligent router automatically select the best model for your task.

python
from openai import OpenAI

client = OpenAI(
    base_url="https://antbase.ai/v1",
    api_key="your-ant-api-key",
)

# Let ANT auto-route (may use Huggingface if optimal)
response = client.chat.completions.create(
    model="ant:auto",
    messages=[{"role": "user", "content": "Hello!"}],
)

Why Use Huggingface Through Antbase?

  • •No separate account needed — access Huggingface models instantly through your Antbase API key.
  • •Intelligent routing — ANT automatically selects the best Huggingface model for each task, or falls over to another provider if Huggingface is slow or down.
  • •Same token prices — Antbase charges zero markup on Huggingface token prices. You pay exactly what Huggingface charges.
  • •Automatic failover — if Huggingface has an outage, your requests seamlessly route to an equivalent model on another provider.