Siliconflow
AI inference provider available on Antbase
OpenAI-compatible
About Siliconflow
Siliconflow 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
Siliconflow Models on Antbase
| Model | Score | Requests | Success Rate | Avg Latency | p95 Latency | Capabilities |
|---|---|---|---|---|---|---|
| GLM 5 | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Step 3.5 Flash | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| Kimi K2.5 | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| GLM 4.7 | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| DeepSeek V3.2 | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| DeepSeek V3.2 Exp | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| GLM 4.6V | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| MiniMax M2.1 | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| DeepSeek V3.1 Terminus | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| DeepSeek V3.1 | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| DeepSeek V3 | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| DeepSeek R1 | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🧠 |
| Z Image Turbo | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| DeepSeek V3.1 Nex N1 | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Qwen3 VL 32B Instruct | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Qwen3 VL 32B Thinking | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🧠🔧 |
| Qwen3 VL 8B Instruct | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Qwen3 VL 235B A22B Instruct | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Qwen3 VL 235B A22B Thinking | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🧠🔧 |
| Qwen3 VL 30B A3B Instruct | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Qwen3 VL 30B A3B Thinking | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🧠🔧 |
| Qwen3 VL 8B Thinking | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🧠🔧 |
| Kimi K2 Instruct 0905 | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| Gpt Oss 120b | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Gpt Oss 20b | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| GLM 4.6 | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Kimi K2 Thinking | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🧠 |
| GLM 4.5 Air | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Wan2.2 I2V A14B | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| Wan2.2 T2V A14B | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| Ling Flash 2.0 | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| Ring Flash 2.0 | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| GLM 4.5V | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Qwen Image | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Qwen3 Coder 480B A35B Instruct | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Ling Mini 2.0 | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| Qwen Image Edit | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Qwen3 Coder 30B A3B Instruct | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Hunyuan MT 7B | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| Qwen3 Next 80B A3B Instruct | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Qwen3 Omni 30B A3B Instruct | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Qwen3 Omni 30B A3B Thinking | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🧠🔧 |
| Qwen3 Omni 30B A3B Captioner | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Qwen3 30B A3B Instruct 2507 | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Qwen3 30B A3B Thinking 2507 | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🧠🔧 |
| Qwen3 235B A22B Instruct 2507 | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Qwen3 235B A22B Thinking 2507 | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🧠🔧 |
| Seed OSS 36B Instruct | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| ERNIE 4.5 300B A47B | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| Hunyuan A13B Instruct | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| Kimi K2 Instruct | 50.0 | 0 | 0.0% | 400ms | 1000ms | |
| Qwen3 32B | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Qwen3 14B | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Qwen3 8B | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Qwen3 Reranker 8B | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Qwen3 Reranker 0.6B | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Qwen2.5 VL 32B Instruct | 50.0 | 0 | 0.0% | 400ms | 1000ms | 👁🔧 |
| QwQ 32B | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🧠🔧 |
| Qwen3 Reranker 4B | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Qwen2.5 VL 72B Instruct | 50.0 | 0 | 0.0% | 400ms | 1000ms | 👁🔧 |
| GLM Z1 32B 0414 | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| GLM 4 32B 0414 | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| GLM Z1 9B 0414 | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| GLM 4 9B 0414 | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| DeepSeek R1 Distill Qwen 32B | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🧠🔧 |
| Qwen2.5 72B Instruct | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Qwen2.5 7B Instruct | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Qwen2.5 VL 7B Instruct | 50.0 | 0 | 0.0% | 400ms | 1000ms | 👁🔧 |
| DeepSeek R1 Distill Qwen 14B | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🧠🔧 |
| Qwen2.5 Coder 32B Instruct | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Qwen2.5 72B Instruct 128K | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Deepseek Vl2 | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Qwen2.5 32B Instruct | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Qwen2.5 14B Instruct | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Meta Llama 3.1 8B Instruct | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🔧 |
| Qwen3 Next 80B A3B Thinking | 50.0 | 0 | 0.0% | 400ms | 1000ms | 🧠🔧 |
| MiniMax M2.5 | 50.0 | 0 | 0.0% | 400ms | 1000ms |
How to Use Siliconflow on Antbase
All Siliconflow models are available through Antbase's unified OpenAI-compatible API. You can either route directly to a specific Siliconflow 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 Siliconflow if optimal)
response = client.chat.completions.create(
model="ant:auto",
messages=[{"role": "user", "content": "Hello!"}],
)Why Use Siliconflow Through Antbase?
- •No separate account needed — access Siliconflow models instantly through your Antbase API key.
- •Intelligent routing — ANT automatically selects the best Siliconflow model for each task, or falls over to another provider if Siliconflow is slow or down.
- •Same token prices — Antbase charges zero markup on Siliconflow token prices. You pay exactly what Siliconflow charges.
- •Automatic failover — if Siliconflow has an outage, your requests seamlessly route to an equivalent model on another provider.