SiliconFlow
InferenceFREE TIERHigh-performance open-source model API — DeepSeek, Qwen
Operational
All systems responding normally
Last checked 21/09/2026, 9:43:17 am
1763ms response
Uptime History100.00% uptime
2026-09-19Today
Uptime
100.00%
Avg Latency
1556ms
P95 Latency
1845ms
Fastest
1113ms
Checks
150
Response Time
Last 60 checks1113ms min1556ms avg2056ms max
💰 Pricing
deepseek-v3FREE
Input: $0.27/1MOutput: $1.1/1M
Strong for CJK tasks
Free tier available
⚡ Rate Limits
free
RPM: 30TPM: 60,000
Free: 30 RPM, 60K TPM. Paid: up to 500 RPM.
🤖 Models (1)
| Model | Task | Context | Vision | Tools | JSON |
|---|---|---|---|---|---|
| DeepSeek V3 High-performance open-source API. Strong for CJK. | llm | 128k | — | ✅ | ✅ |
Recent Checks
Showing last 15Operational
1763ms21 Sept, 09:43 am
Operational
1517ms21 Sept, 09:34 am
Operational
2016ms21 Sept, 09:21 am
Operational
1583ms21 Sept, 09:09 am
Operational
1582ms21 Sept, 08:52 am
Operational
1749ms21 Sept, 08:42 am
Operational
1845ms21 Sept, 08:34 am
Operational
1900ms21 Sept, 08:22 am
Operational
1734ms21 Sept, 08:09 am
Operational
1695ms21 Sept, 07:53 am
Operational
1669ms21 Sept, 07:42 am
Operational
1580ms21 Sept, 07:34 am
Operational
1657ms21 Sept, 07:21 am
Operational
1674ms21 Sept, 07:09 am
Operational
1446ms21 Sept, 06:52 am
Other Inference Providers
Groq
LPU inference — fastest tokens per second on the market
Cerebras
Wafer-scale chip inference — 1,000+ tokens/sec
Together AI
Open-source model inference — Llama, Mixtral, FLUX
Fireworks AI
Fast open-model inference — FireFunction, Llama, Mixtral
OpenRouter
Unified API across 200+ models — route by price or speed
Hugging Face
Serverless inference API — 100k+ open models on demand