DeepSeek
LLMFREE TIERDeepSeek V3, R1 — elite reasoning at fraction of cost
Operational
All systems responding normally
Last checked 01/05/2026, 8:49:30 pm
239ms response
Uptime History100.00% uptime
2026-04-26Today
Uptime
100.00%
Avg Latency
406ms
P95 Latency
450ms
Fastest
85ms
Checks
150
Response Time
Last 60 checks85ms min406ms avg7622ms max
💰 Pricing
deepseek-v3FREE
Input: $0.27/1MOutput: $1.1/1M
deepseek-r1: $0.55/$2.19
Free API in beta
⚡ Rate Limits
standard
RPM: 60TPM: 60,000
Can increase by contacting sales.
🤖 Models (2)
| Model | Task | Context | Vision | Tools | JSON |
|---|---|---|---|---|---|
| DeepSeek V3 | llm | 128k | — | ✅ | ✅ |
| DeepSeek R1 Extended chain-of-thought reasoning | llm | 128k | — | — | — |
Recent Checks
Showing last 15Operational
239ms1 May, 08:49 pm
Operational
291ms1 May, 08:11 pm
Operational
198ms1 May, 07:36 pm
Operational
413ms1 May, 06:51 pm
Operational
392ms1 May, 06:03 pm
Operational
96ms1 May, 05:15 pm
Operational
7536ms1 May, 04:17 pm
Operational
331ms1 May, 03:04 pm
Operational
212ms1 May, 01:46 pm
Operational
152ms1 May, 12:24 pm
Operational
256ms1 May, 11:27 am
Operational
408ms1 May, 10:48 am
Operational
148ms1 May, 09:53 am
Operational
238ms1 May, 09:29 am
Operational
227ms1 May, 09:00 am
Other LLM Providers
OpenAI
GPT-4o, o3, o1 — the benchmark everyone chases
Anthropic
Claude — safety-first reasoning and long context
Mistral AI
Mistral Large, Codestral — European frontier models
xAI Grok
Grok-3 — real-time web access, strong reasoning
AWS Bedrock
Managed foundation models — Claude, Llama, Titan on AWS
Azure OpenAI
OpenAI models on Microsoft Azure — enterprise SLA