Smol
https://info.smol.services/

Check your user token

Server Status

Uptime 19 hours, 24 minutes, 23 seconds
Total prompts 16,358
Active users 8

OpenAI

API Endpoint (Base URL)
https://smol.services/proxy/openai

GPT-4.5

Available
Quota: 3 million tokens

o1

Available

o1 mini

Available

GPT-4o Mini / 3.5 Turbo

Available

GPT-4

Available

GPT-4 Turbo

Available

GPT-4o

Available

o3 mini

Available

GPT 4.1

Available

GPT 4.1 mini

Available

GPT 4.1 nano

Available

o3

Available

o4 mini

Available

Google AI

API Endpoint (Base URL)
https://smol.services/proxy/google-ai

Gemini Flash

Available

Gemini Pro

Available

Gemini Ultra

Available

Mistral AI

API Endpoint (Base URL)
https://smol.services/proxy/mistral-ai

Mistral 7B

Available

Mistral Nemo

Available

Mistral Medium

Available

Mistral Large

Available

AWS Bedrock

API Endpoint (Base URL)
https://smol.services/proxy/aws/claude

AWS Claude (Sonnet)

Unavailable
Quota: 4 million tokens

Azure OpenAI

API Endpoint (Base URL)
https://smol.services/proxy/azure/openai

Azure o3

Available

Azure o4 mini

Available

Deepseek AI

API Endpoint (Base URL)
https://smol.services/proxy/deepseek

Deepseek Chat

Available

xAI (Grok)

API Endpoint (Base URL)
https://smol.services/proxy/xai

Grok 3

Available

Grok 3 Mini

Available

Grok 4

Available

Limits

Context Limits

Anthropic max context: 80000 tokens
OpenAI max output: 65535 tokens
Anthropic max output: 2048 tokens

Token Quotas

GPT-4.5: 3 million tokens
Claude (Sonnet): 4 million tokens
Claude (Opus): 3 million tokens
AWS Claude (Sonnet): 4 million tokens
AWS Claude (Opus): 3 million tokens
GCP Claude (Sonnet): 4 million tokens