We support the models
Feature comparison
Price
per million token
Model Name
- SeaLLM-7b-v3
$0.2
- SeaLLM-7b-v2.5
$0.2
- SQLCoder-7b-2
$0.6
Use case
Model Name
- SeaLLM-7b-v3
RAG, NER, Sentiment analysis
- SeaLLM-7b-v2.5
RAG, NER, Sentiment analysis
- SQLCoder-7b-2
Text-to-SQL
Learn more
Model Name
- SeaLLM-7b-v3
- LLM for Southeast Asia
- SeaLLM-7b-v2.5
- LLM for Southeast Asia
- SQLCoder-7b-2
- Get started with SQLCoder-7b-2
Feature comparison
Model Name
| Feature | |||
|---|---|---|---|
| SeaLLM-7b-v3 | $0.2 | RAG, NER, Sentiment analysis | LLM for Southeast Asia |
| SeaLLM-7b-v2.5 | $0.2 | RAG, NER, Sentiment analysis | LLM for Southeast Asia |
| SQLCoder-7b-2 | $0.6 | Text-to-SQL | Get started with SQLCoder-7b-2 |
LLM as a service
Seamless LLM Integration
Your Quick Setup Guide
1.
Log in to Float16.cloud and navigate to LLM as a Service.
curl -X POST https://api.float16.cloud/v1/chat/completions -d
'{
"model": "SeaLLM-7b-v2.5",
"messages": [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "สวัสดี"
}
]
}'
-H "Content-Type: application/json"
-H "Authorization: Bearer <float16-api-key>"3.
Enter your float16-api-key and model.
4.
Connect to your app via our API.
Pay per token
Cost-efficient pricing model based on actual tokens used, ensuring you only pay for what you need.
OpenAI API Compatibility
Our models are compatible with OpenAI API, allowing you to easily integrate our models into your existing workflow.
Context caching
Our models are optimized for context caching, allowing you to reuse context across multiple request for faster response times.