API Reference
Complete reference for DeepShift AI API v1
Authentication
The DeepShift API uses API keys for authentication. Include your API key in the Authorization header of all requests.
Request Header
Authorization: Bearer YOUR_API_KEYSecurity Best Practices
- Never expose your API key in client-side code
- Use environment variables to store API keys
- Rotate your API keys regularly
Completions
Generate text completions using our advanced AI models.
POST /v1/completions
Create completionRequest Body
{
"model": "deepshift-pro",
"prompt": "Once upon a time",
"max_tokens": 100,
"temperature": 0.7,
"top_p": 1,
"frequency_penalty": 0,
"presence_penalty": 0
}Parameters
modelrequiredID of the model to use. See available models endpoint.
promptrequiredThe prompt to generate completions for.
max_tokensoptionalMaximum number of tokens to generate. Defaults to 16.
temperatureoptionalSampling temperature between 0 and 2. Higher values make output more random. Defaults to 1.
Response
{
"id": "cmpl-abc123",
"object": "text_completion",
"created": 1677858242,
"model": "deepshift-pro",
"choices": [
{
"text": " in a land far, far away...",
"index": 0,
"logprobs": null,
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 5,
"completion_tokens": 9,
"total_tokens": 14
}
}Embeddings
Get vector representations of text that can be used for semantic search, clustering, and more.
POST /v1/embeddings
Create embeddingsRequest Body
{
"model": "deepshift-embed",
"input": "The quick brown fox jumps over the lazy dog"
}Models
List and describe the various models available in the API.
GET /v1/models
List modelsAvailable Models
deepshift-pro
Our most capable model for complex tasks and reasoning
deepshift-fast
Optimized for speed and efficiency in production environments
deepshift-embed
Specialized model for generating high-quality embeddings
Rate Limits
Default Limits
- Requests per minute: 60
- Tokens per minute: 90,000
- Requests per day: 10,000
Contact sales for higher limits or enterprise plans.