# Create chat completion

**POST /z1/chat/completions**

Main endpoint for AI chat interactions. Supports:
- Multi-turn conversations with memory
- RAG document retrieval
- Streaming responses
- Tool/function calling
- Response caching
- Web grounding

## Plimver AI Models
- **PV-TURBO**: Ultra-fast responses (<1s) - 1 credit/request
- **PV-STANDARD**: Balanced performance - 2 credits/request
- **PV-ADVANCED**: Deep reasoning - 5 credits/request
- **PV-CODEX**: Specialized coding - 3 credits/request



## Servers
- Production server: https://api.plimverai.tech (Production server)
- Azure production server: https://zenux-api.redglacier-fb4abe56.southafricanorth.azurecontainerapps.io (Azure production server)


## Authentication methods
- Bearer auth
- Api key auth


## Parameters



## Body parameters
Content-type: application/json

- **model** (string)
  Plimver AI model to use
- **messages** (array[object])
  Array of conversation messages
- **user_id** (string)
  Unique user identifier for memory isolation
- **temperature** (number(float))
  Sampling temperature
- **max_tokens** (integer)
  Maximum tokens in response
- **stream** (boolean)
  Enable Server-Sent Events streaming
- **use_rag** (boolean)
  Enable RAG document retrieval
- **rag_k** (integer)
  Number of RAG documents to retrieve (tier-dependent)
- **skip_cache** (boolean)
  Bypass response cache
- **tools** (array[object])
  Function calling tools (OpenAI format)

## Responses
### 200: Successful response

#### Body Parameters: application/json (object)
- **id** (string)
  
- **object** (string)
  
- **created** (integer(int64))
  
- **model** (string)
  
- **choices** (array[object])
  
- **usage** (object)
  
- **citations** (array[object])
  RAG citations (if use_rag=true)
- **memory_context** (object)
  

### 400: Bad request - invalid parameters

#### Body Parameters: application/json (object)
- **status** (string)
  
- **message** (string)
  
- **code** (string)
  
- **details** (object | null)
  

### 401: Unauthorized - invalid or missing API key

#### Body Parameters: application/json (object)
- **status** (string)
  
- **message** (string)
  
- **code** (string)
  
- **details** (object | null)
  

### 429: Rate limit exceeded
#### Headers
- **X-RateLimit-Limit** (integer)
  Rate limit ceiling for this endpoint
- **X-RateLimit-Remaining** (integer)
  Number of requests remaining
- **X-RateLimit-Reset** (integer)
  Timestamp when rate limit resets
- **Retry-After** (integer)
  Seconds to wait before retrying

#### Body Parameters: application/json (object)
- **status** (string)
  
- **message** (string)
  
- **code** (string)
  
- **details** (object | null)
  

### 500: Internal server error

#### Body Parameters: application/json (object)
- **status** (string)
  
- **message** (string)
  
- **code** (string)
  
- **details** (object | null)
  


[Powered by Bump.sh](https://bump.sh)