LiteLLM Integration
Chat with model (LiteLLM - Cohere format)
Sends a chat request using Cohere-compatible format via LiteLLM.
AuthorizationBearer <token>
Bearer token authentication. Use your MPilot virtual-key JWT or admin JWT.
Virtual keys (prefixed with sk-bf-) can also be passed here.
In: header
modelstring
Model to use for chat completion
messagesarray<CohereMessage>
Array of message objects
tools?array<object>
tool_choice?string
Tool choice mode - AUTO lets the model decide, NONE disables tools, REQUIRED forces tool use
Value in
"AUTO" | "NONE" | "REQUIRED"temperature?number
Range
0 <= value <= 1p?number
Top-p sampling
k?integer
Top-k sampling
max_tokens?integer
stop_sequences?array<string>
frequency_penalty?number
presence_penalty?number
stream?boolean
safety_mode?string
Value in
"CONTEXTUAL" | "STRICT" | "NONE"log_probs?boolean
strict_tool_choice?boolean
thinking?object
response_format?object
Response Body
curl -X POST "https://loading/{AI_GATEWAY_URL}/litellm/cohere/v2/chat" \ -H "Content-Type: application/json" \ -d '{ "model": "command-r-plus", "messages": [ { "role": "system" } ] }'{
"id": "string",
"finish_reason": "COMPLETE",
"message": {
"role": "string",
"content": [
{
"type": "text",
"text": "string",
"image_url": {
"url": "string"
},
"thinking": "string",
"document": {
"data": {},
"id": "string"
}
}
],
"tool_calls": [
{
"id": "string",
"type": "function",
"function": {
"name": "string",
"arguments": "string"
}
}
],
"tool_plan": "string"
},
"usage": {
"billed_units": {
"input_tokens": 0,
"output_tokens": 0,
"search_units": 0,
"classifications": 0
},
"tokens": {
"input_tokens": 0,
"output_tokens": 0
},
"cached_tokens": 0
},
"logprobs": [
{
"token_ids": [
0
],
"text": "string",
"logprobs": [
0
]
}
]
}{
"type": "string",
"message": "string",
"code": "string"
}{
"type": "string",
"message": "string",
"code": "string"
}