Chat Completions -- Hober Docs

Endpoints

POST /v1/chat/completions

Create a chat completion. Supports streaming, tool calls, and JSON mode. OpenAI-compatible request and response format.

Request Body

Parameter	Type	Required	Description
model	string	required	Model slug from the catalog (e.g. "deepseek/deepseek-chat-v3.2")
messages	array	required	Array of message objects with role ("system", "user", "assistant") and content
stream	boolean	optional	If true, returns SSE stream of delta chunks. Default: false
temperature	number	optional	Sampling temperature 0-2. Default: 1.0
max_tokens	integer	optional	Maximum tokens to generate
top_p	number	optional	Nucleus sampling parameter 0-1. Default: 1.0
tools	array	optional	Array of tool definitions for function calling
tool_choice	string \| object	optional	"auto", "none", "required", or a specific tool object
response_format	object	optional	{ "type": "json_object" } to force JSON output
models	array	optional	Hober-specific: fallback model list (tried in order)
provider	object	optional	Hober-specific: provider routing preferences (see Hober Features)

modelstringrequired

Model slug from the catalog (e.g. "deepseek/deepseek-chat-v3.2")

messagesarrayrequired

Array of message objects with role ("system", "user", "assistant") and content

streambooleanoptional

If true, returns SSE stream of delta chunks. Default: false

temperaturenumberoptional

Sampling temperature 0-2. Default: 1.0

max_tokensintegeroptional

Maximum tokens to generate

top_pnumberoptional

Nucleus sampling parameter 0-1. Default: 1.0

toolsarrayoptional

Array of tool definitions for function calling

tool_choicestring | objectoptional

"auto", "none", "required", or a specific tool object

response_formatobjectoptional

{ "type": "json_object" } to force JSON output

modelsarrayoptional

Hober-specific: fallback model list (tried in order)

providerobjectoptional

Hober-specific: provider routing preferences (see Hober Features)

Response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1709000000,
  "model": "deepseek/deepseek-chat-v3.2",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Solana is a high-performance blockchain..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 24,
    "completion_tokens": 128,
    "total_tokens": 152
  }
}

Streaming Example

from openai import OpenAI

client = OpenAI(
    base_url="https://api.hober.dev",
    api_key="hb_live_your_key_here",
)

stream = client.chat.completions.create(
    model="deepseek/deepseek-chat-v3.2",
    messages=[{"role": "user", "content": "Count to 10"}],
    stream=True,
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")