Chat completions

POST /v1/chat/completions — OpenAI-format chat completions through SERV.

POST https://inference-api.openserv.ai/v1/chat/completions

OpenAI Chat Completions format. The universal endpoint — works with every model in the catalog.

Request

Authorization · string · required

Bearer $SERV_API_KEY.

model · string · required

Model ID from the catalog, for example gpt-5.4-mini.

messages · array · required

The conversation so far. Must include a system or developer message. Each entry has a role (system, user, assistant, or tool) and content.

max_completion_tokens · integer

Maximum number of tokens to generate.

reasoning_effort · string

Reasoning depth for reasoning-capable models.

temperature · number

Sampling temperature.

tools · array

Function definitions, in OpenAI format: { type: "function", function: { name, parameters } }.

tool_choice · string | object

"auto", "none", or { type: "function", function: { name } }.

stream · boolean · default: "false"

Stream the response as server-sent events.

All other OpenAI Chat Completions parameters are accepted and forwarded to the model.

Response

id · string

Unique identifier for the completion.

object · string

Always "chat.completion".

model · string

The model used to generate the completion.

choices · array

The generated completions. choices[0].message.content holds the text.

Show Choice object

index · integer

Position of this choice in the array.

message · object

Contains role ("assistant") and content.

finish_reason · string

One of stop, length, content_filter, or tool_calls.

usage · object

Token counts: prompt_tokens, completion_tokens, total_tokens.

curl

curl https://inference-api.openserv.ai/v1/chat/completions \
  -H "Authorization: Bearer $SERV_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4-mini",
    "messages": [
      {"role": "system", "content": "You are a concise assistant."},
      {"role": "user", "content": "Hello!"}
    ]
  }'

{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "model": "gpt-5.4-mini",
  "choices": [
    {
      "index": 0,
      "message": { "role": "assistant", "content": "Hello! How can I help?" },
      "finish_reason": "stop"
    }
  ],
  "usage": { "prompt_tokens": 18, "completion_tokens": 7, "total_tokens": 25 }
}