Chat Completions

Create a completion for the chat conversation

Authorization

AuthorizationBearer <token>

Bearer token authentication using API keys

In: header

Request Body

modelstring

messages

temperature?number|null

max_tokens?number|null

top_p?number|null

frequency_penalty?number|null

presence_penalty?number|null

response_format?

stream?boolean

Defaultfalse

tools?

tool_choice?string|

Value in"required" | "none" | "auto"

reasoning_effort?string|null

Controls the reasoning effort for reasoning-capable models

Value in"minimal" | "low" | "medium" | "high" | "xhigh"

reasoning?

Unified reasoning configuration object for controlling reasoning behavior

effort?string|null

Controls the computational effort for supported models (currently only claude-opus-4-5-20251101)

Value in"low" | "medium" | "high"

free_models_only?boolean

When used with auto routing, only route to free models (models with zero input and output pricing)

Defaultfalse

onboarding?boolean

When true, skips email verification for free model usage. Intended for onboarding flows.

Defaultfalse

no_reasoning?boolean

When used with auto routing, exclude reasoning models from selection

Defaultfalse

sensitive_word_check?

image_config?

web_search?boolean

Enable native web search for models that support it. When enabled, the model can search the web for real-time information.

Defaultfalse

plugins?

Plugins to enable for this request. Currently supported: response-healing (automatically repairs malformed JSON responses when using response_format)

Response Body

curl -X POST "https://api.llmgateway.io/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5",
    "messages": [
      {
        "role": "user"
      }
    ]
  }'

curl -X POST "https://api.llmgateway.io/v1/chat/completions" \  -H "Content-Type: application/json" \  -d '{    "model": "gpt-5",    "messages": [      {        "role": "user"      }    ]  }'

{
  "id": "string",
  "object": "string",
  "created": 0,
  "model": "string",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "string",
        "content": "string",
        "reasoning": "string",
        "tool_calls": [
          {
            "id": "string",
            "type": "function",
            "function": {
              "name": "string",
              "arguments": "string"
            }
          }
        ],
        "images": [
          {
            "type": "image_url",
            "image_url": {
              "url": "string"
            }
          }
        ]
      },
      "finish_reason": "string"
    }
  ],
  "usage": {
    "prompt_tokens": 0,
    "completion_tokens": 0,
    "total_tokens": 0,
    "reasoning_tokens": 0,
    "prompt_tokens_details": {
      "cached_tokens": 0
    },
    "cost_usd_total": 0,
    "cost_usd_input": 0,
    "cost_usd_output": 0,
    "cost_usd_cached_input": 0,
    "info": "string",
    "cost_usd_request": 0
  },
  "metadata": {
    "requested_model": "string",
    "requested_provider": "string",
    "used_model": "string",
    "used_provider": "string",
    "underlying_used_model": "string",
    "routing": [
      {
        "provider": "string",
        "model": "string",
        "status_code": 0,
        "error_type": "string"
      }
    ]
  }
}

{
  "error": {
    "message": "string",
    "type": "string",
    "param": "string",
    "code": "string"
  }
}

Chat Completions

Authorization

Request Body

Response Body

200

500