Chat Completions
Create a completion for the chat conversation
AuthorizationBearer <token>
Bearer token authentication using API keys
In: header
modelstring
messagesarray<object>
temperature?number | null
max_tokens?number | null
top_p?number | null
frequency_penalty?number | null
presence_penalty?number | null
response_format?object
stream?boolean
Default
falsetools?array<object>
tool_choice?string & object
reasoning_effort?string | null
Controls the reasoning effort for reasoning-capable models
Value in
"minimal" | "low" | "medium" | "high"free_models_only?boolean
When used with auto routing, only route to free models (models with zero input and output pricing)
Default
falseResponse Body
curl -X POST "https://api.llmgateway.io/v1/chat/completions" \ -H "Content-Type: application/json" \ -d '{ "model": "gpt-5", "messages": [ { "role": "user", "content": "Hello!" } ] }'{
"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
}
},
"metadata": {
"requested_model": "string",
"requested_provider": "string",
"used_model": "string",
"used_provider": "string",
"underlying_used_model": "string"
}
}{
"error": {
"message": "string",
"type": "string",
"param": "string",
"code": "string"
}
}How is this guide?
Last updated on