Chat Completions

POST https://api.solcardinference.ai/v1/chat/completions

Request and response follow the OpenAI Chat Completions format. Only the fields below are accepted; others are ignored.

Field	Type	Notes
model	string	Required. A model ID.
messages	array	Required. system, user, assistant and tool messages. Content is a string or an array of text parts.
stream	boolean	Stream as server-sent events. See streaming.
stream_options	object	{ "include_usage": true } adds a final usage chunk.
max_completion_tokens	integer	Output token limit, up to 32,768. max_tokens is accepted as an alias.
temperature	number
top_p	number
stop	string | array
presence_penalty	number
frequency_penalty	number
seed	integer
logit_bias	object
logprobs	boolean
top_logprobs	integer
response_format	object	{ "type": "json_object" } or { "type": "json_schema", "json_schema": {...} }.
tools	array	Function tools. See tool calling.
tool_choice	string | object
parallel_tool_calls	boolean
reasoning_effort	string	Default none. See reasoning.
web_search_options	object	{ "search_context_size": "low" | "medium" | "high" }. See web search.
n	integer	Default 1. Only 1 is supported.
user	string

Not supported: image, audio and file content (400 unsupported_content), n above 1 and best_of (400 unsupported_parameter).

Example request

curl https://api.solcardinference.ai/v1/chat/completions \
  -H "Authorization: Bearer $SOLCARD_INFERENCE_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "model": "flash", "messages": [{ "role": "user", "content": "Hi" }] }'

Example response

{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "choices": [{ "index": 0, "message": { "role": "assistant", "content": "Hello! How can I help?" }, "finish_reason": "stop" }],
  "usage": { "prompt_tokens": 9, "completion_tokens": 7, "total_tokens": 16 }
}