Count input tokens (LangChain - OpenAI format)
Counts the number of tokens in a Responses API request via LangChain.
AuthorizationBearer <token>
Bearer token authentication. Use your MPilot virtual-key JWT or admin JWT.
Virtual keys (prefixed with sk-bf-) can also be passed here.
In: header
modelstring
Model identifier
inputstring | array<object>
Input - can be a string or array of messages
stream?boolean
instructions?string
System instructions for the model
max_output_tokens?integer
metadata?object
Empty Object
parallel_tool_calls?boolean
previous_response_id?string
reasoning?object
store?boolean
temperature?number
Range
0 <= value <= 2text?object
tool_choice?string | object
tools?array<object>
top_p?number
truncation?string
Value in
"auto" | "disabled"user?string
fallbacks?array<string>
Response Body
curl -X POST "https://loading/{AI_GATEWAY_URL}/langchain/v1/responses/input_tokens" \ -H "Content-Type: application/json" \ -d '{ "model": "gpt-4", "input": "string" }'{
"object": "string",
"model": "string",
"input_tokens": 0,
"input_tokens_details": {
"text_tokens": 0,
"audio_tokens": 0,
"image_tokens": 0,
"cached_read_tokens": 0,
"cached_write_tokens": 0
},
"tokens": [
0
],
"token_strings": [
"string"
],
"output_tokens": 0,
"total_tokens": 0,
"extra_fields": {
"request_type": "string",
"provider": "openai",
"model_requested": "string",
"model_deployment": "string",
"latency": 0,
"chunk_index": 0,
"raw_request": {},
"raw_response": {},
"cache_debug": {
"cache_hit": true,
"cache_id": "string",
"hit_type": "string",
"requested_provider": "string",
"requested_model": "string",
"provider_used": "string",
"model_used": "string",
"input_tokens": 0,
"threshold": 0,
"similarity": 0
}
}
}{
"event_id": "string",
"type": "string",
"is_bifrost_error": true,
"status_code": 0,
"error": {
"type": "string",
"code": "string",
"message": "string",
"param": "string",
"event_id": "string"
},
"extra_fields": {
"provider": "openai",
"model_requested": "string",
"request_type": "string"
}
}{
"event_id": "string",
"type": "string",
"is_bifrost_error": true,
"status_code": 0,
"error": {
"type": "string",
"code": "string",
"message": "string",
"param": "string",
"event_id": "string"
},
"extra_fields": {
"provider": "openai",
"model_requested": "string",
"request_type": "string"
}
}