Inference¶

POST /cr/gcloud_predict_firebase_base_oss

Primary prediction endpoint. Supports streaming responses and optional RAG retrieval.

Field	Type	Required	Description
`prompt`	string	yes	User prompt text.
`query_only`	string	yes	Query form for routing/retrieval.
`model_name`	string	no	Model name from `/cr/get_allowed_models`.
`stream`	boolean	no	Defaults to `true`.
`use_rag`	boolean	no	Enable retrieval context.
`sequential_budget`	integer	no	Sequential reasoning budget.
`parallel_budget`	integer	no	Parallel reasoning budget.
`temperature`	number	no	Sampling temperature.

Returns

200 OK as a streaming SSE response when stream=true.
Events typically include token chunks and a final final_result payload.

{"type":"final_result","predictions":{"0":{"answers":["..."],"thoughtTraces":["..."]}}}

curl -s -X POST "https://cr-api.icosacomputing.com/cr/gcloud_predict_firebase_base_oss" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: <your_api_key>" \
  -d '{
    "prompt": "What is the capital of France?",
    "query_only": "What is the capital of France?",
    "model_name": "Generalist: Base",
    "stream": true,
    "use_rag": false,
    "sequential_budget": 1,
    "parallel_budget": 1,
    "temperature": 0.0
  }'

import requests

payload = {
    "prompt": "What is the capital of France?",
    "query_only": "What is the capital of France?",
    "model_name": "Generalist: Base",
    "stream": True,
    "use_rag": False,
    "sequential_budget": 1,
    "parallel_budget": 1,
    "temperature": 0.0,
}

resp = requests.post(
    "https://cr-api.icosacomputing.com/cr/gcloud_predict_firebase_base_oss",
    headers={
        "Content-Type": "application/json",
        "X-API-Key": "<your_api_key>",
    },
    json=payload,
    timeout=120,
)
print(resp.text)

const payload = {
  prompt: "What is the capital of France?",
  query_only: "What is the capital of France?",
  model_name: "Generalist: Base",
  stream: true,
  use_rag: false,
  sequential_budget: 1,
  parallel_budget: 1,
  temperature: 0.0,
};

const res = await fetch("https://cr-api.icosacomputing.com/cr/gcloud_predict_firebase_base_oss", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "X-API-Key": "<your_api_key>",
  },
  body: JSON.stringify(payload),
});

console.log(await res.text());