Models API

Run inference against hosted AI models. Currently powered by Ollama.

Available Models

Model	Parameters	Provider	Description
phi3:3.8b	3.8B	Ollama	Microsoft Phi-3 Mini — compact, efficient model for general tasks

More models will be added over time.

---

List Available Models

GET /api/models

Public endpoint — no authentication required.

Response

{
  "models": [
    {
      "name": "phi3:3.8b",
      "provider": "ollama",
      "parameterSize": "3.8B",
      "description": "Microsoft Phi-3 Mini — compact, efficient model for general tasks"
    }
  ]
}

---

Run Inference

POST /api/models/infer

Requires: Authorization: Bearer YOUR_JWT_TOKEN

Request Body

Field	Type	Required	Default	Description
model	string	Yes	—	Model identifier (e.g. phi3:3.8b)
prompt	string	Yes	—	The prompt to send
systemPrompt	string	No	—	System instructions for the model
temperature	number	No	0.7	Sampling temperature (0.0–2.0)
maxTokens	number	No	1024	Maximum tokens to generate (1–8192)
stream	boolean	No	false	Whether to stream the response

Example

curl -X POST https://intelligence.cognitera.ai/api/models/infer \
  -H "Authorization: Bearer YOUR_JWT_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "phi3:3.8b",
    "prompt": "Write a Python function to calculate fibonacci numbers",
    "systemPrompt": "You are a helpful programming assistant.",
    "temperature": 0.3,
    "maxTokens": 2048
  }'

Response

{
  "id": "inference-uuid",
  "model": "phi3:3.8b",
  "response": "Here's a Python function to calculate Fibonacci numbers:\n\n```python\ndef fibonacci(n):\n    if n <= 1:\n        return n\n    a, b = 0, 1\n    for _ in range(2, n + 1):\n        a, b = b, a + b\n    return b\n```\n\nThis iterative approach runs in O(n) time...",
  "tokensUsed": 187,
  "durationMs": 2340
}

---

Health Check

GET /api/models/health

Public endpoint — verify model provider connectivity.

Response

{
  "ollama": true
}