Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
Phi 4 - Model - OpenSmartRoute
Modelv1.0.0
Phi 4
[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 b
Reference model card from the OpenRouter listing - model microsoft/phi-4. Prices are per million tokens as listed; ratings and installs below are from this marketplace.
Phi 4
Microsoft Research Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...
Facts
Vendor
Microsoft
Context window
16,384 tokens
Max output
14,745 tokens
Input price
$0.07 / 1M tokens
Output price
$0.14 / 1M tokens
Input
text
Output
text
Tool calling
no
Structured outputs
yes
Reasoning
no
Open weights
microsoft/phi-4
Endpoint: https://openrouter.ai/api/v1 (OpenAI-compatible), model microsoft/phi-4
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - nothing else to configure
curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'
# or pin it on the OpenAI-compatible endpoint: {"model": "model-microsoft-phi-4", ...}
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
model-microsoft-phi-4.ocm.jsonjson
{
"ocm": "1",
"id": "model-microsoft-phi-4",
"kind": "llm",
"name": "Phi 4",
"description": "[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...",
"publisher": "Microsoft",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"llm",
"microsoft",
"openrouter",
"open-weights",
"models"
],
"languages": [
"en"
],
"modalities": [
"text"
],
"supports_tools": false,
"supports_streaming": true,
"context_window": 16384
},
"quality_prior": 0.6,
"examples": [
"[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion..."
],
"primary": false,
"metadata": {
"source": {
"provider": "models",
"ref": "1736489872",
"url": "https://openrouter.ai/microsoft/phi-4",
"key": "microsoft/phi-4",
"catalogue": "https://openrouter.ai/api/v1"
},
"model": "microsoft/phi-4",
"pricing": {
"input_usd_per_1m": 0.07,
"output_usd_per_1m": 0.14
},
"max_output_tokens": 14745,
"output_modalities": [
"text"
],
"hugging_face_id": "microsoft/phi-4",
"created": 1736489872,
"benchmarks": {
"ifeval": 68.8,
"bbh": 68.9,
"math_lvl5": 50,
"gpqa": 33.6,
"musr": 41.1,
"mmlu_pro": 53.8,
"hf_leaderboard_avg": 52.7,
"hub_downloads": 685789,
"hub_downloads_total": 14367893,
"hub_likes": 2304,
"hub_trending": 5,
"osr_index": 37.1,
"osr_coverage": 0.3
}
},
"cost": {
"usd_per_1k_tokens": 0.000105
},
"endpoints": [
{
"protocol": "openai",
"url": "https://openrouter.ai/api/v1"
}
]
}
Fetch it by URL: GET /api/v1/registry/model-microsoft-phi-4/manifest?version=1.0.0
Reviews
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.
