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.
Mistral Nemo - Model - OpenSmartRoute
Modelv1.0.0
Mistral Nemo
A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chine
Reference model card from the OpenRouter listing - model mistralai/mistral-nemo. Prices are per million tokens as listed; ratings and installs below are from this marketplace.
Mistral Nemo
A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...
Facts
Vendor
Mistral AI
Context window
131,072 tokens
Max output
16,384 tokens
Input price
$0.02 / 1M tokens
Output price
$0.03 / 1M tokens
Input
text
Output
text
Tool calling
yes
Structured outputs
yes
Reasoning
no
Open weights
mistralai/Mistral-Nemo-Instruct-2407
Endpoint: https://openrouter.ai/api/v1 (OpenAI-compatible), model mistralai/mistral-nemo
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-mistralai-mistral-nemo", ...}
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
model-mistralai-mistral-nemo.ocm.jsonjson
{
"ocm": "1",
"id": "model-mistralai-mistral-nemo",
"kind": "llm",
"name": "Mistral Nemo",
"description": "A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...",
"publisher": "Mistral AI",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"llm",
"mistralai",
"openrouter",
"open-weights",
"tool-calling",
"models"
],
"languages": [
"en"
],
"modalities": [
"text"
],
"supports_tools": true,
"supports_streaming": true,
"context_window": 131072
},
"quality_prior": 0.6,
"examples": [
"A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,..."
],
"primary": false,
"metadata": {
"source": {
"provider": "models",
"ref": "1721347200",
"url": "https://openrouter.ai/mistralai/mistral-nemo",
"key": "mistralai/mistral-nemo",
"catalogue": "https://openrouter.ai/api/v1"
},
"model": "mistralai/mistral-nemo",
"pricing": {
"input_usd_per_1m": 0.019,
"output_usd_per_1m": 0.03
},
"max_output_tokens": 16384,
"output_modalities": [
"text"
],
"hugging_face_id": "mistralai/Mistral-Nemo-Instruct-2407",
"created": 1721347200,
"benchmarks": {
"bbh": 50.4,
"math_lvl5": 12.7,
"gpqa": 29,
"musr": 39,
"mmlu_pro": 35.2,
"hf_leaderboard_avg": 38.4,
"ifeval": 63.8,
"hub_downloads": 388807,
"hub_downloads_total": 10383294,
"hub_likes": 1707,
"hub_trending": 4,
"osr_index": 31,
"osr_coverage": 0.3
}
},
"cost": {
"usd_per_1k_tokens": 0.000025
},
"endpoints": [
{
"protocol": "openai",
"url": "https://openrouter.ai/api/v1"
}
]
}
Fetch it by URL: GET /api/v1/registry/model-mistralai-mistral-nemo/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.
