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.
Gemma 4 26B A4B - Model - OpenSmartRoute
Modelv1.0.0
Gemma 4 26B A4B
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B qual
Reference model card from the OpenRouter listing - model google/gemma-4-26b-a4b-it. Prices are per million tokens as listed; ratings and installs below are from this marketplace.
Gemma 4 26B A4B
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
Facts
Vendor
Google
Context window
262,144 tokens
Max output
235,929 tokens
Input price
$0.09 / 1M tokens
Output price
$0.30 / 1M tokens
Input
image, text, video
Output
text
Tool calling
yes
Structured outputs
yes
Reasoning
yes
Open weights
google/gemma-4-26B-A4B-it
Endpoint: https://openrouter.ai/api/v1 (OpenAI-compatible), model google/gemma-4-26b-a4b-it
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-google-gemma-4-26b-a4b-it", ...}
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
model-google-gemma-4-26b-a4b-it.ocm.jsonjson
{
"ocm": "1",
"id": "model-google-gemma-4-26b-a4b-it",
"kind": "llm",
"name": "Gemma 4 26B A4B ",
"description": "Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...",
"publisher": "Google",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"llm",
"google",
"openrouter",
"open-weights",
"reasoning",
"tool-calling",
"image",
"video",
"models"
],
"languages": [
"en"
],
"modalities": [
"image",
"text",
"video"
],
"supports_tools": true,
"supports_streaming": true,
"context_window": 262144
},
"quality_prior": 0.6,
"examples": [
"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at..."
],
"primary": false,
"metadata": {
"source": {
"provider": "models",
"ref": "1775227989",
"url": "https://openrouter.ai/google/gemma-4-26b-a4b-it",
"key": "google/gemma-4-26b-a4b-it",
"catalogue": "https://openrouter.ai/api/v1"
},
"model": "google/gemma-4-26b-a4b-it",
"pricing": {
"input_usd_per_1m": 0.09,
"output_usd_per_1m": 0.3,
"cache_read_usd_per_1m": 0.05
},
"max_output_tokens": 235929,
"output_modalities": [
"text"
],
"hugging_face_id": "google/gemma-4-26B-A4B-it",
"reasoning": true,
"created": 1775227989,
"benchmarks": {
"coding_index": 39.3,
"hub_downloads": 9794984,
"hub_downloads_total": 60749504,
"hub_likes": 1526,
"hub_trending": 20
}
},
"cost": {
"usd_per_1k_tokens": 0.000195
},
"endpoints": [
{
"protocol": "openai",
"url": "https://openrouter.ai/api/v1"
}
]
}
Fetch it by URL: GET /api/v1/registry/model-google-gemma-4-26b-a4b-it/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.
