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.
Inkling Small - Model - OpenSmartRoute
Modelv1.0.0
Inkling Small
Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of.
Reference model card from the OpenRouter listing - model thinkingmachines/inkling-small. Prices are per million tokens as listed; ratings and installs below are from this marketplace.
Inkling Small
Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...
Facts
Vendor
Thinking Machines
Context window
1,048,576 tokens
Max output
262,144 tokens
Input price
$0.45 / 1M tokens
Output price
$1.20 / 1M tokens
Input
text, image, audio
Output
text
Tool calling
yes
Structured outputs
no
Reasoning
yes
Open weights
thinkingmachines/Inkling-Small
Endpoint: https://openrouter.ai/api/v1 (OpenAI-compatible), model thinkingmachines/inkling-small
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-thinkingmachines-inkling-small", ...}
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
model-thinkingmachines-inkling-small.ocm.jsonjson
{
"ocm": "1",
"id": "model-thinkingmachines-inkling-small",
"kind": "llm",
"name": "Inkling Small",
"description": "Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...",
"publisher": "Thinking Machines",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"llm",
"thinkingmachines",
"openrouter",
"open-weights",
"reasoning",
"tool-calling",
"image",
"audio",
"models"
],
"languages": [
"en"
],
"modalities": [
"text",
"image",
"audio"
],
"supports_tools": true,
"supports_streaming": true,
"context_window": 1048576
},
"quality_prior": 0.261,
"examples": [
"Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of..."
],
"primary": false,
"metadata": {
"source": {
"provider": "models",
"ref": "1785443117",
"url": "https://openrouter.ai/thinkingmachines/inkling-small",
"key": "thinkingmachines/inkling-small",
"catalogue": "https://openrouter.ai/api/v1"
},
"model": "thinkingmachines/inkling-small",
"pricing": {
"input_usd_per_1m": 0.45,
"output_usd_per_1m": 1.2,
"cache_read_usd_per_1m": 0.1
},
"max_output_tokens": 262144,
"output_modalities": [
"text"
],
"hugging_face_id": "thinkingmachines/Inkling-Small",
"reasoning": true,
"created": 1785443117,
"benchmarks": {
"intelligence_index": 26.1,
"coding_index": 52.9,
"agentic_index": 25,
"hub_downloads": 489489,
"hub_downloads_total": 604437,
"hub_likes": 408,
"hub_trending": 4,
"osr_index": 35.2,
"osr_coverage": 0.4
}
},
"cost": {
"usd_per_1k_tokens": 0.000825
},
"endpoints": [
{
"protocol": "openai",
"url": "https://openrouter.ai/api/v1"
}
]
}
Fetch it by URL: GET /api/v1/registry/model-thinkingmachines-inkling-small/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.
