MediaWiki - User contributions [en]

AI on Demand: Usage

2026-10-18T09:57:18Z

Sst-mei: /* Usage - List all models - General purpose */

= Overview =
This pages describes some useful usage commands.

= Usage =
We assume you've received your API key from us in our usual manner.

== Usage - List all models ==
=== Usage - List all models - General purpose (including OCR) ===
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# List all general purpose models:
curl https://llm.stoney-cloud.com/v1/models \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang='json'>
{
"object": "list",
"data": [
{
"id": "allenai/olmOCR-2-7B",
"object": "model",
"max_model_len": 8192
},
{
"id": "apertus-ai/Apertus-v1.5-8B",
"object": "model",
"max_model_len": 131072
},
{
"id": "convaiinnovations/laya",
"object": "model",
"max_model_len": 4096
},
{
"id": "deepseek-ai/DeepSeek-V4-Flash-0731",
"object": "model",
"max_model_len": 524288
},
{
"id": "google/gemma-4-31B-it",
"object": "model",
"max_model_len": 163840
},
{
"id": "jaredpalmer/kev-27b",
"object": "model",
"max_model_len": 65536
},
{
"id": "lightonai/LightOnOCR-2-1B",
"object": "model",
"max_model_len": 16384
},
{
"id": "Mapika/decider-31b",
"object": "model",
"max_model_len": 40960
},
{
"id": "MinerU2.5-2509-1.2B",
"object": "model",
"max_model_len": 16384
},
{
"id": "MiniMaxAI/MiniMax-M2.5",
"object": "model",
"max_model_len": 196608
},
{
"id": "NVIDIA/NVIDIA-Nemotron-3-Super-120B-A12B",
"object": "model",
"max_model_len": 131072
},
{
"id": "openai/gpt-oss-120b",
"object": "model",
"max_model_len": 131072
},
{
"id": "opendatalab/MinerU2.5-2509-1.2B",
"object": "model",
"max_model_len": 16384
},
{
"id": "Qwen/Qwen3.5-35B-A3B-FP8",
"object": "model",
"max_model_len": 131072
},
{
"id": "Qwen/Qwen3.8-27B",
"object": "model",
"max_model_len": 262144
},
{
"id": "Qwen/Qwen3-Coder-Next",
"object": "model",
"max_model_len": 262144
},
{
"id": "zai-org/GLM-5.3-Flash",
"object": "model",
"max_model_len": 262144
}
]
}
</syntaxhighlight>

=== Usage - List all models - Audio ===
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# List all audio models:
curl https://llm.stoney-cloud.com/v1/audio/models \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang="json">
{
"data": [
{
"object": "model",
"id": "mistralai/Voxtral-Mini-3B-2507"
},
{
"object": "model",
"id": "openai/whisper-large-v3"
}
],
"object": "list"
}
</syntaxhighlight>

=== Usage - List all models - Embeddings ===
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# List all embeddings models:
curl https://llm.stoney-cloud.com/v1/embeddings/models \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang="json">
{
"data": [
{
"object": "model",
"max_model_len": 8192,
"id": "BAAI/bge-m3"
}
],
"object": "list"
}
</syntaxhighlight>

=== Usage - List all models - Rerank ===
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# List all rerank models:
curl https://llm.stoney-cloud.com/v1/rerank/models \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang="json">
{
"data": [
{
"object": "model",
"max_model_len": 8192,
"id": "BAAI/bge-reranker-v2-m3"
}
],
"object": "list"
}
</syntaxhighlight>

=== Usage - List all models - Images ===
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# List all images models:
curl https://llm.stoney-cloud.com/v1/images/models \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang="json">
{
"data": [
{
"object": "model",
"id": "black-forest-labs/FLUX.1-schnell"
}
],
"object": "list"
}
</syntaxhighlight>

== Usage - Inspecting your usage ==
We issue one key per model for now. The usage is thus per-model-per-key.

<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# Set desired month in the form YYYY-MM, for example: '2026-03'.
MONTH=$(date +%Y-%m)

curl https://llm.stoney-cloud.com/v1/usage?month="$MONTH" \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang="json">
{
"month": "2026-08",
"models": [
{
"cost_chf": 0.000019,
"output": 11,
"input": 256,
"model": "allenai/olmOCR-2-7B"
},
{
"cost_chf": 0.003268,
"output": 942,
"input": 22679,
"model": "apertus-ai/Apertus-v1.5-8B"
},
{
"cost_chf": 0.562569,
"output": 9555,
"input": 257397,
"model": "NVIDIA/NVIDIA-Nemotron-3-Super-120B-A12B"
},
{
"cost_chf": 16.6957,
"output": 120992,
"input": 2734180,
"model": "openai/gpt-oss-120b"
}
],
"total_cost_chf": 17.261556
}
</syntaxhighlight>

[[Category: AI on Demand]]

Category:AI on Demand

2026-10-18T09:39:30Z

Sst-mei: /* Overview */

= Overview =
This category collects all AI on Demand related pages.

stepping stone AG is proud to serve customers with current language models and OCR solutions.

All of our LLM services are reachable via the OpenAI compatible gateway at https://llm.stoney-cloud.com/.

Check out the [[AI on Demand: Usage]] page. You can list the models, show your own usage information, etc.

[[Category: Artificial Intelligence]]

AI on demand: apertus-ai/Apertus-v1.5-8B

2026-10-18T09:38:17Z

Sst-mei:

== Calling the model ==
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# Set the desired model:
MODEL=apertus-ai/Apertus-v1.5-8B

# Set your prompt:
PROMPT='Hello.'

# Set maximum amount of tokens:
MAX_TOKENS=100

curl https://llm.stoney-cloud.com/v1/chat/completions \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
--header 'Content-Type: application/json' \
--data '{
"model": "'"$MODEL"'",
"messages": [
{"role": "user", "content": "'"$PROMPT"'"}
],
"max_tokens": '"$MAX_TOKENS"'
}' \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang="json">
{
"id": "chatcmpl-a8967d004bbaff14",
"object": "chat.completion",
"created": 1785332362,
"model": "apertus-ai/Apertus-v1.5-8B",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Hello! How can I help you today?",
"refusal": null,
"annotations": null,
"audio": null,
"function_call": null,
"reasoning": null
},
"logprobs": null,
"finish_reason": "stop",
"stop_reason": 68,
"token_ids": null,
"routed_experts": null
}
],
"service_tier": null,
"system_fingerprint": "vllm-0.23.1rc1.dev1029+ga601a9d99-99d7c206",
"usage": {
"prompt_tokens": 64,
"total_tokens": 74,
"completion_tokens": 10,
"prompt_tokens_details": null
},
"prompt_logprobs": null,
"prompt_token_ids": null,
"prompt_text": null,
"kv_transfer_params": null,
"metrics": null
}
</syntaxhighlight>

[[Category: AI on Demand]]
[[Category: General purpose models]]

AI on demand: zai-org/GLM-5.3-Flash

2026-10-18T09:38:04Z

Sst-mei:

== Calling the model ==
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# Set the desired model:
MODEL=zai-org/GLM-5.3-Flash

# Set your prompt:
PROMPT='Hello.'

# Set maximum amount of tokens:
MAX_TOKENS=1000

curl https://llm.stoney-cloud.com/v1/chat/completions \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
--header 'Content-Type: application/json' \
--data '{
"model": "'"$MODEL"'",
"messages": [
{"role": "user", "content": "'"$PROMPT"'"}
],
"max_tokens": '"$MAX_TOKENS"'
}' \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang="json">
{
"id": "chatcmpl-b823aeb93ca47bab",
"object": "chat.completion",
"created": 1789132434,
"model": "zai-org/GLM-5.3-Flash",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Hello! I'm GLM, a large language model trained by Z.ai. Nice to meet you, and I hope you're having a great day.\n\nDo you have any questions or topics of interest I can help you with? Whether it's a knowledge inquiry, creative writing, or everyday conversation, I'm happy to provide assistance.",
"refusal": null,
"annotations": null,
"audio": null,
"function_call": null,
"reasoning": "Let me consider how to respond to this greeting appropriately.\n\nThe user has initiated the conversation with a simple \"Hello,\" which calls for a warm and professional response. Since this is the beginning of our interaction, it's important to create a welcoming atmosphere that encourages open communication. I should acknowledge their greeting in a friendly way and express my readiness to assist them with any questions or concerns they might have.\n\nI need to craft a response that not only reciprocates the greeting but also clearly communicates my purpose as an AI assistant designed to be helpful, informative, and supportive. This will help set the right tone for our conversation and make the user feel comfortable sharing what they need help with.\n\nThe response should be concise yet inviting, leaving room for the user to specify their needs or questions without feeling overwhelmed by too much information at once."
},
"logprobs": null,
"finish_reason": "stop",
"stop_reason": 154827,
"token_ids": null,
"routed_experts": null
}
],
"service_tier": null,
"system_fingerprint": "vllm-0.28.1rc1.dev400+g8b6de0eb9-tp2-dp4-6f5a0747",
"usage": {
"prompt_tokens": 14,
"total_tokens": 248,
"completion_tokens": 234,
"prompt_tokens_details": null,
"completion_tokens_details": {
"reasoning_tokens": 165
}
},
"prompt_logprobs": null,
"prompt_token_ids": null,
"prompt_text": null,
"kv_transfer_params": null,
"ec_transfer_params": null,
"metrics": null
}
</syntaxhighlight>

[[Category: AI on Demand]]
[[Category: General purpose models]]

AI on demand: Qwen/Qwen3.8-27B

2026-10-18T09:37:56Z

Sst-mei:

== Calling the model ==
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# Set the desired model:
MODEL=Qwen/Qwen3.8-27B

# Set your prompt:
PROMPT='Hello.'

# Set maximum amount of tokens:
MAX_TOKENS=1000

curl https://llm.stoney-cloud.com/v1/chat/completions \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
--header 'Content-Type: application/json' \
--data '{
"model": "'"$MODEL"'",
"messages": [
{"role": "user", "content": "'"$PROMPT"'"}
],
"max_tokens": '"$MAX_TOKENS"'
}' \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang="json">
{
"id": "chatcmpl-b6f3d4c505290b86",
"object": "chat.completion",
"created": 1789131925,
"model": "Qwen/Qwen3.8-27B",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "\n\nHello! How are you doing? Is there something I can help you with today?",
"refusal": null,
"annotations": null,
"audio": null,
"function_call": null,
"reasoning": "The user said \"Hello.\" This is a simple greeting. I should respond warmly and naturally, keeping it brief and open-ended to invite further conversation.\n"
},
"logprobs": null,
"finish_reason": "stop",
"stop_reason": null,
"token_ids": null,
"routed_experts": null
}
],
"service_tier": null,
"system_fingerprint": "vllm-0.28.0-tp4-63f8683f",
"usage": {
"prompt_tokens": 54,
"total_tokens": 105,
"completion_tokens": 51,
"prompt_tokens_details": null,
"completion_tokens_details": {
"reasoning_tokens": 31
}
},
"prompt_logprobs": null,
"prompt_token_ids": null,
"prompt_text": null,
"kv_transfer_params": null,
"ec_transfer_params": null,
"metrics": null
}
</syntaxhighlight>

[[Category: AI on Demand]]
[[Category: General purpose models]]

AI on demand: Qwen/Qwen3-Coder-Next

2026-10-18T09:37:39Z

Sst-mei:

== Calling the model ==
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# Set the desired model:
MODEL=Qwen/Qwen3-Coder-Next

# Set your prompt:
PROMPT='Hello.'

# Set maximum amount of tokens:
MAX_TOKENS=100

curl https://llm.stoney-cloud.com/v1/chat/completions \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
--header 'Content-Type: application/json' \
--data '{
"model": "'"$MODEL"'",
"messages": [
{"role": "user", "content": "'"$PROMPT"'"}
],
"max_tokens": '"$MAX_TOKENS"'
}' \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang="json">
{
"id": "chatcmpl-bb307cafee7eb3bd",
"object": "chat.completion",
"created": 1778156615,
"model": "Qwen/Qwen3-Coder-Next",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Hi there! How can I help you today? 😊",
"refusal": null,
"annotations": null,
"audio": null,
"function_call": null,
"tool_calls": [],
"reasoning": null
},
"logprobs": null,
"finish_reason": "stop",
"stop_reason": null,
"token_ids": null
}
],
"service_tier": null,
"system_fingerprint": null,
"usage": {
"prompt_tokens": 10,
"total_tokens": 23,
"completion_tokens": 13,
"prompt_tokens_details": null
},
"prompt_logprobs": null,
"prompt_token_ids": null,
"kv_transfer_params": null
}
</syntaxhighlight>

[[Category: AI on Demand]]
[[Category: General purpose models]]

AI on demand: opendatalab/MinerU2.5-2509-1.2B

2026-10-18T09:37:27Z

Sst-mei:

== Calling the model ==
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# Set the desired model:
MODEL=opendatalab/MinerU2.5-2509-1.2B

# Set the desired document to run OCR against:
FILE_PATH=document.png

# Encode document contents with Base64 and detect MIME type:
FILE_CONTENT_BASE64=$(base64 -w 0 < "$FILE_PATH")
FILE_MIME_TYPE=$(file --brief --mime-type "$FILE_PATH")

curl https://llm.stoney-cloud.com/v1/chat/completions \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
--header 'Content-Type: application/json' \
--data '{
"model": "'"$MODEL"'",
"messages": [{
"role": "user",
"content": [{
"type": "image_url",
"image_url": {
"url": "data:'"$FILE_MIME_TYPE"';base64,'"$FILE_CONTENT_BASE64"'"
}
}]
}],
"max_tokens": 4096,
"temperature": 0.2,
"top_p": 0.9
}' \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang="json">
{
"id": "chatcmpl-834171fda5956922",
"object": "chat.completion",
"created": 1788347006,
"model": "opendatalab/MinerU2.5-2509-1.2B",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "This is a lot of 12 point text to test theOCR code and see if it works on all types of file format. The quick brown dog jumped over the lazy fox. The quick brown dog jumped over the lazy fox. The quick brown dog jumped over the lazy fox. The quick brown dog jumped over the lazy fox.",
"refusal": null,
"annotations": null,
"audio": null,
"function_call": null,
"tool_calls": [],
"reasoning": null,
"reasoning_content": null
},
"logprobs": null,
"finish_reason": "stop",
"stop_reason": null,
"token_ids": null
}
],
"service_tier": null,
"system_fingerprint": null,
"usage": {
"prompt_tokens": 412,
"total_tokens": 480,
"completion_tokens": 68,
"prompt_tokens_details": null
},
"prompt_logprobs": null,
"prompt_token_ids": null,
"kv_transfer_params": null
}
</syntaxhighlight>

[[Category: AI on Demand]]
[[Category: General purpose models]]

AI on demand: openai/gpt-oss-120b

2026-10-18T09:37:13Z

Sst-mei:

== Calling the model ==
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# Set the desired model:
MODEL=openai/gpt-oss-120b

# Set your prompt:
PROMPT='Hello.'

# Set maximum amount of tokens:
MAX_TOKENS=100

curl https://llm.stoney-cloud.com/v1/chat/completions \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
--header 'Content-Type: application/json' \
--data '{
"model": "'"$MODEL"'",
"messages": [
{"role": "user", "content": "'"$PROMPT"'"}
],
"max_tokens": '"$MAX_TOKENS"'
}' \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang="json">
{
"id": "chatcmpl-a7415d610c007432",
"object": "chat.completion",
"created": 1788358983,
"model": "openai/gpt-oss-120b",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Hello! 👋 How can I help you today?",
"refusal": null,
"annotations": null,
"audio": null,
"function_call": null,
"reasoning": "User just says \"Hello.\" Likely expecting a greeting. So respond friendly and ask how can help."
},
"logprobs": null,
"finish_reason": "stop",
"stop_reason": null,
"token_ids": null,
"routed_experts": null
}
],
"service_tier": null,
"system_fingerprint": "vllm-0.27.1-tp8-2c775da9",
"usage": {
"prompt_tokens": 69,
"total_tokens": 111,
"completion_tokens": 42,
"prompt_tokens_details": null
},
"prompt_logprobs": null,
"prompt_token_ids": null,
"prompt_text": null,
"kv_transfer_params": null,
"ec_transfer_params": null,
"metrics": null
}
</syntaxhighlight>

[[Category: AI on Demand]]
[[Category: General purpose models]]

AI on demand: NVIDIA/NVIDIA-Nemotron-3-Super-120B-A12B

2026-10-18T09:36:57Z

Sst-mei:

== Calling the model ==
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# Set the desired model:
MODEL=NVIDIA/NVIDIA-Nemotron-3-Super-120B-A12B

# Set your prompt:
PROMPT='Hello.'

# Set maximum amount of tokens:
MAX_TOKENS=100

curl https://llm.stoney-cloud.com/v1/chat/completions \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
--header 'Content-Type: application/json' \
--data '{
"model": "'"$MODEL"'",
"messages": [
{"role": "user", "content": "'"$PROMPT"'"}
],
"max_tokens": '"$MAX_TOKENS"'
}' \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang="json">
{
"id": "chatcmpl-af98aba2443fdd6f",
"object": "chat.completion",
"created": 1778156848,
"model": "NVIDIA/NVIDIA-Nemotron-3-Super-120B-A12B",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "\n\nHello! How can I assist you today?",
"refusal": null,
"annotations": null,
"audio": null,
"function_call": null,
"tool_calls": [],
"reasoning": "We need to respond with a friendly greeting. No special instructions.\n\n"
},
"logprobs": null,
"finish_reason": "stop",
"stop_reason": null,
"token_ids": null
}
],
"service_tier": null,
"system_fingerprint": null,
"usage": {
"prompt_tokens": 18,
"total_tokens": 43,
"completion_tokens": 25,
"prompt_tokens_details": null
},
"prompt_logprobs": null,
"prompt_token_ids": null,
"kv_transfer_params": null
}
</syntaxhighlight>

[[Category: AI on Demand]]
[[Category: General purpose models]]

AI on demand: MiniMaxAI/MiniMax-M2.5

2026-10-18T09:36:48Z

Sst-mei:

== Calling the model ==
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# Set the desired model:
MODEL=MiniMaxAI/MiniMax-M2.5

# Set your prompt:
PROMPT='Hello.'

# Set maximum amount of tokens:
MAX_TOKENS=100

curl https://llm.stoney-cloud.com/v1/chat/completions \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
--header 'Content-Type: application/json' \
--data '{
"model": "'"$MODEL"'",
"messages": [
{"role": "user", "content": "'"$PROMPT"'"}
],
"max_tokens": '"$MAX_TOKENS"'
}' \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang="json">
{
"id": "chatcmpl-9f55d44ee87ed4e7",
"object": "chat.completion",
"created": 1775141698,
"model": "MiniMaxAI/MiniMax-M2.5",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "<think>The user has simply greeted me with \"Hello.\" This is a simple greeting, so I should respond in a friendly and welcoming manner.\n</think>\n\nHello! How can I help you today?",
"refusal": null,
"annotations": null,
"audio": null,
"function_call": null,
"tool_calls": [],
"reasoning": null
},
"logprobs": null,
"finish_reason": "stop",
"stop_reason": null,
"token_ids": null
}
],
"service_tier": null,
"system_fingerprint": null,
"usage": {
"prompt_tokens": 41,
"total_tokens": 80,
"completion_tokens": 39,
"prompt_tokens_details": null
},
"prompt_logprobs": null,
"prompt_token_ids": null,
"kv_transfer_params": null
}
</syntaxhighlight>

[[Category: AI on Demand]]
[[Category: General purpose models]]

AI on demand: google/gemma-4-31B-it

2026-10-18T09:36:37Z

Sst-mei:

== Calling the model ==
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# Set the desired model:
MODEL=google/gemma-4-31B-it

# Set your prompt:
PROMPT='Hello.'

# Set maximum amount of tokens:
MAX_TOKENS=1000

curl https://llm.stoney-cloud.com/v1/chat/completions \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
--header 'Content-Type: application/json' \
--data '{
"model": "'"$MODEL"'",
"messages": [
{"role": "user", "content": "'"$PROMPT"'"}
],
"max_tokens": '"$MAX_TOKENS"'
}' \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang="json">
{
"id": "chatcmpl-b0f2f7e9a94d7216",
"object": "chat.completion",
"created": 1789132182,
"model": "google/gemma-4-31B-it",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Hello! How can I help you today?",
"refusal": null,
"annotations": null,
"audio": null,
"function_call": null,
"reasoning": null
},
"logprobs": null,
"finish_reason": "stop",
"stop_reason": 106,
"token_ids": null,
"routed_experts": null
}
],
"service_tier": null,
"system_fingerprint": "vllm-0.28.0-4f0e9c70",
"usage": {
"prompt_tokens": 15,
"total_tokens": 25,
"completion_tokens": 10,
"prompt_tokens_details": null,
"completion_tokens_details": {
"reasoning_tokens": 0
}
},
"prompt_logprobs": null,
"prompt_token_ids": null,
"prompt_text": null,
"kv_transfer_params": null,
"ec_transfer_params": null,
"metrics": null
}
</syntaxhighlight>

[[Category: AI on Demand]]
[[Category: General purpose models]]

AI on demand: deepseek-ai/DeepSeek-V4-Flash-0731

2026-10-18T09:36:25Z

Sst-mei:

== Calling the model ==
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# Set the desired model:
MODEL=deepseek-ai/DeepSeek-V4-Flash-0731

# Set your prompt:
PROMPT='Hello.'

# Set maximum amount of tokens:
MAX_TOKENS=100

curl https://llm.stoney-cloud.com/v1/chat/completions \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
--header 'Content-Type: application/json' \
--data '{
"model": "'"$MODEL"'",
"messages": [
{"role": "user", "content": "'"$PROMPT"'"}
],
"max_tokens": '"$MAX_TOKENS"'
}' \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang="json">
{
"id": "chatcmpl-a0642a07d24aba3c",
"object": "chat.completion",
"created": 1788358946,
"model": "deepseek-ai/DeepSeek-V4-Flash-0731",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Hello! How can I help you today?",
"refusal": null,
"annotations": null,
"audio": null,
"function_call": null,
"reasoning": "We need answer hello. Need maybe provide greeting. Simple."
},
"logprobs": null,
"finish_reason": "stop",
"stop_reason": null,
"token_ids": null,
"routed_experts": null
}
],
"service_tier": null,
"system_fingerprint": "vllm-0.26.1rc0+infernal.invocation.r2.vllm344438d.b12x1584743.fi1ac6942.cu132.20260812-tp4-27dc2d1f",
"usage": {
"prompt_tokens": 85,
"total_tokens": 108,
"completion_tokens": 23,
"prompt_tokens_details": {
"cached_tokens": 0,
"created_cache_tokens": 0,
"multimodal_tokens": null
}
},
"prompt_logprobs": null,
"prompt_token_ids": null,
"prompt_text": null,
"kv_transfer_params": null,
"ec_transfer_params": null,
"metrics": null
}
</syntaxhighlight>

[[Category: AI on Demand]]
[[Category: General purpose models]]

AI on demand: Qwen/Qwen3.5-35B-A3B-FP8

2026-10-18T09:36:15Z

Sst-mei:

== Calling the model ==
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# Set the desired model:
MODEL=Qwen/Qwen3.5-35B-A3B-FP8

# Set your prompt:
PROMPT='Hello.'

# Set maximum amount of tokens:
MAX_TOKENS=10000

curl https://llm.stoney-cloud.com/v1/chat/completions \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
--header 'Content-Type: application/json' \
--data '{
"model": "'"$MODEL"'",
"messages": [
{"role": "user", "content": "'"$PROMPT"'"}
],
"max_tokens": '"$MAX_TOKENS"'
}' \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang="json">
{
"id": "chatcmpl-a48b0edd8e8a0153",
"object": "chat.completion",
"created": 1788340157,
"model": "Qwen/Qwen3.5-35B-A3B-FP8",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "\n\nHello! How are you doing today? Is there anything I can help you with? I'd be happy to assist you with something you need.",
"refusal": null,
"annotations": null,
"audio": null,
"function_call": null,
"tool_calls": [],
"reasoning": "Thinking Process:\n\n1. **Analyze the Input:**\n * Input: \"Hello.\"\n * Type: Greeting.\n * Intent: Initiating a conversation.\n * Tone: Polite, neutral.\n\n2. **Determine the Appropriate Response:**\n * Acknowledge the greeting, offer assistance, and maintain a friendly tone.\n\n3. **Drafting Responses:**\n * * Option 1 (Simple): Hello! How can I help you?\n * Option 2 (Friendly): Hi there! Hope you're having a good day. What's on your mind?\n * Option 3. **Option 3 (Professional): Hello. How may I assist you today?\n\n4. **Selecting the Best Option:**\n Option 2 strikes a good balance of friendliness and helpfulness for a general assistant persona.\n\n5. **Final Polish:** \"Hello! How can I help you today be? I'm here to assist with whatever you need.\" (Wait, \"How can today be\" is slightly odd. Let's stick to standard.)\n \"Hello! How are you doing well? What can I help you with?\"\n\n6. **Refining for Conciseness:** \"Hello! How can I assist you with anything today?\"\n\n7. **Final Choice:** \"Hello! How are you doing today? Is there something I can help you with?\"\n\n \" (Wait, English correction: \"How are you?\" + \"How can I help you?\")\n\n *Revised:* \"Hello! How are you doing? Is there anything I can assist you with today?\" -> \"Hello! How are you doing? Is there something I can help you with today?\"\n\n *Let's keep it warm and open.* \"Hello! How's there something you'd like to chat about or work on?\"\n\n *Actually, keep it simple.* \"Hello! How are you doing today? How can I assist you?\"\n\n *Wait, the model should just be natural.*\n\n \"Hello! How's it going? Is there something I can help you with today?\"\n\n8\"\n\n *Okay, let's go with a standard friendly greeting.*\n\n \"Hello! How are you doing today? Is there anything I can help you with?\"\n\n *Wait, check the system instructions for tone.* No specific constraints. Be helpful.\n\n *Final Plan:* Greet back warmly and offer help.\n\n *Draft: \"Hello! How are you doing today? Is there anything I can help you with?\"\n\n *Wait, let's make it slightly more engaging.* \"Hello there! How's your day going? Feel free to ask me anything you need.cw\n"
},
"logprobs": null,
"finish_reason": "stop",
"stop_reason": null,
"token_ids": null
}
],
"service_tier": null,
"system_fingerprint": null,
"usage": {
"prompt_tokens": 12,
"total_tokens": 631,
"completion_tokens": 619,
"prompt_tokens_details": null
},
"prompt_logprobs": null,
"prompt_token_ids": null,
"kv_transfer_params": null
}
</syntaxhighlight>

[[Category: AI on Demand]]
[[Category: General purpose models]]

AI on demand: Qwen/Qwen3.5-35B-A3B-FP8

2026-10-18T09:36:03Z

Sst-mei:

AI on demand: Qwen/Qwen3-Coder-Next

2026-10-18T09:35:53Z

Sst-mei:

AI on demand: opendatalab/MinerU2.5-2509-1.2B

2026-10-18T09:35:45Z

Sst-mei:

AI on demand: openai/gpt-oss-120b

2026-10-18T09:35:35Z

Sst-mei:

AI on demand: NVIDIA/NVIDIA-Nemotron-3-Super-120B-A12B

2026-10-18T09:35:22Z

Sst-mei:

AI on demand: MiniMaxAI/MiniMax-M2.5

2026-10-18T09:35:13Z

Sst-mei:

AI on demand: google/gemma-4-31B-it

2026-10-18T09:35:02Z

Sst-mei:

AI on demand: deepseek-ai/DeepSeek-V4-Flash-0731

2026-10-18T09:34:54Z

Sst-mei: /* Calling the model */

AI on demand: apertus-ai/Apertus-v1.5-8B

2026-10-18T09:34:21Z

Sst-mei: /* Calling the model */

AI on demand: BAAI/bge-reranker-v2-m3

2026-10-18T09:33:17Z

Sst-mei:

== Calling the model ==
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# Set the desired model:
MODEL=BAAI/bge-reranker-v2-m3

curl https://llm.stoney-cloud.com/v1/rerank \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
--header 'Content-Type: application/json' \
--data '{
"model": "'"$MODEL"'",
"query": "Which Swiss ski resorts are best for beginners?",
"documents": [
"Zermatt offers challenging slopes and views of the Matterhorn.",
"Grindelwald has beginner-friendly slopes and good ski schools.",
"St. Moritz is known for luxury skiing and advanced runs.",
"Arosa provides gentle slopes ideal for beginners and families."
]
}' \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang="json">
{
"id": "score-b22e866ab7c49d40",
"model": "BAAI/bge-reranker-v2-m3",
"usage": {
"prompt_tokens": 119,
"total_tokens": 119
},
"results": [
{
"index": 1,
"document": {
"text": "Grindelwald has beginner-friendly slopes and good ski schools.",
"multi_modal": null
},
"relevance_score": 0.319301038980484
},
{
"index": 3,
"document": {
"text": "Arosa provides gentle slopes ideal for beginners and families.",
"multi_modal": null
},
"relevance_score": 0.050355106592178345
},
{
"index": 2,
"document": {
"text": "St. Moritz is known for luxury skiing and advanced runs.",
"multi_modal": null
},
"relevance_score": 0.01756473444402218
},
{
"index": 0,
"document": {
"text": "Zermatt offers challenging slopes and views of the Matterhorn.",
"multi_modal": null
},
"relevance_score": 0.013464285060763359
}
]
}
</syntaxhighlight>

[[Category: AI on Demand]]
[[Category: Reranking models]]

AI on demand: BAAI/bge-m3

2026-10-18T09:32:42Z

Sst-mei:

== Calling the model ==
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# Set the desired model:
MODEL=BAAI/bge-m3

curl https://llm.stoney-cloud.com/v1/embeddings \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
--header 'Content-Type: application/json' \
--data '{
"model": "BAAI/bge-m3",
"input": "The quick brown fox jumps over the lazy dog"
}' \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang="json">
{
"id": "embd-ab86614d2cd57a79",
"object": "list",
"created": 1778147167,
"model": "BAAI/bge-m3",
"data": [
{
"index": 0,
"object": "embedding",
"embedding": [
-0.02912014164030552,
0.027682997286319733,
-0.04915034398436546,
0.002660962985828519,
-0.01616787724196911,
0.009036046452820301,
0.02346138469874859,
-0.038587331771850586,
-0.024305706843733788,
-0.05209648981690407,
-0.019904451444745064,
-0.009736654348671436,
-0.012206746265292168,
-0.0041632279753685,
0.025275779888033867,
-0.01667087711393833,
0.020964346826076508,
-0.031832750886678696,
-0.0221859198063612,
-0.01094026304781437,
-0.02541949413716793,
-0.008407295681536198,
0.03740168735384941,
0.034024398773908615,
-0.020569130778312683,
0.028311748057603836,
0.0475335568189621,
-0.008106393739581108,
-0.0006882575107738376,
0.06093493103981018,
-0.0075270445086061954,
-0.022778742015361786,
-0.04300655052065849,
-0.06255171447992325,
-0.01830562949180603,
-0.06750986725091934,
-0.006574936211109161,
0.0028900078032165766,
-0.03729390352964401,
-0.03296450525522232,
0.01276363991200924,
0.012970229610800743,
0.013311551883816719,
-0.0010329476790502667,
0.01812598668038845,
-0.011371406726539135,
0.022958384826779366,
-0.01322173047810793,
-0.014263659715652466,
-0.036826830357313156,
-0.01374269463121891,
0.027215925976634026,
0.008515081368386745,
0.026838675141334534,
0.02651531808078289,
-0.009431261569261551,
0.02518595941364765,
-0.011281585320830345,
-0.013904374092817307,
-0.029587214812636375,
-0.01404808834195137,
0.04609641060233116,
0.0022590116132050753,
-0.008079446852207184,
-0.047641344368457794,
0.1104445606470108,
-0.00530396169051528,
-0.031473465263843536,
-0.007109374739229679,
0.003419955028221011,
0.004675210919231176,
-0.015476251021027565,
-0.028653070330619812,
-0.025670994073152542,
-0.01684153825044632,
0.028922533616423607,
0.03240761160850525,
-0.02850935608148575,
0.010347440838813782,
0.04943777248263359,
0.07465966045856476,
0.009018082171678543,
-0.05744985491037369,
0.0004429324471857399,
0.00833094771951437,
0.04918627440929413,
0.0054297116585075855,
-0.033054325729608536,
0.015018160454928875,
0.03571304306387901,
-0.0014079526299610734,
0.013688801787793636,
0.009000117890536785,
-0.020353559404611588,
-0.006907275877892971,
-0.02353324182331562,
0.0037118750624358654,
0.024395529180765152,
-0.02881474792957306,
-0.022167954593896866,
0.004174456000328064,
0.031024359166622162,
-0.006440204102545977,
-0.05152163282036781,
0.000004464761786948657,
-0.010958227328956127,
0.016194822266697884,
0.007127339020371437,
-0.02304820530116558,
-0.010392352007329464,
0.058455854654312134,
0.025078173726797104,
-0.014569053426384926,
0.016643930226564407,
-0.009440243244171143,
-0.05180906131863594,
-0.014344499446451664,
-0.02019188180565834,
0.014191802591085434,
-0.0011059276293963194,
0.030359679833054543,
0.03883883357048035,
0.08048009872436523,
-0.03095250204205513,
0.02712610363960266,
-0.05400070920586586,
0.010913316160440445,
-0.009089939296245575,
0.0003778118407353759,
0.08141423761844635,
0.011066013015806675,
0.004015022423118353,
0.02504224330186844,
-0.0442640520632267,
-0.04315026476979256,
-0.00979054719209671,
0.004473112523555756,
0.029695000499486923,
0.03497650474309921,
0.00037556630559265614,
0.059138499200344086,
0.0284554623067379,
0.006022533867508173,
-0.047030556946992874,
0.027108140289783478,
-0.08615681529045105,
0.0585995689034462,
-0.0412101224064827,
0.01009594090282917,
-0.015305589884519577,
-0.0679769366979599,
-0.01848527230322361,
-0.013841498643159866,
-0.02098231017589569,
-0.017227770760655403,
-0.018808629363775253,
0.002696891548112035,
0.04462333768606186,
-0.0004965447005815804,
0.03574896976351738,
0.021072132512927055,
-0.019563131034374237,
-0.006215650122612715,
-0.024108100682497025,
0.004733595065772533,
-0.0032201020512729883,
0.002182663418352604,
0.016985252499580383,
0.0036534909158945084,
-0.02741353213787079,
-0.03167107328772545,
-0.0867316722869873,
0.01861102133989334,
-0.014182820916175842,
0.0330902524292469,
-0.0023353600408881903,
0.023551207035779953,
0.00909443013370037,
-0.0017616248223930597,
-0.023012276738882065,
-0.013545087538659573,
-0.0035322317853569984,
-0.0057889982126653194,
-0.021449383348226547,
0.0055509707890450954,
-0.02299431338906288,
0.021126024425029755,
0.008375857956707478,
-0.003570405999198556,
0.008892332203686237,
-0.018934380263090134,
0.01792837865650654,
-0.012610943987965584,
-0.03064710833132267,
-0.013832516968250275,
-0.03959333151578903,
0.010113905183970928,
-0.07523451745510101,
0.01952720247209072,
-0.003161718137562275,
0.0011306286323815584,
0.024916494265198708,
0.02664106711745262,
-0.03865918889641762,
-0.015880446881055832,
-0.020533202216029167,
-0.03362918272614479,
-0.050192274153232574,
0.022724848240613937,
0.024611100554466248,
0.023982349783182144,
0.041749048978090286,
0.04322212189435959,
-0.06571343541145325,
-0.006907275877892971,
0.0022421700414270163,
0.010230672545731068,
-0.0014472495531663299,
0.011883389204740524,
-0.023371564224362373,
0.03159921616315842,
0.01636548340320587,
0.016311591491103172,
0.02656920999288559,
0.07110273092985153,
-0.005021024029701948,
0.010679780505597591,
0.043078407645225525,
-0.03052135743200779,
-0.03251539543271065,
-0.00811986718326807,
-0.007455187384039164,
-0.0252937451004982,
0.019724808633327484,
0.019437380135059357,
0.008757599629461765,
-0.012862443923950195,
0.04455148056149483,
0.041138261556625366,
0.04990484565496445,
-0.021970348432660103,
0.010967209935188293,
0.012143871746957302,
-0.0034087272360920906,
0.02931774966418743,
-0.016185840591788292,
0.015485232695937157,
-0.02822192572057247,
0.023263778537511826,
0.04261133819818497,
-0.021431418135762215,
-0.05155756324529648,
-0.020407453179359436,
-0.01553912553936243,
-0.010958227328956127,
0.03632383048534393,
-0.0041632279753685,
0.009925279766321182,
0.037545401602983475,
0.0012889390345662832,
0.013598980382084846,
0.04613234102725983,
0.0170211810618639,
0.041497550904750824,
-0.0601804293692112,
-0.007486625108867884,
0.010724691674113274,
0.028078211471438408,
0.0027081193402409554,
0.008151303976774216,
-0.0197068452835083,
-0.009332457557320595,
-0.035892684012651443,
0.012368425726890564,
0.045880839228630066,
0.052383918315172195,
0.0098803685978055,
0.002485811011865735,
0.05173720419406891,
-0.02565303072333336,
-0.011892370879650116,
0.0292997844517231,
0.0056093549355864525,
0.015233732759952545,
-0.00010259303235216066,
-0.0026901550590991974,
-0.012440282851457596,
0.03840768709778786,
-0.015287625603377819,
-0.049653343856334686,
-0.00685787433758378,
-0.046311985701322556,
0.029102178290486336,
-0.027862640097737312,
0.0538569912314415,
-0.042898766696453094,
-0.011667817831039429,
-0.11921114474534988,
0.03258725255727768,
0.005528515670448542,
-0.026479389518499374,
0.009107903577387333,
-0.021251775324344635,
0.018314611166715622,
-0.012242675758898258,
0.04422812536358833,
-0.045449696481227875,
-0.03732983022928238,
-0.03847954422235489,
-0.0007668513571843505,
-0.015584036707878113,
0.07002487033605576,
0.050264131277799606,
0.01453312486410141,
-0.0522761344909668,
-0.002461110008880496,
-0.02249131165444851,
-0.06036007031798363,
0.05583306774497032,
0.043868839740753174,
-0.05012041702866554,
-0.019742773845791817,
-0.035784900188446045,
-0.033898647874593735,
-0.05065934732556343,
-0.02687460370361805,
0.010194743983447552,
-0.021431418135762215,
-0.014937321655452251,
-0.010140851140022278,
-0.0009420033311471343,
0.010616905987262726,
0.06474336236715317,
-0.03357528895139694,
-0.08335438370704651,
-0.010257619433104992,
0.015000196173787117,
0.04458741098642349,
0.08903110772371292,
-0.015476251021027565,
0.028724927455186844,
-0.011784585192799568,
-0.07861180603504181,
-0.02991057187318802,
0.004863836336880922,
-0.0018402186688035727,
-0.007410276681184769,
-0.014281623996794224,
0.02195238322019577,
0.0443718396127224,
-0.015063071623444557,
-0.00740129454061389,
0.03873104602098465,
-0.01592535898089409,
-0.02651531808078289,
-0.03370103985071182,
0.052383918315172195,
0.01677866280078888,
0.02912014164030552,
0.01811700314283371,
0.01733555644750595,
-0.021323632448911667,
0.037725046277046204,
-0.03003632090985775,
-0.06682722270488739,
0.05249170586466789,
-0.012485193088650703,
-0.003828642889857292,
-0.03546154126524925,
0.008824965916574001,
0.015979250892996788,
0.04659941419959068,
0.019617022946476936,
0.0634499341249466,
-0.0054880958050489426,
-0.0427909791469574,
-0.07473152130842209,
0.03497650474309921,
-0.0004117756034247577,
0.006435713265091181,
0.0013742694864049554,
-0.021305669099092484,
-0.016625966876745224,
0.01950923725962639,
0.011119905859231949,
0.0316171795129776,
0.1971762329339981,
0.024718886241316795,
-0.0221859198063612,
0.046419769525527954,
-0.012952265329658985,
-0.009916297160089016,
0.04523412510752678,
0.0005928221507929265,
-0.01579960808157921,
-0.01027558371424675,
-0.0221859198063612,
-0.0005425782292149961,
0.022347597405314445,
-0.004890782758593559,
-0.04839584231376648,
0.04214426502585411,
-0.02475481480360031,
0.013455266132950783,
0.04063526168465614,
-0.06959372758865356,
0.02827581949532032,
0.010985174216330051,
-0.02967703528702259,
0.038766976445913315,
-0.045808982104063034,
-0.07200094312429428,
0.03944961726665497,
0.05892292782664299,
-0.03276689723134041,
-0.03580286353826523,
-0.018646951764822006,
-0.0362519733607769,
-0.022293705493211746,
0.029030321165919304,
0.03452739864587784,
0.014110962860286236,
0.008654304780066013,
0.006327927112579346,
-0.01684153825044632,
-0.013922338373959064,
-0.010778584517538548,
-0.013437301851809025,
-0.04315026476979256,
-0.022832633927464485,
0.024179957807064056,
-0.023856600746512413,
-0.024359600618481636,
0.0024633556604385376,
-0.03569507971405983,
-0.05338992178440094,
-0.020587095990777016,
0.02832971327006817,
-0.01909605786204338,
0.011380388401448727,
0.010895351879298687,
0.016149912029504776,
-0.03826397284865379,
-0.048611413687467575,
-0.017730770632624626,
0.019257737323641777,
-0.046419769525527954,
0.05630013719201088,
-0.05267134681344032,
-0.023874564096331596,
-0.03549747169017792,
0.026784781366586685,
-0.029389606788754463,
0.003579388139769435,
-0.02042541652917862,
-0.0034513925202190876,
0.006754579488188028,
0.024341635406017303,
-0.012143871746957302,
-0.01553912553936243,
0.005375818815082312,
-0.005950676742941141,
0.0077381255105137825,
0.031221965327858925,
0.07034822553396225,
0.031060287728905678,
-0.004854854196310043,
-0.04124604910612106,
-0.06000078469514847,
-0.02626381628215313,
0.02552727982401848,
0.041102334856987,
0.0019075848395004869,
0.06700686365365982,
-0.029102178290486336,
0.016347520053386688,
0.011847460642457008,
0.024090135470032692,
-0.06194093078374863,
-0.006233614403754473,
-0.04738984256982803,
0.0015381937846541405,
0.010985174216330051,
-0.025455422699451447,
-0.01623973436653614,
0.023623064160346985,
0.01100313849747181,
0.0005105792661197484,
0.026299744844436646,
-0.013491194695234299,
0.07739023864269257,
-0.014335516840219498,
-0.03028782270848751,
0.05946185812354088,
-0.0079042948782444,
-0.018395449966192245,
0.06477928906679153,
-0.024161992594599724,
-0.035731006413698196,
-0.06600086390972137,
0.010509119369089603,
0.015170857310295105,
0.01042828056961298,
-0.000521807000041008,
0.024359600618481636,
0.02200627699494362,
0.025329673662781715,
0.016652911901474,
-0.019652951508760452,
-0.021072132512927055,
0.005277015268802643,
-0.07537823170423508,
-0.00027844676515087485,
0.027395568788051605,
-0.007284526713192463,
-0.008892332203686237,
-0.006988115608692169,
-0.0018840066622942686,
-0.013787605799734592,
0.03375493362545967,
0.030790822580456734,
-0.014829535968601704,
0.04135383665561676,
0.0010604554554447532,
-0.002270239405333996,
0.049581486731767654,
0.008043518289923668,
-0.009049519896507263,
-0.011398352682590485,
0.039521474391222,
0.04961741715669632,
0.014829535968601704,
-0.032802823930978775,
-0.009592940099537373,
-0.03829990327358246,
-0.0130690336227417,
0.009009100496768951,
-0.0056273192167282104,
-0.02559913694858551,
-0.019419416785240173,
-0.00006048919021850452,
0.011703746393322945,
-0.035299863666296005,
-0.005955168046057224,
-0.039737045764923096,
-0.028904570266604424,
0.00976360123604536,
0.006363855674862862,
-0.013051069341599941,
0.01249417569488287,
-0.012610943987965584,
0.031042322516441345,
-0.0004002672212664038,
-0.000161257732543163,
0.01818886026740074,
-0.009431261569261551,
-0.021808668971061707,
-0.0118564423173666,
0.0031774367671459913,
-0.0046617379412055016,
-0.014452285133302212,
0.019257737323641777,
0.00685787433758378,
-0.019599059596657753,
0.04049154743552208,
0.01395826693624258,
0.007980643771588802,
0.07365366071462631,
-0.025886567309498787,
0.007684232201427221,
0.0011575750540941954,
0.0871628150343895,
-0.0134103549644351,
-0.019670916721224785,
0.022042205557227135,
-0.00013431126717478037,
-0.05306656286120415,
0.06571343541145325,
0.032623182982206345,
-0.009655815549194813,
0.02383863553404808,
0.036754973232746124,
0.0002520616981200874,
0.044479623436927795,
0.02674885280430317,
-0.05155756324529648,
0.04117419198155403,
-0.001863796846009791,
-0.04810841381549835,
0.038946617394685745,
-0.01914995163679123,
0.00976360123604536,
-0.0134103549644351,
0.009799529798328876,
0.007015062030404806,
-0.05234799161553383,
-0.03984483331441879,
-0.00408912543207407,
-0.023030241951346397,
-0.00808842945843935,
0.025455422699451447,
0.027503354474902153,
-0.0076932143419981,
-0.03869511932134628,
0.005986605305224657,
-0.03671904280781746,
0.006386311259120703,
0.014856481924653053,
0.033844754099845886,
0.005564444232732058,
-0.02973092906177044,
-0.0153864286839962,
0.018503235653042793,
-0.016087036579847336,
-0.014155874028801918,
0.0076887235045433044,
0.007095901295542717,
-0.036090292036533356,
0.020964346826076508,
0.004107089713215828,
0.003013512585312128,
0.020712846890091896,
0.0014595999382436275,
0.01480258908122778,
0.042287979274988174,
0.008083938620984554,
-0.03873104602098465,
-0.01792837865650654,
0.02358713559806347,
0.0730428695678711,
-0.006619847379624844,
-0.00016364360635634512,
0.022203883156180382,
0.006404275540262461,
0.02967703528702259,
0.008712689392268658,
-0.017236752435564995,
0.055904924869537354,
0.02141345478594303,
-0.008892332203686237,
0.006422239821404219,
-0.003727593692019582,
0.02967703528702259,
-0.04009633511304855,
0.004091370850801468,
0.004122808575630188,
-0.026982389390468597,
0.008914787322282791,
-0.01932959444820881,
0.03400643169879913,
-0.0776776671409607,
-0.07638423144817352,
0.02274281345307827,
-0.019778702408075333,
-0.02006613090634346,
-0.02967703528702259,
-0.02322784997522831,
-0.016401411965489388,
-0.016006197780370712,
-0.011577996425330639,
0.003179682418704033,
0.041749048978090286,
0.0044169737957417965,
0.0023600608110427856,
0.004985095467418432,
0.0023151501081883907,
-0.03801247477531433,
0.06542600691318512,
0.011712728068232536,
0.004345116671174765,
-0.039126262068748474,
-0.00011010155139956623,
-0.0035928613506257534,
0.03630586341023445,
-0.0012372916098684072,
-0.026048244908452034,
-0.021341597661376,
-0.03671904280781746,
-0.024305706843733788,
0.02554524503648281,
-0.010994155891239643,
-0.0057126497849822044,
-0.002449882449582219,
0.026712924242019653,
0.003922955598682165,
0.0276111401617527,
0.020209845155477524,
0.006193195004016161,
-0.011955246329307556,
0.021682918071746826,
0.008824965916574001,
0.0015134928980842233,
0.014173838309943676,
-0.02511410228908062,
0.06801286339759827,
-0.008110884577035904,
0.055976781994104385,
0.010616905987262726,
0.020515238866209984,
-0.012215728871524334,
0.018934380263090134,
-0.011613924987614155,
0.024090135470032692,
-0.04031190648674965,
0.003224593121558428,
-0.00755399139598012,
0.04760541394352913,
0.0015696313930675387,
0.010203726589679718,
0.030665071681141853,
-0.04915034398436546,
0.02771892584860325,
-0.018575092777609825,
0.04354548081755638,
-0.008160286583006382,
0.008074956014752388,
-0.012790586799383163,
-0.008470171131193638,
0.04146162047982216,
0.04713834077119827,
0.030718965455889702,
-0.03283875435590744,
0.006925240624696016,
-0.01641937717795372,
0.05453963577747345,
-0.05576121062040329,
-0.0003045511548407376,
0.051593489944934845,
0.06255171447992325,
0.0035232496447861195,
0.029227927327156067,
0.009206707589328289,
-0.010473190806806087,
-0.008932751603424549,
0.0712464451789856,
-0.007271053269505501,
0.025670994073152542,
0.028599176555871964,
-0.036934614181518555,
-0.03454536199569702,
-0.03253335878252983,
-0.04041969031095505,
0.001776220859028399,
-0.035964541137218475,
0.024664994329214096,
-0.051593489944934845,
-0.0027440479025244713,
-0.01413790974766016,
-0.03616214916110039,
0.014982231892645359,
-0.010778584517538548,
-0.0056497748009860516,
-0.01586248353123665,
-0.013482212089002132,
0.034383684396743774,
0.02991057187318802,
-0.029659071937203407,
-0.04591676965355873,
0.002580123720690608,
0.011057031340897083,
0.00040110928239300847,
0.01667087711393833,
-0.0662882924079895,
-0.08263581246137619,
-0.024485351517796516,
0.010778584517538548,
-0.039665188640356064,
-0.04713834077119827,
-0.013859462924301624,
-0.03283875435590744,
0.035551365464925766,
-0.018395449966192245,
-0.02991057187318802,
-0.003170700278133154,
0.004765032324939966,
0.011865424923598766,
-0.036036401987075806,
-0.006844400893896818,
-0.011021102778613567,
0.005860855337232351,
-0.1217261478304863,
0.007774054072797298,
0.03337768092751503,
0.022509276866912842,
-0.03003632090985775,
0.02669496089220047,
-0.03686275705695152,
-0.02906624972820282,
0.004102598875761032,
0.0039521474391222,
-0.000857795646879822,
0.02809617668390274,
-0.028599176555871964,
-0.04548562690615654,
-0.012440282851457596,
0.030072249472141266,
0.008286036550998688,
0.006363855674862862,
0.017290646210312843,
0.02335359901189804,
-0.005793489050120115,
0.030251894146203995,
-0.025796744972467422,
-0.045270055532455444,
-0.0008998995181173086,
0.010042048059403896,
-0.02942553535103798,
-0.027808748185634613,
-0.03776097297668457,
-0.06973744183778763,
-0.012215728871524334,
-0.042287979274988174,
0.042683195322752,
0.021018238738179207,
-0.01721878908574581,
0.0520605631172657,
-0.00805699173361063,
-0.004985095467418432,
0.023551207035779953,
-0.0569109246134758,
0.032245930284261703,
0.029156070202589035,
0.016446324065327644,
-0.008200705982744694,
-0.02141345478594303,
-0.015494215302169323,
-0.016185840591788292,
-0.00031016499269753695,
-0.023623064160346985,
-0.0067770350724458694,
-0.003819660749286413,
-0.04013226181268692,
-0.01770382560789585,
0.022670956328511238,
0.00036882967106066644,
0.025509316474199295,
-0.0002235714200651273,
-0.0014247940853238106,
-0.007441714406013489,
0.0774620920419693,
-0.015359482727944851,
-0.02797042578458786,
-0.06991708278656006,
-0.028545284643769264,
-0.022455383092164993,
-0.0174433421343565,
-0.04699462652206421,
0.06370143592357635,
0.0007988502620719373,
0.022167954593896866,
-0.017551127821207047,
-0.024161992594599724,
0.017182860523462296,
-0.03397050499916077,
0.035731006413698196,
0.0443718396127224,
0.00736985681578517,
-0.020209845155477524,
-0.05780914053320885,
-0.0538569912314415,
-0.036701079457998276,
0.014344499446451664,
-0.003734330413863063,
-0.034204039722681046,
0.023802706971764565,
0.04659941419959068,
-0.025150030851364136,
-0.0031864189077168703,
-0.04063526168465614,
-0.006395293399691582,
-0.041102334856987,
-0.017730770632624626,
-0.03776097297668457,
-0.011137870140373707,
-0.056084565818309784,
-0.02912014164030552,
0.014991214498877525,
0.028114140033721924,
-0.037976544350385666,
0.007917768321931362,
0.0063997842371463776,
0.006929731462150812,
-0.007203686982393265,
0.0018256227485835552,
-0.04559341073036194,
-0.04282690957188606,
0.009889351204037666,
0.017434360459446907,
-0.007086919154971838,
0.046311985701322556,
0.013230712153017521,
0.020335596054792404,
0.028293784707784653,
0.013706766068935394,
-0.017371485009789467,
-0.014155874028801918,
0.0161768589168787,
-0.027323711663484573,
-0.024179957807064056,
-0.030844714492559433,
-0.0075180623680353165,
0.002607070142403245,
0.021611060947179794,
-0.0284015703946352,
0.013042086735367775,
0.04067119210958481,
0.017236752435564995,
0.007163267582654953,
0.011631889268755913,
-0.008173760026693344,
0.022239811718463898,
-0.049940772354602814,
0.02152124047279358,
0.02723388932645321,
0.025670994073152542,
-0.0412101224064827,
-0.017775682732462883,
0.021323632448911667,
-0.04634791240096092,
-0.016581054776906967,
0.00485036289319396,
-0.02852731943130493,
0.0396292619407177,
-0.008798019029200077,
0.029533321037888527,
-0.04031190648674965,
0.041497550904750824,
-0.014425338245928288,
-0.04189276322722435,
-0.024108100682497025,
0.0443718396127224,
0.0019120759097859263,
0.049401845782995224,
0.09276768565177917,
-0.0035546873696148396,
0.019850559532642365,
0.0077560897916555405,
0.004935693461447954,
0.013859462924301624,
-0.045449696481227875,
-0.008595921099185944,
-0.004107089713215828,
-0.003976848442107439,
0.00299554830417037,
-0.020946381613612175,
-0.028688998892903328,
0.00808842945843935,
-0.007648303639143705,
-0.054216280579566956,
-0.018754737451672554,
0.039305903017520905,
0.04882698506116867,
-0.007715669926255941,
-0.001061578281223774,
-0.015081035904586315,
0.0022320651914924383,
0.01709303818643093,
-0.011281585320830345,
0.04311433807015419,
0.01380557008087635,
0.01291633676737547,
0.006907275877892971,
0.0006388556794263422,
-0.005227613262832165,
-0.03251539543271065,
0.025329673662781715,
-0.002694646129384637,
0.02694646082818508,
-0.003770258976146579,
0.024539243429899216,
0.004311433527618647,
-0.040347833186388016,
0.044479623436927795,
-0.019167914986610413,
0.03021596558392048,
0.002122033853083849,
0.010221690870821476,
0.04735391214489937,
0.013455266132950783,
0.018134968355298042,
-0.019131986424326897,
-0.022778742015361786,
0.018395449966192245,
-0.0014000931987538934,
0.012943283654749393,
-0.021341597661376,
-0.014389409683644772,
0.003449146868661046,
-0.029209963977336884,
0.03479686379432678,
-0.009440243244171143,
-0.03120400197803974,
0.003074142150580883,
0.04207240790128708,
0.0039005002472549677,
0.01904216594994068,
0.001541562145575881,
-0.026802746579051018,
-0.02870696224272251,
0.0019019710598513484,
-0.022778742015361786,
-0.004926711320877075,
-0.037725046277046204,
-0.0679769366979599,
0.003931937739253044,
-0.015584036707878113,
-0.026659032329916954,
-0.04300655052065849,
-0.051162347197532654,
-0.013275623321533203,
-0.01733555644750595,
0.0459526963531971,
0.010176779702305794,
0.06937815248966217,
0.08766581863164902,
0.020964346826076508,
0.06104271486401558,
0.04178497940301895,
0.023748813197016716,
-0.0330902524292469,
0.03355732560157776,
-0.030198000371456146,
-0.011613924987614155,
0.018090058118104935
]
}
],
"usage": {
"prompt_tokens": 14,
"total_tokens": 14,
"completion_tokens": 0,
"prompt_tokens_details": null
}
}
</syntaxhighlight>

[[Category: AI on Demand]]
[[Category: Embedding models]]

AI on demand: openai/whisper-large-v3

2026-10-18T09:31:51Z

Sst-mei: /* Calling the model */

== Calling the model ==
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# Set the desired model:
MODEL=openai/whisper-large-v3

# Path to the audio file to transcribe:
AUDIO_FILE=your-audio-file.wav

curl https://llm.stoney-cloud.com/v1/audio/transcriptions \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
--form "file=@$AUDIO_FILE" \
--form "model=$MODEL" \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang="json">
{
"text": "Hello and welcome to the Stepping Stone LLM Gateway.",
"usage": {
"type": "duration",
"seconds": 4
}
}
</syntaxhighlight>

[[Category: AI on Demand]]
[[Category: Audio models]]

AI on demand: mistralai/Voxtral-Mini-3B-2507

2026-10-18T09:31:39Z

Sst-mei: /* Limitations */

== Calling the model ==
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# Set the desired model:
MODEL=mistralai/Voxtral-Mini-3B-2507

# Path to the audio file to transcribe:
AUDIO_FILE=your-audio-file.wav

curl https://llm.stoney-cloud.com/v1/audio/transcriptions \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
--form "file=@$AUDIO_FILE" \
--form "model=$MODEL" \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang="json">
{
"text": "Hello and welcome to the Stepping Stone LLM Gateway.",
"usage": {
"type": "duration",
"seconds": 4
}
}
</syntaxhighlight>

== Limitations ==
The maximum request body size is currently 50 MiB, which limits the size of the audio file.

The following audio formats/containers/codecs are supported: aiff, au, avr, caf, flac, htk, ircam, mat4, mat5, mp3, mpc2k, nist, ogg, paf, pvf, raw, rf64, sd2, sds, svx, voc, w64, wav, wavex, wve, xi

[[Category: AI on Demand]]
[[Category: Audio models]]

AI on demand: black-forest-labs/FLUX.1-schnell

2026-10-18T09:30:46Z

Sst-mei:

== Calling the model ==
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# Set the desired model:
MODEL=black-forest-labs/FLUX.1-schnell

# Set your prompt:
PROMPT='Create a photorealistic picture of some cats.'

# Size of the generated image (WIDTHxHEIGHT):
SIZE=1024x1024

# Number of inference steps:
STEPS=4

curl https://llm.stoney-cloud.com/v1/images/generations \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
--header 'Content-Type: application/json' \
--data '{
"model": "'"$MODEL"'",
"prompt": "'"$PROMPT"'",
"size": "'"$SIZE"'",
"num_inference_steps": '"$STEPS"'
}' \
| jq
</syntaxhighlight>

Example output (cropped):
<syntaxhighlight lang="json">
{
"created": 1784646324,
"data": [
{
"b64_json": "iVBORw0KGgoAAAANSUhEUgAABAAAAAQACAIAAADwf7zUAAEAAElEQVR4AQALhP[...]AQABAP8AAP8B/v79AfANpMANoyqSAAAAAElFTkSuQmCC",
"url": null,
"revised_prompt": null
}
],
"output_format": "png",
"size": "1024x1024",
"cot_output": null
}
</syntaxhighlight>

The resulting image is returned as a Base64-encoded string inside <code>.data[0].b64_json</code>.

[[Category: AI on Demand]]
[[Category: Text to Image models]]

Category:Embedding models

2026-10-18T09:29:53Z

Sst-mei: Created page with "Category: AI on Demand"

[[Category: AI on Demand]]

Category:Audio models

2026-10-18T09:29:47Z

Sst-mei: Created page with "Category: AI on Demand"

[[Category: AI on Demand]]

Category:Text to Image models

2026-10-18T09:29:42Z

Sst-mei: Created page with "Category: AI on Demand"

[[Category: AI on Demand]]

Category:General purpose models

2026-10-18T09:29:37Z

Sst-mei: Created page with "Category: AI on Demand"

[[Category: AI on Demand]]

Category:Reranking models

2026-10-18T09:29:30Z

Sst-mei: Created page with "Category: AI on Demand"

[[Category: AI on Demand]]

Main Page

2026-10-18T09:29:00Z

Sst-mei: /* Artificial Intelligence (AI) */

<div style="float:left; width:48%;">
== Introduction ==
Welcome to the wiki of our [https://www.openstack.org/ OpenStack] based [https://www.stoney-cloud.com/ stoney cloud] infrastructure.
This collection serves as a comprehensive resource for all aspects of our cloud environment. Here, you will find guides for managing and utilizing our stoney cloud.

== OpenStack - Getting started ==
[[Quickstart|OpenStack quick start guide]]

== OpenStack - Usage ==
[[:Category:Projects|Projects]]

[[:Category:Instances|Instances]]
* [[VM creation (Linux)]]
* [[VM creation (Windows)]]
* [[VM resize (Linux)]]
* [[VM resize (Windows)]]
* [[Flavor explanation]]
[[:Category:Volumes|Volumes]]
* [[Quota]]

[[:Category:Images|Images]]
* [[Image creation]]
[[:Category:Network|Network]]
* [[Security group rules]]
* [[IP usage]]

[[:Category:Object store|Object store]]
* [[S3 buckets]]

[[:Category:Kubernetes|Kubernetes]]
* [[Kubernetes management]]
* [[Kubernetes usage]]

[[:Category:Backup|Backup]]
* [[Kopia restore process]]
[[:Category:Troubleshooting|Troubleshooting]]
* [[PCI workaround]]
* [[Change user password]]

</div>

<div style="float:right; width:48%">

== Artificial Intelligence (AI) ==
[[AI on Demand: Usage]] (list models, show usage, ...)

[[:Category: General purpose models|General purpose models]]
* [[AI on demand: apertus-ai/Apertus-v1.5-8B]]
* [[AI on demand: deepseek-ai/DeepSeek-V4-Flash-0731]]
* [[AI on demand: google/gemma-4-31B-it]]
* [[AI on demand: MiniMaxAI/MiniMax-M2.5]]
* [[AI on demand: NVIDIA/NVIDIA-Nemotron-3-Super-120B-A12B]]
* [[AI on demand: openai/gpt-oss-120b]]
* [[AI on demand: opendatalab/MinerU2.5-2509-1.2B]]
* [[AI on demand: Qwen/Qwen3-Coder-Next]]
* [[AI on demand: Qwen/Qwen3.5-35B-A3B-FP8]]
* [[AI on demand: Qwen/Qwen3.8-27B]]
* [[AI on demand: zai-org/GLM-5.3-Flash]]

[[:Category: OCR models|OCR models]]
* [[AI on demand: allenai/olmOCR-2-7B]]
* [[AI on demand: lightonai/LightOnOCR-2-1B]]

[[:Category: Text to Image models|Text to Image models]]
* [[AI on demand: black-forest-labs/FLUX.1-schnell]]

[[:Category: Audio models|Audio models]]
* [[AI on demand: mistralai/Voxtral-Mini-3B-2507]]
* [[AI on demand: openai/whisper-large-v3]]

[[:Category: Embedding models|Embedding models]]
* [[AI on demand: BAAI/bge-m3]]

[[:Category: Reranking models|Reranking models]]
* [[AI on demand: BAAI/bge-reranker-v2-m3]]

[[:Category: System One decision models|System One decision models]]
* [[AI on demand: convaiinnovations/laya]]
* [[AI on demand: jaredpalmer/kev-27b]]
* [[AI on demand: Mapika/decider-31b]]

== Quick links ==
* [https://www.stoney-cloud.com/ stoney cloud Website]
* [https://dashboard.stoney-cloud.com/ stoney cloud Dashboard]
* [https://docs.openstack.org/horizon/latest/user/index.html Official OpenStack Dashboard Documentation]
* [https://docs.openstack.org/python-openstackclient/latest/cli/index.html Official OpenStack CLI Documentation]
</div>

<div style="clear:both; height:0px; line-height:0px;"></div>

__NOTOC__

Main Page

2026-10-18T09:28:40Z

Sst-mei: /* Artificial Intelligence (AI) */

<div style="float:left; width:48%;">
== Introduction ==
Welcome to the wiki of our [https://www.openstack.org/ OpenStack] based [https://www.stoney-cloud.com/ stoney cloud] infrastructure.
This collection serves as a comprehensive resource for all aspects of our cloud environment. Here, you will find guides for managing and utilizing our stoney cloud.

== OpenStack - Getting started ==
[[Quickstart|OpenStack quick start guide]]

== OpenStack - Usage ==
[[:Category:Projects|Projects]]

[[:Category:Instances|Instances]]
* [[VM creation (Linux)]]
* [[VM creation (Windows)]]
* [[VM resize (Linux)]]
* [[VM resize (Windows)]]
* [[Flavor explanation]]
[[:Category:Volumes|Volumes]]
* [[Quota]]

[[:Category:Images|Images]]
* [[Image creation]]
[[:Category:Network|Network]]
* [[Security group rules]]
* [[IP usage]]

[[:Category:Object store|Object store]]
* [[S3 buckets]]

[[:Category:Kubernetes|Kubernetes]]
* [[Kubernetes management]]
* [[Kubernetes usage]]

[[:Category:Backup|Backup]]
* [[Kopia restore process]]
[[:Category:Troubleshooting|Troubleshooting]]
* [[PCI workaround]]
* [[Change user password]]

</div>

<div style="float:right; width:48%">

== Artificial Intelligence (AI) ==
[[AI on Demand: Usage]] (list models, show usage, ...)

[[:Category: AI on Demand|AI on Demand models]] (all models and usage)

[[:Category: General purpose models|General purpose models]]
* [[AI on demand: apertus-ai/Apertus-v1.5-8B]]
* [[AI on demand: deepseek-ai/DeepSeek-V4-Flash-0731]]
* [[AI on demand: google/gemma-4-31B-it]]
* [[AI on demand: MiniMaxAI/MiniMax-M2.5]]
* [[AI on demand: NVIDIA/NVIDIA-Nemotron-3-Super-120B-A12B]]
* [[AI on demand: openai/gpt-oss-120b]]
* [[AI on demand: opendatalab/MinerU2.5-2509-1.2B]]
* [[AI on demand: Qwen/Qwen3-Coder-Next]]
* [[AI on demand: Qwen/Qwen3.5-35B-A3B-FP8]]
* [[AI on demand: Qwen/Qwen3.8-27B]]
* [[AI on demand: zai-org/GLM-5.3-Flash]]

[[:Category: OCR models|OCR models]]
* [[AI on demand: allenai/olmOCR-2-7B]]
* [[AI on demand: lightonai/LightOnOCR-2-1B]]

[[:Category: Text to Image models|Text to Image models]]
* [[AI on demand: black-forest-labs/FLUX.1-schnell]]

[[:Category: Audio models|Audio models]]
* [[AI on demand: mistralai/Voxtral-Mini-3B-2507]]
* [[AI on demand: openai/whisper-large-v3]]

[[:Category: Embedding models|Embedding models]]
* [[AI on demand: BAAI/bge-m3]]

[[:Category: Reranking models|Reranking models]]
* [[AI on demand: BAAI/bge-reranker-v2-m3]]

[[:Category: System One decision models|System One decision models]]
* [[AI on demand: convaiinnovations/laya]]
* [[AI on demand: jaredpalmer/kev-27b]]
* [[AI on demand: Mapika/decider-31b]]

== Quick links ==
* [https://www.stoney-cloud.com/ stoney cloud Website]
* [https://dashboard.stoney-cloud.com/ stoney cloud Dashboard]
* [https://docs.openstack.org/horizon/latest/user/index.html Official OpenStack Dashboard Documentation]
* [https://docs.openstack.org/python-openstackclient/latest/cli/index.html Official OpenStack CLI Documentation]
</div>

<div style="clear:both; height:0px; line-height:0px;"></div>

__NOTOC__

AI on Demand: Usage

2026-10-18T09:24:17Z

Sst-mei: /* Usage - Inspecting your usage */

= Overview =
This pages describes some useful usage commands.

= Usage =
We assume you've received your API key from us in our usual manner.

== Usage - List all models ==
=== Usage - List all models - General purpose ===
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# List all general purpose models:
curl https://llm.stoney-cloud.com/v1/models \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang='json'>
{
"object": "list",
"data": [
{
"id": "allenai/olmOCR-2-7B",
"object": "model",
"max_model_len": 8192
},
{
"id": "apertus-ai/Apertus-v1.5-8B",
"object": "model",
"max_model_len": 131072
},
{
"id": "convaiinnovations/laya",
"object": "model",
"max_model_len": 4096
},
{
"id": "deepseek-ai/DeepSeek-V4-Flash-0731",
"object": "model",
"max_model_len": 524288
},
{
"id": "google/gemma-4-31B-it",
"object": "model",
"max_model_len": 163840
},
{
"id": "jaredpalmer/kev-27b",
"object": "model",
"max_model_len": 65536
},
{
"id": "lightonai/LightOnOCR-2-1B",
"object": "model",
"max_model_len": 16384
},
{
"id": "Mapika/decider-31b",
"object": "model",
"max_model_len": 40960
},
{
"id": "MinerU2.5-2509-1.2B",
"object": "model",
"max_model_len": 16384
},
{
"id": "MiniMaxAI/MiniMax-M2.5",
"object": "model",
"max_model_len": 196608
},
{
"id": "NVIDIA/NVIDIA-Nemotron-3-Super-120B-A12B",
"object": "model",
"max_model_len": 131072
},
{
"id": "openai/gpt-oss-120b",
"object": "model",
"max_model_len": 131072
},
{
"id": "opendatalab/MinerU2.5-2509-1.2B",
"object": "model",
"max_model_len": 16384
},
{
"id": "Qwen/Qwen3.5-35B-A3B-FP8",
"object": "model",
"max_model_len": 131072
},
{
"id": "Qwen/Qwen3.8-27B",
"object": "model",
"max_model_len": 262144
},
{
"id": "Qwen/Qwen3-Coder-Next",
"object": "model",
"max_model_len": 262144
},
{
"id": "zai-org/GLM-5.3-Flash",
"object": "model",
"max_model_len": 262144
}
]
}
</syntaxhighlight>

=== Usage - List all models - Audio ===
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# List all audio models:
curl https://llm.stoney-cloud.com/v1/audio/models \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang="json">
{
"data": [
{
"object": "model",
"id": "mistralai/Voxtral-Mini-3B-2507"
},
{
"object": "model",
"id": "openai/whisper-large-v3"
}
],
"object": "list"
}
</syntaxhighlight>

=== Usage - List all models - Embeddings ===
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# List all embeddings models:
curl https://llm.stoney-cloud.com/v1/embeddings/models \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang="json">
{
"data": [
{
"object": "model",
"max_model_len": 8192,
"id": "BAAI/bge-m3"
}
],
"object": "list"
}
</syntaxhighlight>

=== Usage - List all models - Rerank ===
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# List all rerank models:
curl https://llm.stoney-cloud.com/v1/rerank/models \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang="json">
{
"data": [
{
"object": "model",
"max_model_len": 8192,
"id": "BAAI/bge-reranker-v2-m3"
}
],
"object": "list"
}
</syntaxhighlight>

=== Usage - List all models - Images ===
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# List all images models:
curl https://llm.stoney-cloud.com/v1/images/models \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang="json">
{
"data": [
{
"object": "model",
"id": "black-forest-labs/FLUX.1-schnell"
}
],
"object": "list"
}
</syntaxhighlight>

== Usage - Inspecting your usage ==
We issue one key per model for now. The usage is thus per-model-per-key.

<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# Set desired month in the form YYYY-MM, for example: '2026-03'.
MONTH=$(date +%Y-%m)

curl https://llm.stoney-cloud.com/v1/usage?month="$MONTH" \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang="json">
{
"month": "2026-08",
"models": [
{
"cost_chf": 0.000019,
"output": 11,
"input": 256,
"model": "allenai/olmOCR-2-7B"
},
{
"cost_chf": 0.003268,
"output": 942,
"input": 22679,
"model": "apertus-ai/Apertus-v1.5-8B"
},
{
"cost_chf": 0.562569,
"output": 9555,
"input": 257397,
"model": "NVIDIA/NVIDIA-Nemotron-3-Super-120B-A12B"
},
{
"cost_chf": 16.6957,
"output": 120992,
"input": 2734180,
"model": "openai/gpt-oss-120b"
}
],
"total_cost_chf": 17.261556
}
</syntaxhighlight>

[[Category: AI on Demand]]

Category:AI on Demand

2026-10-18T09:24:03Z

Sst-mei: /* Overview */

= Overview =
This category collects all AI on demand related pages.

stepping stone AG is proud to serve customers with current language models and OCR solutions.

All of our LLM services are reachable via the OpenAI-compatible gateway at https://llm.stoney-cloud.com/.

Check out the [[AI on Demand: Usage]] page. You can list the models, show your own usage information, etc.

[[Category: Artificial Intelligence]]

AI on demand: lightonai/LightOnOCR-2-1B

2026-10-18T09:23:13Z

Sst-mei: /* Calling the model */

== Calling the model ==
[[Image:testocr.png|thumb|The image used in the example to run OCR against.]]
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# Set the desired model:
MODEL=lightonai/LightOnOCR-2-1B

# Set the desired document to run OCR against:
FILE_PATH=document.png

# Encode document contents with Base64 and detect MIME type:
FILE_CONTENT_BASE64=$(base64 -w 0 < "$FILE_PATH")
FILE_MIME_TYPE=$(file --brief --mime-type "$FILE_PATH")

curl https://llm.stoney-cloud.com/v1/chat/completions \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
--header 'Content-Type: application/json' \
--data '{
"model": "'"$MODEL"'",
"messages": [{
"role": "user",
"content": [{
"type": "image_url",
"image_url": {
"url": "data:'"$FILE_MIME_TYPE"';base64,'"$FILE_CONTENT_BASE64"'"
}
}]
}],
"max_tokens": 4096,
"temperature": 0.2,
"top_p": 0.9
}' \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang="json">
{
"id": "chatcmpl-b9d11ab9588ee638",
"object": "chat.completion",
"created": 1778491557,
"model": "lightonai/LightOnOCR-2-1B",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "This is a lot of 12 point text to test the ocr code and see if it works on all types of file format.\n\nThe quick brown dog jumped over the lazy fox. The quick brown dog jumped over the lazy fox. The quick brown dog jumped over the lazy fox. The quick brown dog jumped over the lazy fox.",
"refusal": null,
"annotations": null,
"audio": null,
"function_call": null,
"tool_calls": [],
"reasoning": null
},
"logprobs": null,
"finish_reason": "stop",
"stop_reason": null,
"token_ids": null
}
],
"service_tier": null,
"system_fingerprint": null,
"usage": {
"prompt_tokens": 426,
"total_tokens": 495,
"completion_tokens": 69,
"prompt_tokens_details": null
},
"prompt_logprobs": null,
"prompt_token_ids": null,
"kv_transfer_params": null
}
</syntaxhighlight>

[[Category: AI on Demand]]
[[Category: OCR models]]

AI on demand: allenai/olmOCR-2-7B

2026-10-18T09:23:00Z

Sst-mei: /* Calling the model */

== Calling the model ==
[[Image:testocr.png|thumb|The image used in the example to run OCR against.]]
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# Set the desired model:
MODEL=allenai/olmOCR-2-7B

# Set the desired document to run OCR against:
FILE_PATH=document.png

# Encode document contents with Base64 and detect MIME type:
FILE_CONTENT_BASE64=$(base64 -w 0 < "$FILE_PATH")
FILE_MIME_TYPE=$(file --brief --mime-type "$FILE_PATH")

curl https://llm.stoney-cloud.com/v1/chat/completions \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
--header 'Content-Type: application/json' \
--data '{
"model": "'"$MODEL"'",
"messages": [{
"role": "user",
"content": [{
"type": "image_url",
"image_url": {
"url": "data:'"$FILE_MIME_TYPE"';base64,'"$FILE_CONTENT_BASE64"'"
}
}]
}],
"max_tokens": 4096,
"temperature": 0.2,
"top_p": 0.9
}' \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang="json">
{
"id": "chatcmpl-b96a0fa8d921c5ed",
"object": "chat.completion",
"created": 1779956243,
"model": "allenai/olmOCR-2-7B",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "This is a lot of 12 point text to test the ocr code and see if it works on all types of file format.\nThe quick brown dog jumped over the lazy fox. The quick brown dog jumped over the lazy fox. The quick brown dog jumped over the lazy fox. The quick brown dog jumped over the lazy fox.",
"refusal": null,
"annotations": null,
"audio": null,
"function_call": null,
"tool_calls": [],
"reasoning": null
},
"logprobs": null,
"finish_reason": "stop",
"stop_reason": null,
"token_ids": null
}
],
"service_tier": null,
"system_fingerprint": null,
"usage": {
"prompt_tokens": 412,
"total_tokens": 481,
"completion_tokens": 69,
"prompt_tokens_details": null
},
"prompt_logprobs": null,
"prompt_token_ids": null,
"kv_transfer_params": null
}
</syntaxhighlight>

[[Category: AI on Demand]]
[[Category: OCR models]]

Category:OCR models

2026-10-18T09:21:31Z

Sst-mei: Created page with "Category: AI on Demand"

[[Category: AI on Demand]]

AI on demand: Usage

2026-10-18T09:20:52Z

Sst-mei: Sst-mei moved page AI on demand: Usage to AI on Demand: Usage

#REDIRECT [[AI on Demand: Usage]]

AI on Demand: Usage

2026-10-18T09:20:52Z

Sst-mei: Sst-mei moved page AI on demand: Usage to AI on Demand: Usage

= Overview =
This pages describes some useful usage commands.

= Usage =
We assume you've received your API key from us in our usual manner.

== Usage - List all models ==
=== Usage - List all models - General purpose ===
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# List all general purpose models:
curl https://llm.stoney-cloud.com/v1/models \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang='json'>
{
"object": "list",
"data": [
{
"id": "allenai/olmOCR-2-7B",
"object": "model",
"max_model_len": 8192
},
{
"id": "apertus-ai/Apertus-v1.5-8B",
"object": "model",
"max_model_len": 131072
},
{
"id": "convaiinnovations/laya",
"object": "model",
"max_model_len": 4096
},
{
"id": "deepseek-ai/DeepSeek-V4-Flash-0731",
"object": "model",
"max_model_len": 524288
},
{
"id": "google/gemma-4-31B-it",
"object": "model",
"max_model_len": 163840
},
{
"id": "jaredpalmer/kev-27b",
"object": "model",
"max_model_len": 65536
},
{
"id": "lightonai/LightOnOCR-2-1B",
"object": "model",
"max_model_len": 16384
},
{
"id": "Mapika/decider-31b",
"object": "model",
"max_model_len": 40960
},
{
"id": "MinerU2.5-2509-1.2B",
"object": "model",
"max_model_len": 16384
},
{
"id": "MiniMaxAI/MiniMax-M2.5",
"object": "model",
"max_model_len": 196608
},
{
"id": "NVIDIA/NVIDIA-Nemotron-3-Super-120B-A12B",
"object": "model",
"max_model_len": 131072
},
{
"id": "openai/gpt-oss-120b",
"object": "model",
"max_model_len": 131072
},
{
"id": "opendatalab/MinerU2.5-2509-1.2B",
"object": "model",
"max_model_len": 16384
},
{
"id": "Qwen/Qwen3.5-35B-A3B-FP8",
"object": "model",
"max_model_len": 131072
},
{
"id": "Qwen/Qwen3.8-27B",
"object": "model",
"max_model_len": 262144
},
{
"id": "Qwen/Qwen3-Coder-Next",
"object": "model",
"max_model_len": 262144
},
{
"id": "zai-org/GLM-5.3-Flash",
"object": "model",
"max_model_len": 262144
}
]
}
</syntaxhighlight>

=== Usage - List all models - Audio ===
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# List all audio models:
curl https://llm.stoney-cloud.com/v1/audio/models \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang="json">
{
"data": [
{
"object": "model",
"id": "mistralai/Voxtral-Mini-3B-2507"
},
{
"object": "model",
"id": "openai/whisper-large-v3"
}
],
"object": "list"
}
</syntaxhighlight>

=== Usage - List all models - Embeddings ===
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# List all embeddings models:
curl https://llm.stoney-cloud.com/v1/embeddings/models \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang="json">
{
"data": [
{
"object": "model",
"max_model_len": 8192,
"id": "BAAI/bge-m3"
}
],
"object": "list"
}
</syntaxhighlight>

=== Usage - List all models - Rerank ===
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# List all rerank models:
curl https://llm.stoney-cloud.com/v1/rerank/models \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang="json">
{
"data": [
{
"object": "model",
"max_model_len": 8192,
"id": "BAAI/bge-reranker-v2-m3"
}
],
"object": "list"
}
</syntaxhighlight>

=== Usage - List all models - Images ===
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# List all images models:
curl https://llm.stoney-cloud.com/v1/images/models \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang="json">
{
"data": [
{
"object": "model",
"id": "black-forest-labs/FLUX.1-schnell"
}
],
"object": "list"
}
</syntaxhighlight>

== Usage - Inspecting your usage ==
We issue one key per model for now. The usage is thus per-model-per-key.

<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# Set desired month in the form YYYY-MM, for example: '2026-03'.
MONTH=$(date +%Y-%m)

curl https://llm.stoney-cloud.com/v1/usage?month="$MONTH" \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang="json">
{
"month": "2026-08",
"models": [
{
"cost_chf": 0.000019,
"output": 11,
"input": 256,
"model": "allenai/olmOCR-2-7B"
},
{
"cost_chf": 0.003268,
"output": 942,
"input": 22679,
"model": "apertus-ai/Apertus-v1.5-8B"
},
{
"cost_chf": 0.562569,
"output": 9555,
"input": 257397,
"model": "NVIDIA/NVIDIA-Nemotron-3-Super-120B-A12B"
},
{
"cost_chf": 16.6957,
"output": 120992,
"input": 2734180,
"model": "openai/gpt-oss-120b"
}
],
"total_cost_chf": 17.261556
}
</syntaxhighlight>

[[Category: AI on demand]]

Main Page

2026-10-18T09:20:31Z

Sst-mei: /* Artificial Intelligence (AI) */

<div style="float:left; width:48%;">
== Introduction ==
Welcome to the wiki of our [https://www.openstack.org/ OpenStack] based [https://www.stoney-cloud.com/ stoney cloud] infrastructure.
This collection serves as a comprehensive resource for all aspects of our cloud environment. Here, you will find guides for managing and utilizing our stoney cloud.

== OpenStack - Getting started ==
[[Quickstart|OpenStack quick start guide]]

== OpenStack - Usage ==
[[:Category:Projects|Projects]]

[[:Category:Instances|Instances]]
* [[VM creation (Linux)]]
* [[VM creation (Windows)]]
* [[VM resize (Linux)]]
* [[VM resize (Windows)]]
* [[Flavor explanation]]
[[:Category:Volumes|Volumes]]
* [[Quota]]

[[:Category:Images|Images]]
* [[Image creation]]
[[:Category:Network|Network]]
* [[Security group rules]]
* [[IP usage]]

[[:Category:Object store|Object store]]
* [[S3 buckets]]

[[:Category:Kubernetes|Kubernetes]]
* [[Kubernetes management]]
* [[Kubernetes usage]]

[[:Category:Backup|Backup]]
* [[Kopia restore process]]
[[:Category:Troubleshooting|Troubleshooting]]
* [[PCI workaround]]
* [[Change user password]]

</div>

<div style="float:right; width:48%">

== Artificial Intelligence (AI) ==
[[AI on Demand: Usage]] (list models, show usage, ...)

[[:Category: AI on Demand|AI on Demand models]] (all models and usage)

* [[AI on demand: allenai/olmOCR-2-7B]]
* [[AI on demand: apertus-ai/Apertus-v1.5-8B]]
* [[AI on demand: BAAI/bge-m3]]
* [[AI on demand: BAAI/bge-reranker-v2-m3]]
* [[AI on demand: black-forest-labs/FLUX.1-schnell]]
* [[AI on demand: deepseek-ai/DeepSeek-V4-Flash-0731]]
* [[AI on demand: google/gemma-4-31B-it]]
* [[AI on demand: lightonai/LightOnOCR-2-1B]]
* [[AI on demand: MiniMaxAI/MiniMax-M2.5]]
* [[AI on demand: mistralai/Voxtral-Mini-3B-2507]]
* [[AI on demand: NVIDIA/NVIDIA-Nemotron-3-Super-120B-A12B]]
* [[AI on demand: openai/gpt-oss-120b]]
* [[AI on demand: openai/whisper-large-v3]]
* [[AI on demand: opendatalab/MinerU2.5-2509-1.2B]]
* [[AI on demand: Qwen/Qwen3-Coder-Next]]
* [[AI on demand: Qwen/Qwen3.5-35B-A3B-FP8]]
* [[AI on demand: Qwen/Qwen3.8-27B]]
* [[AI on demand: zai-org/GLM-5.3-Flash]]

[[:Category: OCR models|OCR models]]

[[:Category: System One decision models|System One decision models]]
* [[AI on demand: convaiinnovations/laya]]
* [[AI on demand: jaredpalmer/kev-27b]]
* [[AI on demand: Mapika/decider-31b]]

== Quick links ==
* [https://www.stoney-cloud.com/ stoney cloud Website]
* [https://dashboard.stoney-cloud.com/ stoney cloud Dashboard]
* [https://docs.openstack.org/horizon/latest/user/index.html Official OpenStack Dashboard Documentation]
* [https://docs.openstack.org/python-openstackclient/latest/cli/index.html Official OpenStack CLI Documentation]
</div>

<div style="clear:both; height:0px; line-height:0px;"></div>

__NOTOC__

AI on demand: Mapika/decider-31b

2026-10-18T09:18:32Z

Sst-mei: /* Usage - Score */

= Overview =
System One decision models such as [https://huggingface.co/Mapika/decider-31b Mapika/decider-31b] assess text and return structured answers and probabilities in a single forward pass.

They support three question types:
* '''Choice'''
** Selects the single best option (or returns a probability distribution) from a fixed set of 2 to 255 declared options.

* '''Noul (Yes/No)'''
** Returns a boolean probability distribution for a binary question.

* '''Score'''
** Assigns a numeric value along a defined ordered scale (typically 2 to 10 levels) to represent a grading rubric or rating.

These models suit classification, routing, and decision support. They do not generate conversational answers or explanations, and their predictions can be wrong. Reported probabilities require evaluation on representative data before using them for consequential automation.

Our [https://huggingface.co/Mapika/decider-31b Mapika/decider-31b] implementation has a multilingual checkpoint with a fixed 65'536-token input limit.

= Usage =
== Usage - Choice ==
The following '''choice''' example routes a request to a department.

Example call:
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-....

# Execute the actual call:
curl --fail-with-body -sS \
https://llm.stoney-cloud.com/v1/systemone \
-H "apikey: $STONEY_KEY" \
-H 'Content-Type: application/json' \
--data-binary '{
"model": "Mapika/decider-31b",
"state": {
"document": "Meine Rechnung wurde zweimal belastet. Bitte prüfen Sie die doppelte Zahlung."
},
"questions": {
"department": {
"type": "choice",
"instructions": "Which department should handle this request?",
"criteria": {
"technical": "Application errors and login problems",
"billing": "Invoices, payments and duplicate charges",
"support": "General customer support and newsletter preferences"
}
}
}
}' | jq .
</syntaxhighlight>

Example answer:
<syntaxhighlight lang="json">
{
"model": "Mapika/decider-31b",
"answers": {
"department": {
"type": "choice",
"choice": "billing",
"confidence": 0.9264,
"x_p_max": 0.9509,
"certainty": 0.795,
"probabilities": {
"technical": 0.0351,
"billing": 0.9509,
"support": 0.014
}
}
},
"usage": {
"input_tokens": 88,
"output_tokens": 0,
"prompt_tokens": 88,
"completion_tokens": 0
}
}
</syntaxhighlight>

== Usage - Noul ==
The following '''noul''' example detects if customer explicitly requests a refund.

Example call:
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-....

# Execute the actual call:
{
"model": "Mapika/decider-31b",
"answers": {
"refund_requested": {
"type": "noul",
"noul": 0.9327
}
},
"usage": {
"input_tokens": 89,
"output_tokens": 0,
"prompt_tokens": 89,
"completion_tokens": 0
}
}
</syntaxhighlight>

Example answer:
<syntaxhighlight lang="json">
"model": "Mapika/decider-31b",
"answers": {
"refund_requested": {
"type": "noul",
"noul": 0.9851
}
},
"usage": {
"input_tokens": 60,
"output_tokens": 23,
"prompt_tokens": 60,
"completion_tokens": 23
},
"latency_ms": 86.9
}
</syntaxhighlight>

== Usage - Score ==
The following '''score''' example estimates the urgency of a support request. The criteria is arranged from lowest to highest.

Example call:
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-....

# Execute the actual call:
curl --fail-with-body -sS \
https://llm.stoney-cloud.com/v1/systemone \
-H "apikey: $STONEY_KEY" \
-H 'Content-Type: application/json' \
--data-binary '{
"model": "Mapika/decider-31b",
"state": {
"document": "Unser gesamtes Produktionssystem ist ausgefallen. Alle Kunden sind betroffen und können keine Bestellungen aufgeben. Wir benötigen sofort Hilfe."
},
"questions": {
"urgency": {
"type": "score",
"instructions": "How urgent is this support request?",
"criteria": [
"Not urgent: informational request with no operational impact",
"Low urgency: minor inconvenience with a workaround",
"Moderate urgency: partial disruption affecting some users",
"High urgency: major disruption requiring prompt attention",
"Critical urgency: complete production outage affecting all customers"
]
}
}
}' | jq .
</syntaxhighlight>

Example answer:
<syntaxhighlight lang="json">
{
"model": "Mapika/decider-31b",
"answers": {
"urgency": {
"type": "score",
"score": 3.9,
"confidence": 0.915,
"x_p_max": 0.9466,
"certainty": 0.8337,
"legend": {
"0": "Not urgent: informational request with no operational impact",
"1": "Low urgency: minor inconvenience with a workaround",
"2": "Moderate urgency: partial disruption affecting some users",
"3": "High urgency: major disruption requiring prompt attention",
"4": "Critical urgency: complete production outage affecting all customers"
},
"probabilities": {
"0": 0.0076,
"1": 0.011,
"2": 0.0039,
"3": 0.031,
"4": 0.9466
}
}
},
"usage": {
"input_tokens": 140,
"output_tokens": 0,
"prompt_tokens": 140,
"completion_tokens": 0
}
}
</syntaxhighlight>

[[Category:AI on Demand]]
[[Category: System One decision models]]

AI on demand: convaiinnovations/laya

2026-10-18T09:17:48Z

Sst-mei: /* System One Model - Usage score */

= System One Model - Introduction =

System One models such as Laya assess text and return structured decisions in a single forward pass.
They support three question types:
* '''choice'''
**selects a category, such as the department responsible for a ticket

* '''noul'''
** returns the probability that a statement is true, such as whether a customer requests a refund.

* '''score'''
** assesses text against an ordered scale, such as urgency from low to critical.

These models suit classification, routing, and decision support. They do not generate conversational answers or explanations, and their predictions can be wrong. Reported probabilities require evaluation on representative data before using them for consequential automation.

Our service uses Laya’s multilingual checkpoint with a fixed 4,096-token input limit.

= System One Model - Usage =

To use a System One model set your stoney key

<syntaxhighlight lang="bash">

STONEY_KEY=sk-....

</syntaxhighlight>

== System One Model - Usage choice ==

Use this category for example to route a request to a department.

'''Input:'''

<syntaxhighlight lang="bash">
curl --fail-with-body -sS \
https://llm.stoney-cloud.com/v1/systemone \
-H "apikey: $STONEY_KEY" \
-H 'Content-Type: application/json' \
--data-binary '{
"model": "convaiinnovations/laya",
"state": {
"document": "Meine Rechnung wurde zweimal belastet. Bitte prüfen Sie die doppelte Zahlung."
},
"questions": {
"department": {
"type": "choice",
"instructions": "Which department should handle this request?",
"criteria": {
"technical": "Application errors and login problems",
"billing": "Invoices, payments and duplicate charges",
"support": "General customer support and newsletter preferences"
}
}
}
}' | jq .
</syntaxhighlight>

'''Output:'''

<syntaxhighlight lang="json">
{
"model": "convaiinnovations/laya",
"answers": {
"department": {
"type": "choice",
"choice": "billing",
"probabilities": {
"technical": 0.0,
"billing": 0.9999,
"support": 0.0
},
"confidence": 0.9994,
"answer_confidence": 0.9999,
"action": {
"act_probability": 1.0
}
}
},
"usage": {
"input_tokens": 61,
"output_tokens": 0,
"state_tokens": 20,
"state_tokens_dropped": 0,
"truncated": false,
"truncated_questions": [],
"prompt_tokens": 61,
"completion_tokens": 0
},
"routing": {
"model": "multilingual",
"repo": "convaiinnovations/laya/multilingual",
"reason": "explicit model='multilingual'",
"detection": null,
"workflow": null
}
}
</syntaxhighlight>

== System One Model - Usage noul ==

Use noul to check a statement, for example to detect if customer explicitly requests a refund.

'''Input:'''

<syntaxhighlight lang="bash">
curl --fail-with-body -sS \
https://llm.stoney-cloud.com/v1/systemone \
-H "apikey: $STONEY_KEY" \
-H 'Content-Type: application/json' \
--data-binary '{
"model": "convaiinnovations/laya",
"state": {
"document": "Meine Rechnung wurde zweimal belastet. Bitte erstatten Sie mir die zweite Zahlung zurück."
},
"questions": {
"refund_requested": {
"type": "noul",
"instructions": "Does the customer explicitly request a refund?",
"criteria": {
"true": "The customer explicitly asks for money to be returned.",
"false": "The customer does not ask for money to be returned."
}
}
}
}' | jq .
</syntaxhighlight>

'''Output:'''

<syntaxhighlight lang="json">
{
"model": "convaiinnovations/laya",
"answers": {
"refund_requested": {
"type": "noul",
"noul": 0.9697,
"confidence": 0.9697,
"answer_confidence": 0.9697,
"action": {
"act_probability": 1.0
}
}
},
"usage": {
"input_tokens": 65,
"output_tokens": 0,
"state_tokens": 22,
"state_tokens_dropped": 0,
"truncated": false,
"truncated_questions": [],
"prompt_tokens": 65,
"completion_tokens": 0
},
"routing": {
"model": "multilingual",
"repo": "convaiinnovations/laya/multilingual",
"reason": "explicit model='multilingual'",
"detection": null,
"workflow": null
}
}
</syntaxhighlight>

== System One Model - Usage score ==

Use score to for example estimate the urgency of a support request. Arrange criteria from lowest to highest.

'''Input:'''

<syntaxhighlight lang="bash">
curl --fail-with-body -sS \
https://llm.stoney-cloud.com/v1/systemone \
-H "apikey: $STONEY_KEY" \
-H 'Content-Type: application/json' \
--data-binary '{
"model": "convaiinnovations/laya",
"state": {
"document": "Unser gesamtes Produktionssystem ist ausgefallen. Alle Kunden sind betroffen und können keine Bestellungen aufgeben. Wir benötigen sofort Hilfe."
},
"questions": {
"urgency": {
"type": "score",
"instructions": "How urgent is this support request?",
"criteria": [
"Not urgent: informational request with no operational impact",
"Low urgency: minor inconvenience with a workaround",
"Moderate urgency: partial disruption affecting some users",
"High urgency: major disruption requiring prompt attention",
"Critical urgency: complete production outage affecting all customers"
]
}
}
}' | jq .
</syntaxhighlight>

'''Output:'''

<syntaxhighlight lang="json">
{
"model": "convaiinnovations/laya",
"answers": {
"urgency": {
"type": "score",
"score": 3.987,
"legend": {
"0": "Not urgent: informational request with no operational impact",
"1": "Low urgency: minor inconvenience with a workaround",
"2": "Moderate urgency: partial disruption affecting some users",
"3": "High urgency: major disruption requiring prompt attention",
"4": "Critical urgency: complete production outage affecting all customers"
},
"probabilities": {
"0": 0.0003,
"1": 0.0016,
"2": 0.0012,
"3": 0.0044,
"4": 0.9924
},
"confidence": 0.9673,
"answer_confidence": 0.9924,
"action": {
"act_probability": 1.0
}
}
},
"usage": {
"input_tokens": 112,
"output_tokens": 0,
"state_tokens": 31,
"state_tokens_dropped": 0,
"truncated": false,
"truncated_questions": [],
"prompt_tokens": 112,
"completion_tokens": 0
},
"routing": {
"model": "multilingual",
"repo": "convaiinnovations/laya/multilingual",
"reason": "explicit model='multilingual'",
"detection": null,
"workflow": null
}
}
</syntaxhighlight>

[[Category:AI on Demand]]
[[Category: System One decision models]]

AI on demand: jaredpalmer/kev-27b

2026-10-18T09:17:27Z

Sst-mei: /* Usage - Score */

= Overview =
System One decision models such as [https://huggingface.co/jaredpalmer/kev-27b jaredpalmer/kev-27b] assess text and return structured answers and probabilities in a single forward pass.

They support three question types:
* '''Choice'''
** Selects the single best option (or returns a probability distribution) from a fixed set of 2 to 255 declared options.

* '''Noul (Yes/No)'''
** Returns a boolean probability distribution for a binary question.

* '''Score'''
** Assigns a numeric value along a defined ordered scale (typically 2 to 10 levels) to represent a grading rubric or rating.

These models suit classification, routing, and decision support. They do not generate conversational answers or explanations, and their predictions can be wrong. Reported probabilities require evaluation on representative data before using them for consequential automation.

Our [https://huggingface.co/jaredpalmer/kev-27b jaredpalmer/kev-27b] implementation has a multilingual checkpoint with a fixed 65'536-token input limit.

= Usage =
== Usage - Choice ==
The following '''choice''' example routes a request to a department.

Example call:
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-....

# Execute the actual call:
curl --fail-with-body -sS \
https://llm.stoney-cloud.com/v1/systemone \
-H "apikey: $STONEY_KEY" \
-H 'Content-Type: application/json' \
--data-binary '{
"model": "jaredpalmer/kev-27b",
"state": {
"document": "Meine Rechnung wurde zweimal belastet. Bitte prüfen Sie die doppelte Zahlung."
},
"questions": {
"department": {
"type": "choice",
"instructions": "Which department should handle this request?",
"criteria": {
"technical": "Application errors and login problems",
"billing": "Invoices, payments and duplicate charges",
"support": "General customer support and newsletter preferences"
}
}
}
}' | jq .
</syntaxhighlight>

Example answer:
<syntaxhighlight lang="json">
{
"model": "jaredpalmer/kev-27b",
"answers": {
"department": {
"type": "choice",
"choice": "billing",
"confidence": 0.9985,
"probabilities": {
"technical": 0.0003,
"billing": 0.999,
"support": 0.0007
}
}
},
"usage": {
"input_tokens": 59,
"output_tokens": 62,
"prompt_tokens": 59,
"completion_tokens": 62
},
"latency_ms": 45.9
}
</syntaxhighlight>

== Usage - Noul ==
The following '''noul''' example detects if customer explicitly requests a refund.

Example call:
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-....

# Execute the actual call:
curl --fail-with-body -sS \
https://llm.stoney-cloud.com/v1/systemone \
-H "apikey: $STONEY_KEY" \
-H 'Content-Type: application/json' \
--data-binary '{
"model": "jaredpalmer/kev-27b",
"state": {
"document": "Meine Rechnung wurde zweimal belastet. Bitte erstatten Sie mir die zweite Zahlung zurück."
},
"questions": {
"refund_requested": {
"type": "noul",
"instructions": "Does the customer explicitly request a refund?",
"criteria": {
"true": "The customer explicitly asks for money to be returned.",
"false": "The customer does not ask for money to be returned."
}
}
}
}' | jq .
</syntaxhighlight>

Example answer:
<syntaxhighlight lang="json">
"model": "jaredpalmer/kev-27b",
"answers": {
"refund_requested": {
"type": "noul",
"noul": 0.9851
}
},
"usage": {
"input_tokens": 60,
"output_tokens": 23,
"prompt_tokens": 60,
"completion_tokens": 23
},
"latency_ms": 86.9
}
</syntaxhighlight>

== Usage - Score ==
The following '''score''' example estimates the urgency of a support request. The criteria is arranged from lowest to highest.

Example call:
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-....

# Execute the actual call:
curl --fail-with-body -sS \
https://llm.stoney-cloud.com/v1/systemone \
-H "apikey: $STONEY_KEY" \
-H 'Content-Type: application/json' \
--data-binary '{
"model": "jaredpalmer/kev-27b",
"state": {
"document": "Unser gesamtes Produktionssystem ist ausgefallen. Alle Kunden sind betroffen und können keine Bestellungen aufgeben. Wir benötigen sofort Hilfe."
},
"questions": {
"urgency": {
"type": "score",
"instructions": "How urgent is this support request?",
"criteria": [
"Not urgent: informational request with no operational impact",
"Low urgency: minor inconvenience with a workaround",
"Moderate urgency: partial disruption affecting some users",
"High urgency: major disruption requiring prompt attention",
"Critical urgency: complete production outage affecting all customers"
]
}
}
}' | jq .
</syntaxhighlight>

Example answer:
<syntaxhighlight lang="json">
{
"model": "jaredpalmer/kev-27b",
"answers": {
"urgency": {
"type": "score",
"score": 3.9722,
"legend": {
"0": "Not urgent: informational request with no operational impact",
"1": "Low urgency: minor inconvenience with a workaround",
"2": "Moderate urgency: partial disruption affecting some users",
"3": "High urgency: major disruption requiring prompt attention",
"4": "Critical urgency: complete production outage affecting all customers"
},
"probabilities": {
"0": 0.0001,
"1": 0.0001,
"2": 0.0003,
"3": 0.0264,
"4": 0.9731
},
"confidence": 0.9769
}
},
"usage": {
"input_tokens": 91,
"output_tokens": 162,
"prompt_tokens": 91,
"completion_tokens": 162
},
"latency_ms": 99.0
}
</syntaxhighlight>

[[Category:AI on Demand]]
[[Category: System One decision models]]

Category:System One decision models

2026-10-18T09:17:11Z

Sst-mei: Created page with "Category: AI on Demand"

[[Category: AI on Demand]]

AI on demand: jaredpalmer/kev-27b

2026-10-18T09:16:33Z

Sst-mei: /* Usage - Score */

Category:AI on demand

2026-10-18T09:14:31Z

Sst-mei: Sst-mei moved page Category:AI on demand to Category:AI on Demand

#REDIRECT [[:Category:AI on Demand]]

Category:AI on Demand

2026-10-18T09:14:31Z

Sst-mei: Sst-mei moved page Category:AI on demand to Category:AI on Demand

= Overview =
This category collects all AI on demand related pages.

stepping stone AG is proud to serve customers with current language models and OCR solutions.

All of our LLM services are reachable via the OpenAI-compatible gateway at https://llm.stoney-cloud.com/.

Check out the [[AI on demand: Usage]] page. You can list the models, show your own usage information, etc.

[[Category: Artificial Intelligence]]

Main Page

2026-10-18T09:10:51Z

Sst-mei: /* Overview */

<div style="float:left; width:48%;">
== Introduction ==
Welcome to the wiki of our [https://www.openstack.org/ OpenStack] based [https://www.stoney-cloud.com/ stoney cloud] infrastructure.
This collection serves as a comprehensive resource for all aspects of our cloud environment. Here, you will find guides for managing and utilizing our stoney cloud.

== OpenStack - Getting started ==
[[Quickstart|OpenStack quick start guide]]

== OpenStack - Usage ==
[[:Category:Projects|Projects]]

[[:Category:Instances|Instances]]
* [[VM creation (Linux)]]
* [[VM creation (Windows)]]
* [[VM resize (Linux)]]
* [[VM resize (Windows)]]
* [[Flavor explanation]]
[[:Category:Volumes|Volumes]]
* [[Quota]]

[[:Category:Images|Images]]
* [[Image creation]]
[[:Category:Network|Network]]
* [[Security group rules]]
* [[IP usage]]

[[:Category:Object store|Object store]]
* [[S3 buckets]]

[[:Category:Kubernetes|Kubernetes]]
* [[Kubernetes management]]
* [[Kubernetes usage]]

[[:Category:Backup|Backup]]
* [[Kopia restore process]]
[[:Category:Troubleshooting|Troubleshooting]]
* [[PCI workaround]]
* [[Change user password]]

</div>

<div style="float:right; width:48%">

== Artificial Intelligence (AI) ==
[[:Category:AI on demand|AI on demand]]
* [[AI on demand: Usage]] (list models, show usage, ...)
* [[AI on demand: allenai/olmOCR-2-7B]]
* [[AI on demand: apertus-ai/Apertus-v1.5-8B]]
* [[AI on demand: BAAI/bge-m3]]
* [[AI on demand: BAAI/bge-reranker-v2-m3]]
* [[AI on demand: black-forest-labs/FLUX.1-schnell]]
* [[AI on demand: convaiinnovations/laya]]
* [[AI on demand: deepseek-ai/DeepSeek-V4-Flash-0731]]
* [[AI on demand: google/gemma-4-31B-it]]
* [[AI on demand: jaredpalmer/kev-27b]]
* [[AI on demand: lightonai/LightOnOCR-2-1B]]
* [[AI on demand: Mapika/decider-31b]]
* [[AI on demand: MiniMaxAI/MiniMax-M2.5]]
* [[AI on demand: mistralai/Voxtral-Mini-3B-2507]]
* [[AI on demand: NVIDIA/NVIDIA-Nemotron-3-Super-120B-A12B]]
* [[AI on demand: openai/gpt-oss-120b]]
* [[AI on demand: openai/whisper-large-v3]]
* [[AI on demand: opendatalab/MinerU2.5-2509-1.2B]]
* [[AI on demand: Qwen/Qwen3-Coder-Next]]
* [[AI on demand: Qwen/Qwen3.5-35B-A3B-FP8]]
* [[AI on demand: Qwen/Qwen3.8-27B]]
* [[AI on demand: zai-org/GLM-5.3-Flash]]

== Quick links ==
* [https://www.stoney-cloud.com/ stoney cloud Website]
* [https://dashboard.stoney-cloud.com/ stoney cloud Dashboard]
* [https://docs.openstack.org/horizon/latest/user/index.html Official OpenStack Dashboard Documentation]
* [https://docs.openstack.org/python-openstackclient/latest/cli/index.html Official OpenStack CLI Documentation]
</div>

<div style="clear:both; height:0px; line-height:0px;"></div>

__NOTOC__