MediaWiki - Recent changes [en]

AI on demand: Usage

Sst-mei — Tue, 08 Sep 2026 19:29:28 GMT

Usage - List all models - Generic

← Older revision		Revision as of 21:29, 8 September 2026
Line 61:		Line 61:
	"max_model_len": 131072,		"max_model_len": 131072,
	"id": "openai/gpt-oss-120b"		"id": "openai/gpt-oss-120b"
			},
			{
			"object": "model",
			"max_model_len": 16384,
			"id": "opendatalab/MinerU2.5-2509-1.2B"
	},		},
	{		{
Line 76:		Line 81:
	"max_model_len": 262144,		"max_model_len": 262144,
	"id": "Qwen/Qwen3-Coder-Next"		"id": "Qwen/Qwen3-Coder-Next"
			},
			{
			"object": "model",
			"max_model_len": 262144,
			"id": "zai-org/GLM-5.3-Flash"
	}		}
	],		],

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

Sst-yde — Wed, 02 Sep 2026 14:24:19 GMT

Created page with "== 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 '{ "mo..."

New page

== 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]]

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

Sst-yde — Wed, 02 Sep 2026 14:22:43 GMT

Created page with "== 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 '{..."

New page

== 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]]

Main Page

Sst-yde — Wed, 02 Sep 2026 14:21:40 GMT

Overview

← Older revision		Revision as of 16:21, 2 September 2026
Line 43:		Line 43:
	* [[AI on demand: BAAI/bge-reranker-v2-m3]]		* [[AI on demand: BAAI/bge-reranker-v2-m3]]
	* [[AI on demand: black-forest-labs/FLUX.1-schnell]]		* [[AI on demand: black-forest-labs/FLUX.1-schnell]]
			* [[AI on demand: deepseek-ai/DeepSeek-V4-Flash-0731]]
	* [[AI on demand: MiniMaxAI/MiniMax-M2.5]]		* [[AI on demand: MiniMaxAI/MiniMax-M2.5]]
	* [[AI on demand: NVIDIA/NVIDIA-Nemotron-3-Super-120B-A12B]]		* [[AI on demand: NVIDIA/NVIDIA-Nemotron-3-Super-120B-A12B]]
Line 50:		Line 51:
	* [[AI on demand: lightonai/LightOnOCR-2-1B]]		* [[AI on demand: lightonai/LightOnOCR-2-1B]]
	* [[AI on demand: mistralai/Voxtral-Mini-3B-2507]]		* [[AI on demand: mistralai/Voxtral-Mini-3B-2507]]
			* [[AI on demand: openai/gpt-oss-120b]]
	* [[AI on demand: openai/whisper-large-v3]]		* [[AI on demand: openai/whisper-large-v3]]
	* [[AI on demand: opendatalab/MinerU2.5-2509-1.2B]]		* [[AI on demand: opendatalab/MinerU2.5-2509-1.2B]]

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

Sst-yde — Wed, 02 Sep 2026 11:03:50 GMT

Calling the model

← Older revision		Revision as of 13:03, 2 September 2026
(One intermediate revision by the same user not shown)
Line 5:		Line 5:

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

	# Set the desired document to run OCR against:		# Set the desired document to run OCR against:
Line 39:		Line 39:
	<syntaxhighlight lang="json">		<syntaxhighlight lang="json">
	{		{
	"id": "chatcmpl-~~928cc308fa758fc8~~",		"id": "chatcmpl-834171fda5956922",
	"object": "chat.completion",		"object": "chat.completion",
	"created": ~~1778491655~~,		"created": 1788347006,
	"model": "MinerU2.5-2509-1.2B",		"model": "opendatalab/MinerU2.5-2509-1.2B",
	"choices": [		"choices": [
	{		{

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

Sst-yde — Wed, 02 Sep 2026 09:09:53 GMT

Calling the model

← Older revision		Revision as of 11:09, 2 September 2026
Line 11:		Line 11:

	# Set maximum amount of tokens:		# Set maximum amount of tokens:
	MAX_TOKENS=~~100~~		MAX_TOKENS=10000

	curl https://llm.stoney-cloud.com/v1/chat/completions \		curl https://llm.stoney-cloud.com/v1/chat/completions \
Line 30:		Line 30:
	<syntaxhighlight lang="json">		<syntaxhighlight lang="json">
	{		{
	"id": "chatcmpl-~~a8634d242bc04923~~",		"id": "chatcmpl-a48b0edd8e8a0153",
	"object": "chat.completion",		"object": "chat.completion",
	"created": ~~1778156754~~,		"created": 1788340157,
	"model": "Qwen/Qwen3.5-35B-A3B-FP8",		"model": "Qwen/Qwen3.5-35B-A3B-FP8",
	"choices": [		"choices": [
Line 39:		Line 39:
	"message": {		"message": {
	"role": "assistant",		"role": "assistant",
	"content": "~~Thinking Process:~~\n\n1. Analyze the Input:\n * Input: \"Hello.\"\n * Context: This is a greeting.\n * Intent: The user is initiating a conversation.\n * Tone: Friendly, polite, neutral.\n\n2. Determine the Appropriate Response:\n * Acknowledge the greeting.\n Offer assistance.\n Keep it friendly and open-ended.\n\n3. Drafting Options:\n",		"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,		"refusal": null,
	"annotations": null,		"annotations": null,
Line 45:		Line 45:
	"function_call": null,		"function_call": null,
	"tool_calls": [],		"tool_calls": [],
	"reasoning": ~~null~~		"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,		"logprobs": null,
	"finish_reason": "~~length~~",		"finish_reason": "stop",
	"stop_reason": null,		"stop_reason": null,
	"token_ids": null		"token_ids": null
Line 57:		Line 57:
	"usage": {		"usage": {
	"prompt_tokens": 12,		"prompt_tokens": 12,
	"total_tokens": ~~112~~,		"total_tokens": 631,
	"completion_tokens": ~~100~~,		"completion_tokens": 619,
	"prompt_tokens_details": null		"prompt_tokens_details": null
	},		},

AI on demand: Usage

Sst-mei — Mon, 31 Aug 2026 07:15:02 GMT

Usage - List all models - Generic

← Older revision		Revision as of 09:15, 31 August 2026
(2 intermediate revisions by the same user not shown)
Line 29:		Line 29:
	{		{
	"object": "model",		"object": "model",
	"max_model_len": ~~262144~~,		"max_model_len": 131072,
	"id": "apertus-ai/Apertus-v1.5-8B"		"id": "apertus-ai/Apertus-v1.5-8B"
			},
			{
			"object": "model",
			"max_model_len": 131072,
			"id": "deepseek-ai/DeepSeek-V4-Flash-0731"
	},		},
	{		{
Line 51:		Line 56:
	"max_model_len": 131072,		"max_model_len": 131072,
	"id": "NVIDIA/NVIDIA-Nemotron-3-Super-120B-A12B"		"id": "NVIDIA/NVIDIA-Nemotron-3-Super-120B-A12B"
			},
			{
			"object": "model",
			"max_model_len": 131072,
			"id": "openai/gpt-oss-120b"
	},		},
	{		{
Line 56:		Line 66:
	"max_model_len": 131072,		"max_model_len": 131072,
	"id": "Qwen/Qwen3.5-35B-A3B-FP8"		"id": "Qwen/Qwen3.5-35B-A3B-FP8"
			},
			{
			"object": "model",
			"max_model_len": 262144,
			"id": "Qwen/Qwen3.8-27B"
	},		},
	{		{
Line 192:		Line 207:
	<syntaxhighlight lang="json">		<syntaxhighlight lang="json">
	{		{
			"month": "2026-08",
	"models": [		"models": [
	{		{
	"cost_chf": 0.~~000002~~,		"cost_chf": 0.000019,
	"~~model~~": ~~"MinerU2.5-2509-1.2B"~~,		"output": 11,
	"~~output~~": 16,		"input": 256,
	"~~input~~": 70		"model": "allenai/olmOCR-2-7B"
	},		},
	{		{
	"cost_chf": 0.~~054537~~,		"cost_chf": 0.003268,
	"~~model~~": ~~"MiniMaxAI/MiniMax-M2.5"~~,		"output": 942,
	"~~output~~": ~~3603~~,		"input": 22679,
	"~~input~~": ~~10097~~		"model": "apertus-ai/Apertus-v1.5-8B"
	},		},
	{		{
	"cost_chf": 0.~~0016~~,		"cost_chf": 0.562569,
	"~~model~~": "~~mistralai/Voxtral-Mini-3B-2507~~",		"output": 9555,
	"~~seconds~~": 8		"input": 257397,
			"model": "NVIDIA/NVIDIA-Nemotron-3-Super-120B-A12B"
	},		},
	{		{
	"cost_chf": 0.~~003774~~,		"cost_chf": 16.6957,
	"~~model~~": ~~"swiss-ai/Apertus-70B-Instruct-2509"~~,		"output": 120992,
	"~~output~~": ~~551~~,		"input": 2734180,
	"~~input~~": ~~443~~		"model": "openai/gpt-oss-120b"
	}		}
	],		],
	~~"month": "2026-03",~~		"total_cost_chf": 17.261556
	"total_cost_chf": 0.~~059913~~
	}		}
	</syntaxhighlight>		</syntaxhighlight>

	[[Category: AI on demand]]		[[Category: AI on demand]]

Kubernetes management

Sst-yde — Thu, 13 Aug 2026 13:10:55 GMT

Troubleshooting

@@ Line 124: / Line 124: @@
 openstack coe cluster template create "$cluster_template" \
    --coe kubernetes \
    --image "$image" \
@@ Line 129: / Line 130: @@
    --master-flavor 'Standard Düdingen c002m0004' \
    --flavor 'Standard Düdingen c002m0004' \
-   --master-lb-enabled
+   --labels kube_dashboard_enabled=false
 </syntaxhighlight>
@@ Line 450: / Line 451: @@
 openstack coe cluster resize "$cluster" --nodegroup "$node_group" "$node_count"
 </syntaxhighlight>
 = Troubleshooting =

Main Page

Sst-nho — Wed, 12 Aug 2026 07:24:26 GMT

Overview

← Older revision		Revision as of 09:24, 12 August 2026
Line 40:		Line 40:
	* [[AI on demand: Usage]] (list models, show usage, ...)		* [[AI on demand: Usage]] (list models, show usage, ...)
	* [[AI on demand: apertus-ai/Apertus-v1.5-8B]]		* [[AI on demand: apertus-ai/Apertus-v1.5-8B]]
	* <s>[[AI on demand: apertus-ai/Apertus-v1.5-8B-Prerelease-2607]]</s> (discontinued since the 29th of July 2026)
	* <s>[[AI on demand: swiss-ai/Apertus-70B-Instruct-2509]]</s> (discontinued since the 7th of May 2026)
	* [[AI on demand: BAAI/bge-m3]]		* [[AI on demand: BAAI/bge-m3]]
	* [[AI on demand: BAAI/bge-reranker-v2-m3]]		* [[AI on demand: BAAI/bge-reranker-v2-m3]]

AI on demand: swiss-ai/Apertus-70B-Instruct-2509

Sst-nho — Wed, 12 Aug 2026 07:24:04 GMT

Sst-nho deleted page AI on demand: swiss-ai/Apertus-70B-Instruct-2509 content was: "'''IMPORTANT''': This model is '''discontinued''' since the 7th of May 2026! == Calling the model == <syntaxhighlight lang="bash"> # Set your personal key: STONEY_KEY=sk-... # Set the desired model: MODEL=swiss-ai/Apertus-70B-Instruct-2509 # Set your prompt: PROMPT='Say 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" \..."