AI on demand: MinerU - Revision history

Sst-yde at 14:59, 2 April 2026

2026-04-02T14:59:14Z

← Older revision		Revision as of 16:59, 2 April 2026
Line 1:		Line 1:
	== Calling the model ==		== Calling the model ==
	<syntaxhighlight lang="bash">		<syntaxhighlight lang="bash">
	# Set your personal key		# Set your personal key:
	STONEY_KEY=sk-...		STONEY_KEY=sk-...

	# Set the desired model		# Set the desired model:
	MODEL_ID=MinerU2.5-2509-1.2B		MODEL_ID=MinerU2.5-2509-1.2B

			# Set your prompt:
			PROMPT='Describe an imaginary document.'

			# Set maximum amount of tokens:
			MAX_TOKENS=2000

	curl -s https://llm.stoney-cloud.com/v1/chat/completions \		curl -s https://llm.stoney-cloud.com/v1/chat/completions \
Line 13:		Line 19:
	"model": "'"$MODEL_ID"'",		"model": "'"$MODEL_ID"'",
	"messages": [		"messages": [
	{"role": "user", "content": "~~Describe an imaginary document.~~"}		{"role": "user", "content": "'"$PROMPT"'"}
	],		],
	"max_tokens": ~~2000~~		"max_tokens": '"$MAX_TOKENS"'
	}' \		}' \
	\| jq .		\| jq .

2026-03-30T12:53:03Z

Calling the model

2026-03-30T09:30:01Z

Calling the model

@@ Line 19: / Line 19: @@
 </syntaxhighlight>
+Example output:
 [[Category:AI on demand]]

2026-03-30T09:25:24Z

Calling a model

2026-03-30T09:25:16Z

Calling a model

← Older revision		Revision as of 11:25, 30 March 2026
Line 1:		Line 1:
	== Calling a model ==		== Calling a model ==
	~~We assume you've received your API key from us in our usual manner. The route above is available in the usual OpenAI-compatible manner.~~
	~~For instance, receiving a list of available model is done via https://llm.stoney-cloud.com/v1/models which requires you to provide your key.~~
	~~As an initial service we provide access to some OCR models.~~

	<syntaxhighlight lang="bash">		<syntaxhighlight lang="bash">
	# Set your personal key		# Set your personal key
Line 15:		Line 11:
	-H "Content-Type: application/json" \		-H "Content-Type: application/json" \
	-d '{		-d '{
	"model":"'"$MODEL_ID"'",		"model": "'"$MODEL_ID"'",
	"messages":[		"messages": [
	{"role": "user", "content": "Describe an imaginary document."}		{"role": "user", "content": "Describe an imaginary document."}
	],		],
	"max_tokens": 2000		"max_tokens": 2000
	}" \| jq .		}' \| jq .
	</syntaxhighlight>		</syntaxhighlight>

2026-03-30T09:21:56Z

← Older revision		Revision as of 11:21, 30 March 2026
Line 1:		Line 1:
	~~stepping stone AG is proud to serve customers with current Language Models and OCR solutions.~~

	~~All of our LLM services are reachable from https://llm.stoney-cloud.com/.~~

	== Calling a model ==		== Calling a model ==
	We assume you've received your API key from us in our usual manner. The route above is available in the usual OpenAI-compatible manner.		We assume you've received your API key from us in our usual manner. The route above is available in the usual OpenAI-compatible manner.

2026-03-30T09:21:24Z

Inspecting your usage

← Older revision		Revision as of 11:21, 30 March 2026
Line 27:		Line 27:
	</syntaxhighlight>		</syntaxhighlight>

	~~== Inspecting your usage ==~~

	~~<syntaxhighlight lang="bash">~~
	~~curl -s https://llm.stoney-cloud.com/v1/usage \~~
	~~-H "Authorization: Bearer $STONEY_KEY" \~~
	~~\| jq .~~
	~~</syntaxhighlight>~~

	~~We issue one key per model for now. The usage is thus per-model-per-key.~~


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

2026-03-30T09:20:27Z

Calling a model

← Older revision		Revision as of 11:20, 30 March 2026
Line 18:		Line 18:
	-H "Authorization: Bearer $STONEY_KEY" \		-H "Authorization: Bearer $STONEY_KEY" \
	-H "Content-Type: application/json" \		-H "Content-Type: application/json" \
	-d "{		-d '{
	\"model\":\"${MODEL_ID}\",		"model":"'"$MODEL_ID"'",
	\"messages\":[		"messages":[
	{\"role\":\"user\",\"content\":\"Describe an imaginary document.\"}		{"role": "user", "content": "Describe an imaginary document."}
	],		],
	\"max_tokens\":2000}" \| jq .		"max_tokens": 2000
			}" \| jq .
	</syntaxhighlight>		</syntaxhighlight>

2026-03-30T09:19:39Z

Calling a model

← Older revision		Revision as of 11:19, 30 March 2026
Line 9:		Line 9:

	<syntaxhighlight lang="bash">		<syntaxhighlight lang="bash">
	STONEY_KEY=~~<your~~-~~key-here>~~		# Set your personal key
	MODEL_ID=~~<hosted-model~~-~~name~~-~~here>~~		STONEY_KEY=sk-...

			# Set the desired model
			MODEL_ID=MinerU2.5-2509-1.2B

	curl -s https://llm.stoney-cloud.com/v1/chat/completions \		curl -s https://llm.stoney-cloud.com/v1/chat/completions \

2026-03-30T09:14:14Z

← Older revision		Revision as of 11:14, 30 March 2026
Line 1:		Line 1:
	stepping stone AG is proud to serve customers with current Language Models and OCR solutions.		stepping stone AG is proud to serve customers with current Language Models and OCR solutions.

	All of our LLM services are reachable from https://llm.stoney-cloud.com/.		All of our LLM services are reachable from https://llm.stoney-cloud.com/.

Line 25:		Line 26:

	<syntaxhighlight lang="bash">		<syntaxhighlight lang="bash">
	curl -s https://llm.stoney-cloud.com/v1/usage -H "Authorization: Bearer $STONEY_KEY" \| jq .		curl -s https://llm.stoney-cloud.com/v1/usage \
			-H "Authorization: Bearer $STONEY_KEY" \
			\| jq .
	</syntaxhighlight>		</syntaxhighlight>