LLM Tech

LLM Tech states that prompts and outputs are processed only in volatile memory with zero content retention and are not used for training. Its current EU path uses a Hetzner edge in Nuremberg, Germany, and a dedicated GPU deployment rented from Seeweb S.r.l. in Italy.

Data handling can vary by model and deployment. The privacy badge above shows the more conservative of the provider-wide fallback and the policies for routes on this page; each model page shows the policy for that specific route.

Models served by LLM Tech

Model name

Model	Context	Input /M	Output /M	Cache read /M	TTFT	Throughput
Qwen3.8 27B NVFP4 qwen3.8-27b:llmtech	262k	$0.15/M	$0.701/M	$0.0399/M	0.2s	61.6 tps
Qwen3.8 27B Thinking NVFP4 qwen3.8-27b:thinking:llmtech	262k	$0.15/M	$0.701/M	$0.0399/M	0.2s	61.6 tps

Qwen3.8 27B

NVFP4

qwen3.8-27b:llmtech

Context

262k

Input /M

$0.15/M

Output /M

$0.701/M

Cache read /M

$0.0399/M

TTFT

0.2s

Throughput

61.6 tps

Qwen3.8 27B Thinking

NVFP4

qwen3.8-27b:thinking:llmtech

Context

262k

Input /M

$0.15/M

Output /M

$0.701/M

Cache read /M

$0.0399/M

TTFT

0.2s

Throughput

61.6 tps

Prices are per million tokens. TTFT is the observed time to first token. Selectable routes include the applicable provider-selection markup; fixed routes show the standard model price. Availability and pricing refresh continuously; each model page shows the live provider comparison.

Using LLM Tech via the API

Call a model served by LLM Tech using its displayed model ID, including the provider suffix when selection is supported.

curl https://nano-gpt.com/api/v1/chat/completions \
  -H "Authorization: Bearer $NANOGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3.8-27b:llmtech",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

For models with provider selection, append :llmtech to the model ID, set "provider": "llmtech" in the request body, or send an X-Provider: llmtech header. Explicit provider selection adds a route-specific markup over that provider's base price; the prices in the table above already include it. Models without provider selection use the displayed model ID without a provider suffix or selection surcharge.

See the API documentation for provider preferences, price-aware routing, and error behavior.