IONOS

EU

11 models available

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 IONOS

11 models

Model	Context	Input /M	Output /M	TTFT	Throughput
GPT OSS 120B	131k	$0.18/M	$0.75/M	N/A	N/A
LightOnOCR 2	33k	$0.18/M	$0.35/M	N/A	327.2 tps
Llama 3.1 8B	131k	$0.18/M	$0.18/M	N/A	N/A
Llama 3.3 70B Instruct	131k	$0.75/M	$0.75/M	N/A	N/A
Mistral Small 3 24B (2501)	33k	$0.12/M	$0.35/M	1.5s	43.4 tps
Qwen3 Coder Next	262k	$0.18/M	$0.93/M	N/A	N/A
Qwen3.5 397B	262k	$0.70/M	$4.20/M	N/A	N/A
Qwen3.5 397B Thinking	262k	$0.70/M	$4.20/M	N/A	N/A
Qwen3.5 9B	262k	$0.12/M	$0.18/M	N/A	N/A
Qwen3.8 27B	262k	$0.47/M	$2.84/M	N/A	N/A
Qwen3.8 27B Thinking	262k	$0.47/M	$2.84/M	N/A	N/A

GPT OSS 120B

Context: 131k
Input /M: $0.18/M
Output /M: $0.75/M
TTFT: N/A
Throughput: N/A

LightOnOCR 2

Context: 33k
Input /M: $0.18/M
Output /M: $0.35/M
TTFT: N/A
Throughput: 327.2 tps

Llama 3.1 8B

Context: 131k
Input /M: $0.18/M
Output /M: $0.18/M
TTFT: N/A
Throughput: N/A

Llama 3.3 70B Instruct

Context: 131k
Input /M: $0.75/M
Output /M: $0.75/M
TTFT: N/A
Throughput: N/A

Mistral Small 3 24B (2501)

Context: 33k
Input /M: $0.12/M
Output /M: $0.35/M
TTFT: 1.5s
Throughput: 43.4 tps

Qwen3 Coder Next

Context: 262k
Input /M: $0.18/M
Output /M: $0.93/M
TTFT: N/A
Throughput: N/A

Qwen3.5 397B

Context: 262k
Input /M: $0.70/M
Output /M: $4.20/M
TTFT: N/A
Throughput: N/A

Qwen3.5 397B Thinking

Context: 262k
Input /M: $0.70/M
Output /M: $4.20/M
TTFT: N/A
Throughput: N/A

Qwen3.5 9B

Context: 262k
Input /M: $0.12/M
Output /M: $0.18/M
TTFT: N/A
Throughput: N/A

Qwen3.8 27B

Context: 262k
Input /M: $0.47/M
Output /M: $2.84/M
TTFT: N/A
Throughput: N/A

Qwen3.8 27B Thinking

Context: 262k
Input /M: $0.47/M
Output /M: $2.84/M
TTFT: N/A
Throughput: N/A

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 IONOS via the API

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

cURL

curl https://nano-gpt.com/api/v1/chat/completions \
  -H "Authorization: Bearer $NANOGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-oss-120b:ionos",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

For models with provider selection, append :ionos to the model ID, set "provider": "ionos" in the request body, or send an X-Provider: ionos 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.