Provider Models
STACKIT LLM Models
Compare STACKIT models with normalized token pricing, context window limits, modalities, and capability metadata. This page is optimized for provider-level model research.
10 active models listed. Open all STACKIT models filters
| Model | Context | Input Price | Output Price |
|---|---|---|---|
|
E5 Mistral 7B
stackit/intfloat/e5-mistral-7b-instruct
|
4,096 | $0.02/1M | $0.02/1M |
|
Gemma 3 27B
stackit/google/gemma-3-27b-it
|
37,000 | $0.49/1M | $0.71/1M |
|
GPT-OSS 120B
stackit/openai/gpt-oss-120b
|
131,000 | $0.49/1M | $0.71/1M |
|
GPT OSS 20B
stackit/openai/gpt-oss-20b
|
131,072 | $0.18/1M | $0.29/1M |
|
Llama 3.1 8B
stackit/neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8
|
128,000 | $0.16/1M | $0.27/1M |
|
Llama 3.3 70B
stackit/cortecs/Llama-3.3-70B-Instruct-FP8-Dynamic
|
128,000 | $0.49/1M | $0.71/1M |
|
Mistral Nemo
stackit/neuralmagic/Mistral-Nemo-Instruct-2407-FP8
|
128,000 | $0.49/1M | $0.71/1M |
|
Qwen3.6 27B
stackit/Qwen/Qwen3.6-27B
|
262,144 | $0.53/1M | $0.76/1M |
|
Qwen3-VL 235B
stackit/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8
|
218,000 | $1.64/1M | $1.91/1M |
|
Qwen3-VL Embedding 8B
stackit/Qwen/Qwen3-VL-Embedding-8B
|
32,000 | $0.09/1M | $0.09/1M |