Model
Model
mistralai
A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...
| Provider | Quantization | Input / M tokens | Output / M tokens |
|---|---|---|---|
| Io Netio-net/fp16 | fp16 | $0.01656 | $0.0216 |
| DekaLLMdekallm/fp8 | fp8 | $0.018 | $0.03 |
| DeepInfradeepinfra/fp8 | fp8 | $0.029 | $0.03 |
| Parasailparasail/fp8 | fp8 | $0.03 | $0.03 |
| Mistralmistral/eu | — | $0.15 | $0.15 |
Prices are what the Provider charges, synced 2026-10-21. Amber adds its platform fee to each Trial’s total; see pricing.
Amber has no curated Model Configuration for this Model yet. Create a custom one in your Workspace to evaluate it.