Infomaniak
Inference provider
- Endpoints
- 10
- Models
- 10
Models served
10 shown
| Model | Creator | Type | In $/1M | Out $/1M | Context | Max output | Tools | Region |
|---|---|---|---|---|---|---|---|---|
| All-MiniLM-L12-v2 mini_lm_l12_v2 | Unattributed | Embedding | Listed at $0 (unverified) | — | 128 | 384 | Region not stated | |
| Apertus v1.5 70B swiss-ai/Apertus-v1.5-70B | Swiss AI | Chat | $0.87 | $3.10 | 100K | 8.2K | Region not stated | |
| BGE Multilingual Gemma2 bge_multilingual_gemma2 | BAAI (Beijing Academy of AI) | Embedding | $0.08 | $0 | 8K | 3.6K | Region not stated | |
| Gemma-4-31B-IT google/gemma-4-31B-it | Chat | $0.25 | $0.50 | 100K | 32.8K | Region not stated | ||
| Kimi K2.6 moonshotai/Kimi-K2.6 | Moonshot AI | Chat | $0.74 | $3.72 | 256K | 256K | Region not stated | |
| Ministral 3 14B mistralai/Ministral-3-14B-Instruct-2512 | Mistral AI | Chat | $0.37 | $0.50 | 100K | 25.6K | Region not stated | |
| Mistral Small 4 mistralai/Mistral-Small-4-119B-2603 | Mistral AI | Chat | $0.25 | $0.93 | 256K | 256K | Region not stated | |
| nemotron-3-nano-30b-a3b nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8 | NVIDIA | Chat | $0.06 | $0.25 | 1M | 262K | Region not stated | |
| Qwen3.5 122B-A10B Qwen/Qwen3.5-122B-A10B-FP8 | Alibaba (Qwen) | Chat | $0.50 | $3.97 | 200K | 65.5K | Region not stated | |
| Qwen3.5 397B-A17B Qwen/Qwen3.5-397B-A17B-FP8 | Alibaba (Qwen) | Chat | $0.99 | $4.46 | 200K | 65.5K | Region not stated |
One row per model and variant. Dated pins appear on the model page, not as separate rows. Prices are indicative; verify with the provider.