Providerinference
Inference
npm install @ai-sdk/openai-compatible
9 Available ModelsOfficial Documentation ↗
Endpoint: https://inference.net/v1
Hosted Models
| Model | Lab | Context | Input / 1M | Output / 1M | Action |
|---|---|---|---|---|---|
| Llama 3.1 8B Instruct fp8 meta/llama-3.1-8b-instruct | Meta | 16,000 | $0.03 | $0.03 | Specs & Providers → |
| Llama 3.2 11B Vision Instruct meta/llama-3.2-11b-vision-instruct | Meta | 16,000 | $0.06 | $0.06 | Specs & Providers → |
| Llama 3.2 1B Instruct meta/llama-3.2-1b-instruct | Meta | 16,000 | $0.01 | $0.01 | Specs & Providers → |
| Llama 3.2 3B Instruct meta/llama-3.2-3b-instruct | Meta | 16,000 | $0.02 | $0.02 | Specs & Providers → |
| Google Gemma 3 google/gemma-3 | 125,000 | $0.15 | $0.30 | Specs & Providers → | |
| Osmosis Structure 0.6B osmosis/osmosis-structure-0.6b | Osmosis | 4,000 | $0.10 | $0.50 | Specs & Providers → |
| Mistral Nemo 12B Instruct mistral/mistral-nemo-12b-instruct | Mistral | 16,000 | $0.04 | $0.10 | Specs & Providers → |
| Qwen3-Embedding 4B qwen/qwen3-embedding-4b | Alibaba | 32,000 | $0.01 | $0.00 | Specs & Providers → |
| Qwen 2.5 7B Vision Instruct qwen/qwen-2.5-7b-vision-instruct | Alibaba | 125,000 | $0.20 | $0.20 | Specs & Providers → |