Models
Models
Open models on Apple Silicon.
Each model has a page with its context length, capabilities, and the rate it bills at. Comparisons pair models of a similar size or from the same family.
Whether a model is loaded on a node right now changes through the day; the pricing page shows it live. A model that is not loaded answers 404 until an operator loads it.
| Model | Parameters | Context | Capabilities | Input / 1M | Output / 1M |
|---|---|---|---|---|---|
| Llama 3.2 1B llama-3.2-1b | 1B | 128K | Text | - | - |
| Llama 3.2 3B llama-3.2-3b | 3B | 128K | Text | - | - |
| Llama 3.1 8B llama-3.1-8b | 8B | 128K | Text | - | - |
| Llama 3.1 70B llama-3.1-70b | 70B | 128K | Text | - | - |
| Llama 3.3 70B llama-3.3-70b | 70B | 128K | Text | - | - |
| DeepSeek V3.1 deepseek-v3.1 | 671B MoE | 128K | Text, Reasoning, and Reasoning can be switched off | - | - |
| DeepSeek V3.2 deepseek-v3.2 | 671B MoE | 128K | Text, Reasoning, and Reasoning can be switched off | - | - |
| Qwen3 235B qwen3-235b | 235B MoE | 256K | Text, Reasoning, and Reasoning can be switched off | - | - |
| Qwen3-VL 4B qwen3-vl-4b | 4B | 256K | Text, Reasoning, and Image input | - | - |
| Kimi K2 Thinking kimi-k2-thinking | 1T MoE | 256K | Text, Reasoning, and Reasoning can be switched off | - | - |
| GLM 4.7 glm-4.7 | 355B MoE | 198K | Text, Reasoning, and Reasoning can be switched off | - | - |
| GPT-OSS 20B gpt-oss-20b | 20B | 128K | Text and Reasoning | - | - |
| GPT-OSS 120B gpt-oss-120b | 120B | 128K | Text and Reasoning | - | - |
The published rates could not be loaded just now. The pricing page reads them live.
Comparisons
Pairs of models in the same size class, or neighbours in size within one family.
- Llama 3.2 1B vs Llama 3.2 3B
- Llama 3.2 1B vs Qwen3-VL 4B
- Llama 3.2 3B vs Qwen3-VL 4B
- Llama 3.1 8B vs GPT-OSS 20B
- Llama 3.1 70B vs Llama 3.3 70B
- Llama 3.1 70B vs GPT-OSS 120B
- Llama 3.3 70B vs GPT-OSS 120B
- DeepSeek V3.1 vs DeepSeek V3.2
- DeepSeek V3.1 vs Qwen3 235B
- DeepSeek V3.1 vs Kimi K2 Thinking
- DeepSeek V3.1 vs GLM 4.7
- DeepSeek V3.2 vs Qwen3 235B
- DeepSeek V3.2 vs Kimi K2 Thinking
- DeepSeek V3.2 vs GLM 4.7
- Qwen3 235B vs Kimi K2 Thinking
- Qwen3 235B vs GLM 4.7
- Kimi K2 Thinking vs GLM 4.7
- Llama 3.2 3B vs Llama 3.1 8B
- Llama 3.1 8B vs Llama 3.1 70B
- GPT-OSS 20B vs GPT-OSS 120B
About these figures
Context length, capabilities, and weights size come from the model card each id is served with. Rates are the published per-token prices, refreshed every few minutes. There are no speed figures here: the network does not publish per-model throughput yet.