IO.NET serves 11 of the models we track. We do not support bring-your-own-key for this provider yet.
| Model | Made by | Input / 1M | Output / 1M | Context |
|---|---|---|---|---|
| GPT-OSS 20B | OpenAI | $0.03 | $0.14 | 64K |
| GPT-OSS 120B | OpenAI | $0.04 | $0.4 | 131K |
| Devstral Small 2505 | Mistral | $0.05 | $0.22 | 128K |
| Llama 3.3 70b Instruct | NVIDIA | $0.13 | $0.38 | 128K |
| Llama 4 Maverick 17b 128e Instruct | NVIDIA | $0.15 | $0.6 | 430K |
| Qwen 3 Coder 480B | Qwen | $0.22 | $0.95 | 106K |
| Llama-3.2-90B-Vision-Instruct | NVIDIA | $0.35 | $0.4 | 16K |
| GLM-4.6 | Zhipu AI | $0.4 | $1.75 | 200K |
| Magistral Small 2506 | NVIDIA | $0.5 | $1.5 | 128K |
| Kimi K2 Thinking | Vertex | $0.55 | $2.25 | 33K |
| DeepSeek R1 | DeepSeek | $2 | $8.75 | 128K |
IO.NET serves 11 of the models we track, across 1 model type.
GPT-OSS 20B at $0.03 per million input tokens.
Not yet — IO.NET is not currently one of the providers Serenities supports for bring-your-own-key.
