All Providers
5 Models
4 Families
1.0M Max Context
$0.05–$2 Input Cost/MTok
$0.15–$6 Output Cost/MTok
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Setup
Set the following environment variable to use RunInfra:
RUNINFRA_GATEWAY_KEY Models (5)
| Model | Model ID | Input Cost | Output Cost | Context | Capabilities |
|---|---|---|---|---|---|
| Nemotron 3.5 Lightning 30B A3B nemotron | nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 | $0.05/MTok | $0.15/MTok | 262.1K | Reasoning Tools Open |
| Qwen3.8 27B qwen | Qwen/Qwen3.8-27B | $0.10/MTok | $0.40/MTok | 262.1K | Reasoning Tools Open |
| DeepSeek V4 Flash 0731 deepseek-flash | deepseek-ai/DeepSeek-V4-Flash-0731 | $0.13/MTok | $0.27/MTok | 1.0M | Reasoning Tools Open |
| DeepSeek V4 Pro 0813 deepseek-thinking | deepseek-ai/DeepSeek-V4-Pro-0813 | $0.60/MTok | $1.90/MTok | 1.0M | Reasoning Tools |
| Qwen3.8 2.4T A95B (NVFP4) qwen | Inferact/Qwen3.8-2.4T-A95B-NVFP4 | $2/MTok | $6/MTok | 262.1K | Reasoning Tools Open |