All Models
| Model | Model ID | Input Cost | Output Cost | Context | Max Output | Capabilities |
|---|---|---|---|---|---|---|
| E5 Mistral 7B mistral | intfloat/e5-mistral-7b-instruct | $0.02/MTok | $0.02/MTok | 4.1K | 4.1K | Open |
| Qwen3-VL Embedding 8B qwen | Qwen/Qwen3-VL-Embedding-8B | $0.09/MTok | $0.09/MTok | 32K | 4.1K | Open |
| Llama 3.1 8B llama | neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8 | $0.16/MTok | $0.27/MTok | 128K | 8.2K | Tools Open |
| Mistral Nemo mistral | neuralmagic/Mistral-Nemo-Instruct-2407-FP8 | $0.49/MTok | $0.71/MTok | 128K | 8.2K | Tools Open |
| Gemma 3 27B gemma | google/gemma-3-27b-it | $0.49/MTok | $0.71/MTok | 37K | 8.2K | Open |
| GPT-OSS 120B gpt | openai/gpt-oss-120b | $0.49/MTok | $0.71/MTok | 131K | 8.2K | Reasoning Tools Open |
| Llama 3.3 70B llama | cortecs/Llama-3.3-70B-Instruct-FP8-Dynamic | $0.49/MTok | $0.71/MTok | 128K | 8.2K | Tools Open |
| Qwen3-VL 235B qwen | Qwen/Qwen3-VL-235B-A22B-Instruct-FP8 | $1.64/MTok | $1.91/MTok | 218K | 8.2K | Tools Open |