All Models
| Model | Model ID | Input Cost | Output Cost | Context | Max Output | Capabilities |
|---|---|---|---|---|---|---|
| Llama 3.1 8B Instant llama | llama-3.1-8b-instant | $0.05/MTok | $0.08/MTok | 131.1K | 131.1K | Tools Open |
| Llama 3 8B llama | llama3-8b-8192 | $0.05/MTok | $0.08/MTok | 8.2K | 8.2K | Tools Open |
| GPT OSS 20B gpt-oss | openai/gpt-oss-20b | $0.07/MTok | $0.30/MTok | 131.1K | 65.5K | Reasoning Tools Open |
| Llama 4 Scout 17B llama | meta-llama/llama-4-scout-17b-16e-instruct | $0.11/MTok | $0.34/MTok | 131.1K | 8.2K | Tools Open |
| GPT OSS 120B gpt-oss | openai/gpt-oss-120b | $0.15/MTok | $0.60/MTok | 131.1K | 65.5K | Reasoning Tools Open |
| Llama Guard 3 8B llama | llama-guard-3-8b | $0.20/MTok | $0.20/MTok | 8.2K | 8.2K | Open |
| Gemma 2 9B gemma | gemma2-9b-it | $0.20/MTok | $0.20/MTok | 8.2K | 8.2K | Tools Open |
| Llama Guard 4 12B llama | meta-llama/llama-guard-4-12b | $0.20/MTok | $0.20/MTok | 131.1K | 1.0K | Open |
| Llama 4 Maverick 17B llama | meta-llama/llama-4-maverick-17b-128e-instruct | $0.20/MTok | $0.60/MTok | 131.1K | 8.2K | Tools Open |
| Qwen QwQ 32B qwen | qwen-qwq-32b | $0.29/MTok | $0.39/MTok | 131.1K | 16.4K | Reasoning Tools Open |
| Qwen3 32B qwen | qwen/qwen3-32b | $0.29/MTok | $0.59/MTok | 131.1K | 16.4K | Reasoning Tools Open |
| Llama 3 70B llama | llama3-70b-8192 | $0.59/MTok | $0.79/MTok | 8.2K | 8.2K | Tools Open |
| Llama 3.3 70B Versatile llama | llama-3.3-70b-versatile | $0.59/MTok | $0.79/MTok | 131.1K | 32.8K | Tools Open |
| DeepSeek R1 Distill Llama 70B deepseek-thinking | deepseek-r1-distill-llama-70b | $0.75/MTok | $0.99/MTok | 131.1K | 8.2K | Reasoning Tools Open |
| Mistral Saba 24B mistral | mistral-saba-24b | $0.79/MTok | $0.79/MTok | 32.8K | 32.8K | Tools |
| Kimi K2 Instruct kimi | moonshotai/kimi-k2-instruct | $1.00/MTok | $3.00/MTok | 131.1K | 16.4K | Tools Open |
| Kimi K2 Instruct 0905 kimi | moonshotai/kimi-k2-instruct-0905 | $1.00/MTok | $3.00/MTok | 262.1K | 16.4K | Tools Open |