Models
| Model | Provider | Context | Prices |
|---|---|---|---|
| llama3-8b-8192 | groq | — |
|
| llama3-groq-70b-8192-tool-use-preview | groq | — |
|
| llama3-groq-8b-8192-tool-use-preview | groq | — |
|
| mistral-saba-24b | groq | — |
|
| mixtral-8x7b-32768 | groq | — |
|
| Qwen2.5-VL 7B Instruct | qwen | 131,072 |
|
| Hermes 4 70B | nousresearch | 131,072 |
|
| INTELLECT-3-FP8 | prime-intellect | 131,072 |
|
| Qwen2.5-Coder-7B | qwen | 32,768 |
|
| NVIDIA-Nemotron-Nano-12B-v2 | nvidia | 131,072 |
|
| WizardLM-2-8x22B | alpindale | 65,535 |
|
| ERNIE-4.5-21B-A3B-PT | baidu | 120,000 |
|
| ERNIE-4.5-300B-A47B-Base-PT | baidu | 123,000 |
|
| ERNIE-4.5-VL-28B-A3B-PT | baidu | 30,000 |
|
| ERNIE-4.5-VL-424B-A47B-Base-PT | baidu | 123,000 |
|
| Meta-Llama-3-70B-Instruct | meta | 8,192 |
|
| Meta-Llama-3-8B-Instruct | meta | 8,192 |
|
| GLM-4-32B-0414 | z-ai | 32,000 |
|
| Qwen2.5-Coder-3B-Instruct | qwen | 32,768 |
|
| Qwen2.5-Coder 7B Instruct | qwen | 131,072 |
|
| Qwen3-4B-Thinking-2507 | qwen | 262,144 |
|
| DeepSeek R1 Distill Qwen 7B | deepseek | 131,072 |
|
| Gemma Sea Lion V4 27B It | aisingapore | 128,000 |
|
| Qwen-SEA-LION-v4-32B-IT | aisingapore | — |
|
| Olmo-3-7B-Instruct | allenai | — |
|