Models
Showing 1–11 of 11 · Sorted by input price, low to high.
| Model | Provider | Modality | Input ↑ | Output | Context |
|---|---|---|---|---|---|
| ALLaM-2-7b | Groq | text | Not published— | Not published— | 4K |
| Canopy Labs Orpheus Arabic Saudi | Groq | text | Not published— | Not published— | 4K |
| Canopy Labs Orpheus V1 English | Groq | text | Not published— | Not published— | 4K |
| GPT OSS 120B | Groq | text | Not published— | Not published— | 131K |
| GPT OSS 20B | Groq | text | Not published— | Not published— | 131K |
| Llama Prompt Guard 2 22M | Groq | text | Not published— | Not published— | 512 |
| Prompt Guard 2 86M | Groq | text | Not published— | Not published— | 512 |
| Qwen/Qwen3.8-27B | Groq | text | Not published— | Not published— | 131K |
| Safety GPT OSS 20B | Groq | text | Not published— | Not published— | 131K |
| Whisper | Groq | audio | Not published— | Not published— | 448 |
| Whisper Large V3 Turbo | Groq | audio | Not published— | Not published— | 448 |
Token rates are USD per 1M tokens. A dash means the source did not publish that amount. A zero is a real zero.