Skip to content
Sovyron

Groq

11 modelsProvider docs

As of Nov 22, 2026, Groq lists 11 supported models in the Sovyron catalog, including Qwen3.8 27B, Canopy Labs Orpheus V1 English, Canopy Labs Orpheus Arabic Saudi, Safety GPT OSS 20B and GPT OSS 120B across the qwen, orpheus, gpt-oss-safeguard, gpt-oss, llama-prompt-guard and allam families. The cheapest rate in the table is Llama Prompt Guard 2 22M at $0.03 per 1M output tokens, the priciest Qwen3.8 27B at $4. On a 3:1 input:output blend the metered rates span $0.03–$1.6 per 1M tokens, and every price is Groq's own, normalized to USD. Offer mix: 1 free-tier offer. Open a model to compare it with the cheapest offer across all providers.

Supported models and pricing

11 of 11 models
Groq model prices in USD per 1M tokens, updated Nov 22, 2026
Model1M input1M output1M cache readContextReleasedTags
Qwen3.8 27B$0.8$4—131kAug 14, 2026
Canopy Labs Orpheus V1 English———4kDec 19, 2025
Canopy Labs Orpheus Arabic Saudi———4kDec 16, 2025
Safety GPT OSS 20B$0.075$0.3$0.0375131kOct 29, 2025
GPT OSS 120B$0.15$0.6$0.075131kAug 5, 2025
GPT OSS 20B$0.075$0.3$0.0375131kAug 5, 2025
Llama Prompt Guard 2 22M$0.03$0.03—512Apr 29, 2025
Prompt Guard 2 86M$0.04$0.04—512Apr 29, 2025
ALLaM-2-7bfreefree—4kJan 23, 2025free
Whisper Large v3 Turbo———448Oct 1, 2024
Whisper———448Nov 6, 2023