Groq (via Hugging Face)

Inference provider

Endpoints
5
Models
5

Models served

5 shown

ModelCreatorTypeIn $/1MOut $/1MContextMax outputToolsRegion
GPT OSS 20B
openai/gpt-oss-20b
OpenAIOther$0.10$0.50131KRegion not stated
GPT-OSS 120B
openai/gpt-oss-120b
OpenAIOther$0.15$0.75131KRegion not stated
Llama 3.3 70b Instruct
meta-llama/Llama-3.3-70B-Instruct
MetaOther$0.59$0.79131KRegion not stated
Llama-4-Scout-17B-16E-Instruct-FP8
meta-llama/Llama-4-Scout-17B-16E-Instruct
MetaOther$0.11$0.34131KRegion not stated
Qwen3 32B
Qwen/Qwen3-32B
Alibaba (Qwen)Other$0.29$0.59131KRegion not stated

One row per model and variant. Dated pins appear on the model page, not as separate rows. Prices are indicative; verify with the provider.