Inference host prices: groq
Open-weight models served by inference hosts, with each host's price per 1M tokens (input, output). One row per model, host and quantization.
Sources for this list
- Last verified 2026-10-23T16:29:31+00:00 · https://console.groq.com/docs/models (first-party,
groq-models)
| SKU | Name | Input / 1M | Output / 1M | Cached input | Context window | Last verified | Source |
|---|---|---|---|---|---|---|---|
| meta-llama/llama-prompt-guard-2-22m/groq/unknown | meta-llama/llama-prompt-guard-2-22m via Groq | USD 0.03 | USD 0.03 | – | 2026-10-23 16:29 UTC | source | |
| meta-llama/llama-prompt-guard-2-86m/groq/unknown | meta-llama/llama-prompt-guard-2-86m via Groq | USD 0.04 | USD 0.04 | – | 2026-10-23 16:29 UTC | source | |
| openai/gpt-oss-120b/groq/unknown | openai/gpt-oss-120b via Groq | USD 0.15 | USD 0.60 | – | 2026-10-23 16:29 UTC | source | |
| openai/gpt-oss-20b/groq/unknown | openai/gpt-oss-20b via Groq | USD 0.075 | USD 0.30 | – | 2026-10-23 16:29 UTC | source | |
| openai/gpt-oss-safeguard-20b/groq/unknown | openai/gpt-oss-safeguard-20b via Groq | USD 0.075 | USD 0.30 | – | 2026-10-23 16:29 UTC | source | |
| qwen/qwen3.8-27b/groq/unknown | qwen/qwen3.8-27b via Groq | USD 0.80 | USD 4.00 | – | 2026-10-23 16:29 UTC | source |