Groq Pricing
Groq charges from $0.030 per 1 million output tokens, depending on the model. Llama Prompt Guard 2 22M is the cheapest at $0.030/1M output and $0.030/1M input; its current flagship Qwen3.8 27B costs $4.00/1M output. The largest context window is 131K tokens (GPT OSS 120B). Prices are USD, current as of October 12, 2026.
Last updated · synced weekly from the upstream model catalog
Cheapest input
$0.030/1M
Llama Prompt Guard 2 22M
Cheapest output
$0.030/1M
Llama Prompt Guard 2 22M
Longest context
131K
GPT OSS 120B
Models priced
16
Avg $0.913/1M output
Pricing by model
All prices in USD per 1 million tokens. All 16 priced models, cheapest first.
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| Llama Prompt Guard 2 22M | $0.030 | $0.030 | 512 |
| Meta Llama Llama Prompt Guard 2 22M | $0.030 | $0.030 | 512 |
| Meta Llama Llama Prompt Guard 2 86M | $0.040 | $0.040 | 512 |
| Prompt Guard 2 86M | $0.040 | $0.040 | 512 |
| Llama 3.1 8B Tools | $0.050 | $0.080 | 131K |
| Llama Guard 3 8B | $0.200 | $0.200 | 8K |
| GPT OSS 20B ReasoningToolsCache | $0.075 | $0.300 | 131K |
| OpenAI GPT Oss 20B | $0.075 | $0.300 | 131K |
| OpenAI GPT Oss Safeguard 20B | $0.075 | $0.300 | 131K |
| Safety GPT OSS 20B ReasoningTools | $0.075 | $0.300 | 131K |
| GPT OSS 120B ReasoningToolsCache | $0.150 | $0.600 | 131K |
| OpenAI GPT Oss 120B | $0.150 | $0.600 | 131K |
| Llama 3.3 70B Tools | $0.590 | $0.790 | 131K |
| Qwen3.6 27B VisionReasoningToolsCache | $0.600 | $3.00 | 131K |
| Qwen Qwen3.8 27B | $0.800 | $4.00 | 131K |
| Qwen3.8 27B VisionReasoningTools | $0.800 | $4.00 | 131K |
Frequently asked questions
How much does Groq cost per 1M tokens?
Groq pricing starts at $0.030 per 1 million output tokens (Llama Prompt Guard 2 22M) across 16 models, with its current flagship Qwen3.8 27B at $4.00. Older premium models in the catalog list higher. Rates current as of October 12, 2026.
What is the cheapest Groq model?
Llama Prompt Guard 2 22M is the cheapest Groq model on both axes — $0.030 per 1M input tokens and $0.030 per 1M output. It is the right default for high-volume, low-complexity work such as classification, extraction and routing.
What is the largest Groq context window?
GPT OSS 120B has the largest context window in the Groq catalog at 131K input tokens, with up to 66K output tokens per response.
Does Groq support prompt caching?
Yes. GPT OSS 20B reads cached input at $0.037 per 1M tokens, against $0.075 per 1M uncached. Caching pays off when a long system prompt or document is reused across many requests.
Which Groq models support reasoning or vision?
The Groq catalog includes 5 reasoning models, 2 vision models, 7 with tool calling. Reasoning models bill their internal thinking as output tokens, so they cost more per visible response than the headline rate suggests.
How do I calculate my actual Groq bill?
Multiply your input tokens by the input rate and your output tokens by the output rate, both per million, then add retries and any conversation history resent on each turn. Calcaas does this against your real usage pattern and shows the margin left at your price point.
Other providers
What will this actually cost you?
Per-token rates only tell you half the story. Calcaas multiplies them by your real usage — prompt size, response length, retries and conversation history — then shows the margin left at your price point.
Open the free cost calculator