Groq (host) · LLMs & Coding

Prompt Guard 2 86M

Catalog data · checked Nov 16, 2026

Prompt Guard 2 86M is a language model from Groq (host), released in April 2025. It reads text and writes text, with a context window of 512 tokens and up to 512 output tokens per answer. It costs $0.04 per million input tokens and $0.04 per million output tokens. That makes it cheaper than 99% of the 185 paid language models we track.

Calculate my costCompare

Input price$0.04per 1M tokens
Output price$0.04per 1M tokens
Context window512tokens per request
Max output512tokens per answer
ReleasedApr 2025Apr 2025
WeightsOpencan be self-hosted

What it can do

  • Tool calling
  • Structured output
  • Reasoning mode
  • Image input
  • File input
  • Audio input
  • Video input
  • Image output
  • Audio output
  • Prompt caching

What it costs in practice

1,000 support replies1,000 chats with 800 input and 250 output tokens each$0.042
Summarize a 300-page reportabout 150,000 input tokens in one request, 2,000 tokens outtoo long
10,000 product descriptions300 input and 200 output tokens per text$0.2
One day of agentic codingabout 3M input and 150K output tokens across many calls$0.126

Calculated from the list prices above. Your bill depends on your real token counts. Use your own numbers →

Compare Prompt Guard 2 86M with

Questions & answers

How much does Prompt Guard 2 86M cost?

Prompt Guard 2 86M costs $0.04 per 1 million input tokens and $0.04 per 1 million output tokens (USD, list price checked Nov 16, 2026).

How large is the context window of Prompt Guard 2 86M?

Prompt Guard 2 86M can process up to 512 tokens per request and return up to 512 tokens. As a rule of thumb, 1,000 tokens are about 750 English words.

Does Prompt Guard 2 86M support tool calling?

No tool calling is listed for this model in the catalog.

Can Prompt Guard 2 86M read images?

No, this model accepts text only.