Meta: Llama Prompt Guard 2 22M
Llama Prompt Guard 2 22M is a language model from Meta released on Oct 1, 2024. It reads text and writes text, with a 512 token context window and up to 512 tokens per reply.
Show moreShow less
It costs $0.03 per million input tokens and $0.03 per million output tokens.
Its weights are open, so you can host it yourself.
2 providers serve it, including Groq and Helicone. The lowest input price is $0.01 per million tokens at Helicone.
- Modalities
- In / out price
- $0.03 / $0.03 per 1M
- Context
- 512
- Max output
- 512
- Released
- Oct 1, 2024
- Knowledge cutoff
- n/a
- Tool calling
- Structured output
- Reasoning
- Prompt caching
- Open weights
- Free to use
Llama Prompt Guard 2 22M pricing
USD, as listed on Oct 15, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.
| Input | $0.03 / 1M tokens | |
|---|---|---|
| Output | $0.03 / 1M tokens |
Llama Prompt Guard 2 22M providers
2 providers serve it, including Groq and Helicone. The lowest input price is $0.01 per million tokens at Helicone. Each host sets its own price and limits, so the cheapest one is not always the one with the longest context.
| Provider | Input /M | Output /M | Cache read /M | Context | Max output |
|---|---|---|---|---|---|
| Groq | $0.03 | $0.03 | – | 512 | 512 |
| Helicone | $0.01 | $0.01 | – | 512 | 2 |
What Llama Prompt Guard 2 22M costs per month
Pick a workload close to yours or type your own volumes.
Alternatives to Llama Prompt Guard 2 22M
Models that take the same inputs, closest in price, cheaper ones first.
- 128K context
Reads text. Tool calling, structured output. Served by 3 providers.
by meta-llamaJul 23, 2024$0.02/M input tokens$0.05/M output tokens3 providers
- 16K context
Reads text and images.
by paddlepaddleOct 16, 2025$0.02/M input tokens$0.02/M output tokens
- 1M context
Reads text, images and files.
by scaledownOct 13, 2026$0.05/M input tokens$0/M output tokens
- 1M context
Reads text, images and files.
by scaledownOct 13, 2026$0.05/M input tokens$0/M output tokens
- 66K context
Reads text. Tool calling, reasoning. Served by 2 providers.
by sarvamFeb 18, 2026$0.02/M input tokens$0.10/M output tokens2 providers
Reads text and audio. Tool calling, structured output. Served by 2 providers.
by mistralaiJul 15, 2025$0.04/M input tokens$0.04/M output tokens2 providers
More from Meta
- 164K context
Reads text and images.
by meta-llamaApr 30, 2025$0.18/M input tokens$0.18/M output tokens
- 131K context
Reads text and images. Tool calling, structured output. Served by 5 providers.
by meta-llamaApr 5, 2025$0.20/M input tokens$0.78/M output tokens5 providers
- Index 10
Reads text and images. Tool calling, structured output. Served by 7 providers.
by meta-llamaJan 15, 20251.05M context$0.25/M input tokens$1/M output tokens7 providers
- Index 8.1
Reads text and images. Tool calling, structured output. Served by 4 providers.
by meta-llamaJan 1, 2025328K context$0.085/M input tokens$0.46/M output tokens4 providers
- 128K context
Reads text. Tool calling, structured output. Served by 3 providers.
by meta-llamaDec 6, 2024$1.35/M input tokens$1.35/M output tokens3 providers
- 24K context
Reads text. Tool calling, structured output. Served by 34 providers.
by meta-llamaDec 1, 2024$0.71/M input tokens$0.71/M output tokens34 providers
Llama Prompt Guard 2 22M questions
How much does the Llama Prompt Guard 2 22M API cost?
$0.03 per million input tokens and $0.03 per million output tokens. The estimator on this page turns that into a monthly bill for your own workload.
What is the context window of Llama Prompt Guard 2 22M?
512 tokens of input, and it can write up to 512 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.
Which providers serve Llama Prompt Guard 2 22M?
2 providers serve it, including Groq and Helicone. The lowest input price is $0.01 per million tokens at Helicone. Prices differ by host, so the Providers table on this page lists each one with its input and output price.
Does Llama Prompt Guard 2 22M support tool calling?
Not through the standard tools parameter. For an agent that calls your APIs, pick a model from the alternatives below that does.
Is Llama Prompt Guard 2 22M open source?
Its weights are published, so you can run it on your own hardware or a cloud of your choice. Read the license before commercial use.
When was Llama Prompt Guard 2 22M released?
Oct 1, 2024.
Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 15, 2026. The summary is written from these facts.
Building on Llama Prompt Guard 2 22M?
I test your real tasks on it and the two closest alternatives, then ship the agent on whichever wins on cost and accuracy.
Book Meeting