Llama Guard 3 8B
meta/llama-guard-3-8bPor Meta · família: llama · lançado 2024-04-18
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Capacidades
Model fit scores
0–100 · higher is betterThese scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.
Coding3
- Tool calling0/40
- Structured output0/20
- Reasoning0/10
- Context window (100K → 1M)0/20
- Provider availability3/10
Agents8
- Tool calling0/35
- Structured output0/25
- Reasoning0/15
- Output token limit5/15
- Provider availability3/10
JSON / structured output30
- Structured output / JSON mode0/50
- Tool calling0/20
- Temperature control10/10
- Price-friendly for high-volume20/20
Cost efficiency89
- Headline price (log-scaled)89/95
- Has prompt-cache pricing0/5
Long context0
- Context ≥ 100K0/100
Production-readiness64
- Number of independent providers15/40
- Has published per-token price20/20
- Context window ≥ 8K8/15
- No data inconsistencies across providers6/10
- Official model (not derivative)15/15
Cost Efficiency Index
Open full calculator →Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.
| Scenario | Cost | Assumption |
|---|---|---|
RAG answer per 1,000 RAG answers | $0.13 < $0.01 per request | 5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot. |
Support ticket triage per 10,000 tickets | $0.26 < $0.01 per request | 1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support. |
Data extraction per 1,000 documents | $0.07 < $0.01 per request | 2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines. |
Code review per 1,000 PRs | $0.22 < $0.01 per request | 8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads. |
Agent step per 1,000 steps | $0.28 < $0.01 per request | 12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step. |
Detalhes de preço
Preço recomendado de kilo · meta-llama/llama-guard-3-8b
Disponível em 3 provedores
| Provedor | ID do modelo do provedor | Entrada / 1M | Saída / 1M | Contexto | Lançado |
|---|---|---|---|---|---|
| Groq groq | llama-guard-3-8b | $0.200 | $0.200 | 8K | 2024-07-23 |
| Kilo Gateway kilo | meta-llama/llama-guard-3-8b | $0.020 | $0.060 | 131K | 2024-04-18 |
| Cloudflare AI Gateway cloudflare-ai-gateway | workers-ai/@cf/meta/llama-guard-3-8b | $0.480 | $0.030 | 128K | 2025-04-03 |
Inconsistências de dados entre provedores
- context_window varies: 128000, 131072, 8192
- release_date varies (span 350d): 2024-04-18, 2024-07-23, 2025-04-03
Os provedores reportam valores diferentes para este modelo. Os dados rápidos acima usam um provedor representativo; consulte a tabela para detalhes por provedor.
Frequently asked questions
How much does Llama Guard 3 8B cost?
Llama Guard 3 8B costs $0.020 per 1M input tokens and $0.060 per 1M output tokens, sourced from kilo. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.
What is the context window of Llama Guard 3 8B?
Llama Guard 3 8B has a context window of 8K tokens, with a max output of 8K tokens per reply. This is the total combined size of prompt + completion.
Does Llama Guard 3 8B support tool calling?
No. Llama Guard 3 8B does not support tool calling (function calling). If your workflow requires it, look at the /capabilities/tool-calling list for alternatives.
Does Llama Guard 3 8B support structured output / JSON mode?
Support for structured output / JSON-schema-constrained decoding is not reported for Llama Guard 3 8B in our data source. Verify with Meta's official documentation before relying on it in production.
Can Llama Guard 3 8B accept image input?
No. Llama Guard 3 8B only accepts text as input. If you need image input, see our /capabilities/vision list for current vision-capable models.
Is Llama Guard 3 8B open-weight?
Yes. Llama Guard 3 8B's weights are publicly available, so you can self-host or fine-tune. Note that open weights ≠ open source — the training data and code are typically not released.
What are the best alternatives to Llama Guard 3 8B?
If Llama Guard 3 8B doesn't fit, consider Meta-Llama-3.1-8B-Instruct, Llama-3.3-70B-Instruct, Llama 4 Maverick 17B 128E Instruct FP8. Each one targets the same use case — see the Related links below for direct head-to-head pages.
Where does this data come from?
All numbers come from the public models.dev API and are normalised into a single canonical model record. We re-pull daily and write any changes (price, context, capability) to the /changelog page.
Explore more
More Meta models
- Meta-Llama-3.1-8B-Instruct$0.02 in / $0.03 out
- Llama-3.3-70B-Instruct$0.05 in / $0.23 out
- Llama 4 Maverick 17B 128E Instruct FP8$0.14 in / $0.59 out
- Llama 4 Scout 17B 16E Instruct$0.08 in / $0.30 out
- Meta-Llama-3.1-70B-Instruct$0.40 in / $0.40 out
Capability lists this model is in
Última atualização:
Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.