# `ReqLLM.Providers.Meta.Llama`
[🔗](https://github.com/agentjido/req_llm/blob/main/lib/req_llm/providers/meta/llama.ex#L1)

Meta Llama native-payload helpers used by Amazon Bedrock.

Bedrock's native Llama endpoint uses a formatted `prompt`, `max_gen_len`,
`generation`, and token-count fields instead of Meta's OpenAI-compatible
Model API envelope.

# `extract_usage`

Extracts token usage from a native Llama response.

# `format_llama_prompt`

Formats messages using the Llama 3 prompt token convention.

# `format_request`

Formats a ReqLLM context into Meta's native Llama request format.

# `parse_response`

Parses a native Llama response into a ReqLLM response.

# `parse_stop_reason`

Normalizes Meta's native stop reason.

---

*Consult [api-reference.md](api-reference.md) for complete listing*