ReqLLM.Providers.Meta (ReqLLM v1.19.0)

View Source

Meta Model API provider using the OpenAI-compatible Responses API.

Meta exposes Muse models at https://api.meta.ai/v1. This provider supports text generation, streaming, reasoning effort, encrypted reasoning continuity, tool calling, structured output, and prompt-cache retention controls through ReqLLM's standard APIs.

Requests default to stateless operation with encrypted reasoning returned so ReqLLM can preserve reasoning context across tool calls and conversation turns.

Configuration

MODEL_API_KEY=your-api-key

Examples

ReqLLM.generate_text("meta:muse-spark-1.1", "Hello!")

ReqLLM.stream_text("meta:muse-spark-1.1", "Solve this carefully",
  reasoning_effort: :high,
  max_tokens: 1024
)

ReqLLM.generate_text("meta:muse-spark-1.1", "Summarize this conversation",
  provider_options: [prompt_cache_retention: "24h"]
)

Meta's native Llama payload helpers used by Amazon Bedrock live in ReqLLM.Providers.Meta.Llama.

Summary

Functions

attach(request, model_input, user_opts)

Default implementation of attach/3.

attach_stream(model, context, opts, finch_name)

Default implementation of attach_stream/4.

base_url()
build_body(request)

Default implementation of build_body/1.

decode_response(request_response)

Default implementation of decode_response/1.

decode_stream_event(event, model)

Default implementation of decode_stream_event/2.

default_base_url()
default_env_key()

Callback implementation for ReqLLM.Provider.default_env_key/0.

encode_body(request)

Default implementation of encode_body/1.

extract_usage(body) deprecated
extract_usage(body, model)

Default implementation of extract_usage/2.

format_llama_prompt(messages) deprecated
format_request(context, opts \\ []) deprecated
parse_response(body, opts) deprecated
parse_stop_reason(reason) deprecated
pre_validate_options(operation, model, opts)
prepare_request(operation, model_spec, input, opts)

Default implementation of prepare_request/4.

provider_extended_generation_schema()
provider_id()
provider_schema()
supported_provider_options()
translate_options(operation, model, opts)

Default implementation of translate_options/3.

Functions

attach(request, model_input, user_opts)

Default implementation of attach/3.

Sets up Bearer token authentication and standard pipeline steps.

attach_stream(model, context, opts, finch_name)

Default implementation of attach_stream/4.

Builds complete streaming requests using OpenAI-compatible format.

base_url()

build_body(request)

Default implementation of build_body/1.

Builds request body using OpenAI-compatible format for chat and embedding operations.

decode_response(request_response)

Default implementation of decode_response/1.

Handles success/error responses with standard ReqLLM.Response creation.

decode_stream_event(event, model)

Default implementation of decode_stream_event/2.

Decodes SSE events using OpenAI-compatible format.

default_base_url()

default_env_key()

Callback implementation for ReqLLM.Provider.default_env_key/0.

encode_body(request)

Default implementation of encode_body/1.

Encodes request body using OpenAI-compatible format for chat and embedding operations.

extract_usage(body)

This function is deprecated. Use ReqLLM.Providers.Meta.Llama.extract_usage/1.

extract_usage(body, model)

Default implementation of extract_usage/2.

Extracts usage data from standard usage field in response body.

format_llama_prompt(messages)

This function is deprecated. Use ReqLLM.Providers.Meta.Llama.format_llama_prompt/1.

format_request(context, opts \\ [])

This function is deprecated. Use ReqLLM.Providers.Meta.Llama.format_request/2.

parse_response(body, opts)

This function is deprecated. Use ReqLLM.Providers.Meta.Llama.parse_response/2.

parse_stop_reason(reason)

This function is deprecated. Use ReqLLM.Providers.Meta.Llama.parse_stop_reason/1.

pre_validate_options(operation, model, opts)

prepare_request(operation, model_spec, input, opts)

Default implementation of prepare_request/4.

Handles :chat, :object, and :embedding operations using OpenAI-compatible patterns.

provider_extended_generation_schema()

provider_id()

provider_schema()

supported_provider_options()

translate_options(operation, model, opts)

Default implementation of translate_options/3.

Pass-through implementation that returns options unchanged.