ReqLLM.Providers.Cerebras (ReqLLM v1.0.0)

View Source

Cerebras provider – OpenAI-compatible Chat Completions API with ultra-fast inference.

Implementation

Uses built-in OpenAI-style encoding/decoding defaults with Cerebras-specific adjustments.

Cerebras-Specific Notes

  • System messages have stronger influence compared to OpenAI's implementation
  • Streaming not supported with reasoning models in JSON mode or tool calling
  • Requires strict: true in tool schemas for structured output (automatically added)
  • Qwen models do NOT support strict: true (automatically excluded)
  • Only supports tool_choice: "auto" or "none", not function-specific choices

Unsupported OpenAI Features

The following fields will result in a 400 error if supplied:

  • frequency_penalty
  • logit_bias
  • presence_penalty
  • parallel_tool_calls
  • service_tier

Configuration

# Add to .env file (automatically loaded)
CEREBRAS_API_KEY=csk_...

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.

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.

default_provider_opts()
encode_body(request)

Default implementation of encode_body/1.

extract_usage(body, model)

Default implementation of extract_usage/2.

metadata()
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.

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.

default_provider_opts()

encode_body(request)

Default implementation of encode_body/1.

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

extract_usage(body, model)

Default implementation of extract_usage/2.

Extracts usage data from standard usage field in response body.

metadata()

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.