Package com.tnsai.llm.providers

Class CerebrasClient

java.lang.Object

com.tnsai.llm.providers.AbstractLLMClient

com.tnsai.llm.providers.AbstractOpenAICompatibleClient

com.tnsai.llm.providers.CerebrasClient

All Implemented Interfaces:

com.tnsai.llm.LLMClient

public class CerebrasClient
extends AbstractOpenAICompatibleClient

Cerebras LLM client.

Cerebras's WSE-3 chip hosts inference at top-of-industry token throughput — reportedly 1800+ tok/s on Llama 70B. The API is OpenAI-compatible, so this client shares its wire format with GroqClient / OpenRouterClient / NvidiaNIMClient.

Default base URL is https://api.cerebras.ai/v1; supply a baseUrl parameter or set CEREBRAS_BASE_URL to route through a mirror or proxy.

Supported models (at time of writing — Cerebras's catalog evolves quickly, check the live list at inference-docs.cerebras.ai):

• llama-3.3-70b — Llama 3.3 70B (flagship; the headline-throughput model)
• llama3.1-8b — Llama 3.1 8B (fastest)
• qwen-3-32b — Qwen 3 32B

Configuration via environment variables:

• CEREBRAS_API_KEY — Required.
• CEREBRAS_BASE_URL — Optional override, defaults to https://api.cerebras.ai/v1.

Headline use case: latency-sensitive agent inner loops where the sub-second roundtrip beats a 5× cheaper but 10× slower competitor — tool-call loops in tnsai-coordination, REPL-style chat, realtime UI agents.

See Also:

• Cerebras Chat Completions API

Constructor Summary

Constructors

Constructor	Description
CerebrasClient(String model)
CerebrasClient(String model, float temperature)
CerebrasClient(String model, float temperature, Float topP, Integer maxTokens)
CerebrasClient(String model, float temperature, Integer maxTokens)
CerebrasClient(String baseUrl, String model, float temperature, Float topP, Integer maxTokens, String apiKey)
CerebrasClient(String baseUrl, String model, float temperature, Integer maxTokens, String apiKey)

Method Summary

Methods inherited from class com.tnsai.llm.providers.AbstractOpenAICompatibleClient

chat, streamChat

Methods inherited from class com.tnsai.llm.providers.AbstractLLMClient

getBaseUrl, getCallTimeoutMs, getMaxTokens, getModel, getTemperature, getTopP

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface com.tnsai.llm.LLMClient

chat, chat, chat, chat, chat, getCapabilities, getProviderName, listModels, streamChat, streamChat, streamChatWithHandler, streamChatWithHandler, streamChatWithSpec, streamChatWithSpec

Constructor Details

CerebrasClient

public CerebrasClient(String model)

CerebrasClient

public CerebrasClient(String model,
 float temperature)

CerebrasClient

public CerebrasClient(String model,
 float temperature,
 Integer maxTokens)

CerebrasClient

public CerebrasClient(String model,
 float temperature,
 Float topP,
 Integer maxTokens)

CerebrasClient

public CerebrasClient(String baseUrl,
 String model,
 float temperature,
 Integer maxTokens,
 String apiKey)

CerebrasClient

public CerebrasClient(String baseUrl,
 String model,
 float temperature,
 Float topP,
 Integer maxTokens,
 String apiKey)