Package com.tnsai.llm.providers

Class FireworksAIClient

java.lang.Object

com.tnsai.llm.providers.AbstractLLMClient

com.tnsai.llm.providers.AbstractOpenAICompatibleClient

com.tnsai.llm.providers.FireworksAIClient

All Implemented Interfaces:

com.tnsai.llm.LLMClient

public class FireworksAIClient
extends AbstractOpenAICompatibleClient

Fireworks.ai LLM client.

Fireworks hosts open models behind an OpenAI-compatible API at https://api.fireworks.ai/inference/v1. The wire format matches every other OpenAI-shape provider in this module (GroqClient, OpenRouterClient, NvidiaNIMClient, XAIGrokClient, CerebrasClient, TogetherAIClient), so this client is a thin same-shape addition.

Distinguishes itself with firefunction-v2 — a function-calling-tuned model that tops the Berkeley Function Calling Leaderboard for open-weight tool-use accuracy. Mention this in the model field to route a tool-use loop specifically at FireFunction.

Supported models (at time of writing — the catalogue evolves quickly, check the live list at fireworks.ai/models):

• accounts/fireworks/models/firefunction-v2 — function-calling-tuned (FireFunction)
• accounts/fireworks/models/llama-v3p3-70b-instruct — Llama 3.3 70B
• accounts/fireworks/models/llama-v3p1-405b-instruct — Llama 3.1 405B (frontier)
• accounts/fireworks/models/llama-v3p1-8b-instruct — Llama 3.1 8B (fast / cheap)
• accounts/fireworks/models/mixtral-8x7b-instruct — Mixtral 8x7B
• accounts/fireworks/models/qwen2p5-72b-instruct — Qwen 2.5 72B
• accounts/fireworks/models/deepseek-v3 — DeepSeek V3

Configuration via environment variables:

• FIREWORKS_API_KEY — Required.
• FIREWORKS_BASE_URL — Optional override, defaults to https://api.fireworks.ai/inference/v1.

See Also:

• Fireworks Chat Completions API

Constructor Summary

Constructors

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

FireworksAIClient

public FireworksAIClient(String model)

FireworksAIClient

public FireworksAIClient(String model,
 float temperature)

FireworksAIClient

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

FireworksAIClient

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

FireworksAIClient

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

FireworksAIClient

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